WO2025205334A1 - Operation system and method - Google Patents

Abstract

In the present invention, a processor identifies, on the basis of sensor data received via a communication interface, whether a current situation falls under a stopped vehicle-related scenario, which is a scenario related to traveling near a stopped vehicle that could potentially start moving. If the current situation has been found to fall under a stopped vehicle-related scenario, the processor determines whether to execute avoidance control with respect to the stopped vehicle in accordance with either the type of the stopped vehicle or the behavior of the stopped vehicle. If it was sensed that the stopped vehicle started moving during execution of the avoidance control, the processor determines whether to suspend or continue the avoidance control in accordance with the location or driving speed of a host vehicle with respect to the stopped vehicle.

Description

Driving system and method CROSS-REFERENCE TO RELATED APPLICATIONS

This application is based on Patent Application No. 2024-054721 filed in Japan on March 28, 2024, and the contents of the original application are incorporated by reference in their entirety.

This specification discloses technology for autonomously driving a vehicle.

Patent Document 1 describes technology related to overtaking a preceding vehicle.

Patent No. 6031066

There may be cases where another vehicle is stopped or parked in front of the vehicle, blocking the path of the vehicle. In such a scenario, it may be necessary to drive the vehicle in a way that avoids the other vehicle. However, Patent Document 1 does not consider such a scenario. With the configuration disclosed in Patent Document 1, the autonomous vehicle cannot respond appropriately when there is a stopped vehicle ahead, which may reduce the convenience or sense of security of the vehicle user.

One of the purposes of this disclosure is to provide autonomous driving technology that can respond appropriately to other vehicles that are stopped in front of the vehicle.

The driving system disclosed herein is configured to be able to control the autonomous driving of a vehicle, and includes a communication circuit that receives signals indicative of the external environment, and a processing unit that executes processing related to the autonomous driving of the vehicle based on the signals received by the communication circuit. The processing unit is configured to: determine, based on the signals received by the communication circuit, whether the current situation corresponds to a scenario in which the vehicle is driving near another stopped vehicle; and, based on determining that the current situation corresponds to the scenario, determine a response to the other vehicle depending on the type or behavior of the other vehicle.

Furthermore, the method included in the present disclosure is a method executed by a processor included in a driving system configured to be able to drive its own vehicle autonomously, and includes: determining whether the current situation corresponds to a scenario in which the vehicle is traveling near another stopped vehicle, based on a signal indicating the external environment received by a communication circuit; and, based on the determination that the current situation corresponds to the scenario, determining a response to the other vehicle depending on the type or behavior of the other vehicle.

With the above technology, the behavior of the host vehicle is determined in response to a vehicle stopped in front of the host vehicle (i.e., a stopped vehicle) depending on the type or behavior of that vehicle. This makes it possible to respond appropriately to a vehicle stopped in front of the host vehicle.

Note that the reference symbols in parentheses in the claims indicate a correspondence with the specific means described in the embodiments described below as one aspect, and do not limit the technical scope of this disclosure.

FIG. 1 is a diagram illustrating a vehicle equipped with a driving system. FIG. 2 is a diagram illustrating a hardware configuration of an operation system. FIG. 2 is a diagram illustrating a functional configuration of the driving system. FIG. 10 is a diagram illustrating the functional configuration of a risk confirmation unit. FIG. 10 is a diagram for explaining a vertical safe distance. FIG. 10 is a diagram for explaining a vertical safe distance. FIG. 10 is a diagram for explaining a lateral safe distance. FIG. 2 is a diagram showing a lane-based coordinate system. 10 is a flowchart illustrating a process for deriving assumptions. FIG. 10 is a diagram for explaining a stopped vehicle-related scenario. 10 is a flowchart illustrating an example of the operation of the driving system in a scenario involving a stopped vehicle. FIG. 10 is a diagram illustrating an initial phase of avoidance control. FIG. 10 is a diagram illustrating the middle phase of avoidance control. FIG. 10 is a diagram illustrating a later phase of avoidance control. 10 is a flowchart showing an example of the operation of the driving system during avoidance control. 10 is a flowchart showing an example of the operation of the driving system during avoidance control. 10 is a flowchart showing an example of the operation of the driving system during avoidance control. 10 is a flowchart showing an example of the operation of the driving system during avoidance control. 10 is a flowchart showing an example of the operation of the driving system during avoidance control. 10 is a flowchart illustrating an example of the operation of the driving system in a scenario involving a stopped vehicle. 10 is a flowchart illustrating an example of the operation of the driving system in a scenario where the vehicle is stopped behind a stationary vehicle. 10 is a flowchart showing an example of the operation of a driving system that determines whether to execute avoidance control based on the relationship between the expected stopping time of a stopped vehicle and the avoidance required time. 10 is a flowchart showing an example of the operation of a driving system that stops and resumes avoidance control in response to the behavior of a stopped vehicle. 10 is a flowchart showing an example of the operation of a driving system that changes the inter-vehicle distance depending on the type of preceding vehicle. FIG. 1 is a diagram showing a situation in which a vehicle encounters a stopped vehicle on a road without a center line. FIG. 1 is a diagram showing a situation in which a vehicle encounters a stopped vehicle on a road with multiple lanes in each direction. 27 is a flowchart for explaining an example of operation of the driving system in the situation shown in FIG. 26. FIG. 1 is a diagram illustrating a functional configuration of a driving system according to one embodiment. FIG. 10 is a diagram illustrating a functional configuration of a driving system according to another embodiment.

Embodiments of the present disclosure are described below using the drawings. The present disclosure is not limited to the following embodiments. The configurations disclosed below may be modified in various ways without departing from the spirit of the invention. Various modified examples may be combined as appropriate as long as no technical contradictions arise. The present disclosure also includes configurations that are not explicitly stated and are made by combining multiple modified examples. In the following description, components having the same function may be given the same reference numerals, and detailed descriptions thereof may be omitted. Furthermore, components having the same function may be given the same or similar names, and detailed descriptions thereof may be omitted. When only part of a configuration is mentioned, descriptions given elsewhere may apply to other parts.

(Explanation of terms)
The following explains terms related to the disclosure of this specification, which are included in the embodiments of the specification.

A road user may be a traffic participant on or adjacent to an active road for the purpose of moving from one place to another. Road users may include pedestrians, cyclists, vehicles, and other vulnerable road users. A pedestrian may be a person walking on a sidewalk adjacent to a road. A cyclist may be a person riding a bicycle. A vehicle may be a passenger car, commercial vehicle, bus, etc. A vehicle may be a manually or autonomous vehicle.

A vulnerable road user (VRU) may be a road user not in a vehicle, such as a passenger car, public transport, train, etc. Vulnerable road users may also include unprotected road users, such as cyclists, motorcyclists, pedestrians, people with disabilities, or people with reduced mobility and orientation.

The dynamic driving task (DDT) may be the real-time operational and tactical functions for operating a vehicle in traffic. The DDT may also be all real-time operational and tactical functions for operating a vehicle on a road. Operational functions may include lateral vehicle motion control through steering and longitudinal vehicle motion control through acceleration and deceleration. Tactical functions may include detecting objects or events and responding to them. Responding to detected objects/events may include planning and execution for avoidance, etc.

An ADS feature may be a design-specific functionality of an automated driving system within a specific operational design domain at a given level of automation.

An automated driving system (ADS) may be a collection of hardware and software capable of performing the entire dynamic driving task on a continuous basis, whether or not it is limited to a specific operational design domain.

DDT fallback may be a response by a driver or automated system to either perform the DDT or transition to a minimum risk state after a failure occurs or upon detection of a malfunction or potentially dangerous behavior. DDT fallback may be a method of controlled transition from autonomy to driver or other system control using takeover/fallback conditions and associated use cases. DDT fallback may also be a response by a user to perform the DDT or achieve a minimum risk state after a system failure related to DDT performance or upon departure from the operational design domain, or a response by an automated driving system to achieve a minimum risk state given the same circumstances.

The Minimal Risk Condition (MRC) may be a vehicle state intended to reduce the risk of not being able to complete a given trip. The Minimal Risk Condition may also be a stable, stopped state that a user or automated driving system places on the vehicle after a DDT fallback is performed, to reduce the risk of an accident if a given trip cannot or should not be continued.

An operational design domain (ODD) may be the specific conditions under which a given automated driving system is designed to function. An operational design domain may also be the operating conditions under which a given automated driving system or its functions are specifically designed to function, including, but not limited to, environmental, geographic, time-of-day restrictions, and/or the presence or absence of certain traffic/road characteristic requirements.

Safety of the intended functionality (SOTIF) may be the absence of undue risk due to inadequacies in the intended functionality or its implementation.

A driving policy may be a strategy and rules that define control behavior at the vehicle level.

A scenario may be a description of the temporal relationships between several scenes in a sequence of scenes, including the goals and values in a specific situation influenced by actions and events. A scenario may also be a description of a continuous time series of activities that integrates a subject vehicle, all its external environments, and their interactions in the process of performing a specific driving task.

A safety-relevant object may be any dynamic or static object that may be relevant to the safe performance of a dynamic driving task.

Reasonably foreseeable may mean being technically reliable and having a reliable or measurable probability of occurrence.

A triggering condition may be a specific condition in a scenario that acts as a trigger for a subsequent system response that contributes to unsafe behavior or the failure to prevent, detect, and mitigate reasonably foreseeable indirect misuse.

A Minimal Risk Maneuver (MRM) may be a vehicle movement directed by the automated driving system during DDT fallback to achieve a minimal risk condition.

A safety-related model may be a representation of safety-related aspects of driving behavior based on assumptions about the reasonably foreseeable behavior of other road users. A safety-related model may be an on-board or off-board safety verification or analysis device, a mathematical model, a more conceptual set of rules, a set of scenario-based behaviors, or a combination of these.

A formal model may be a model expressed in formal notation used to verify system performance.

A safety envelope may be a set of limits and conditions within which an (autonomous) driving system is designed to operate, subject to constraints or controls, in order to maintain operation within an acceptable level of risk. A safety envelope may be a general concept that can be used to cover all principles to which a driving policy can adhere, according to which an ego-vehicle operated by an (autonomous) driving system may have one or more boundaries around it.

Response time may be the time it takes a road user in a given scenario to perceive a particular stimulus and begin to execute a response (braking, steering, accelerating, stopping, etc.).

Risk acceptance criteria/criterion are standards that demonstrate the absence of unreasonable levels of risk, and may be, for example, physical parameters that define when a particular behavior is considered undesirable, a maximum number of accidents per hour, or as low as reasonably practicable.

A positive risk balance may be a criterion that demonstrates that a technical solution achieves an acceptable level of residual risk.

A proper response may be an action that is significant to avoid or ameliorate a hazardous situation in a reasonably foreseeable scenario in which other safety-related objects are operating within their expected ranges.

OEDR (object and event detection and response) may be a subtask of the dynamic driving task that involves monitoring the driving environment and executing appropriate responses to such objects and events.

(First embodiment)
<Operation system>
The driving system 9 of this embodiment is a system that realizes functions related to driving the vehicle 1. The driving system 9 may be a vehicle system itself, or may be a component that constitutes part of a vehicle system. Part or all of the driving system 9 may be mounted on the vehicle 1 as shown in FIG. 1 . The vehicle 1 may be referred to as a host vehicle, a host vehicle, or the like. The vehicle 1 may be configured to be capable of wireless communication directly with a roadside device 92. The vehicle 1 may be configured to be capable of communication with other road users, such as a following vehicle 93, directly or indirectly via a communication infrastructure.

Vehicle 1 may be a road user capable of manual driving, such as a four-wheeled car or truck. Vehicle 1 may also be capable of automated driving. Autonomous driving may be referred to as autonomous driving by a driving system 9. Driving is classified into levels according to the extent to which a human driver performs all dynamic driving tasks (DDTs). There may be six automation levels, from 0 to 5, as specified in SAE J3016. At levels 0 to 2, the driver performs some or all of the DDTs. Levels 0 to 2 may be classified as so-called manual driving. Level 0 means that driving is not automated. Level 1 means that the driving system 9 assists the driver. Level 2 means that driving is partially automated. Level 2 may be divided into levels 2.0 and 2.5. At level 2.0, the system provides partial steering assistance and the driver essentially performs the steering. Level 2.5 is a level where the driver is still required to monitor their surroundings, but the driving system 9 essentially performs steering. In this disclosure, vehicle control equivalent to Level 2.5 is also referred to as automated driving with a surrounding monitoring obligation or semi-automated driving.

At levels 3 and above, while the ADS feature is activated, the driving system 9 performs all of the DDT. Levels 3 to 5 may be classified as so-called automated driving. Systems capable of driving at levels 3 and above may be called automated driving systems (ADS). Vehicles equipped with automated driving systems or vehicles capable of driving at levels 3 and above may be called automated vehicles (AV).

Level 3 indicates a state in which driving is conditionally automated. A level 3 autonomous driving system performs DDT but does not perform DDT fallback. That is, at level 3, DDT fallback is performed by a driver who is ready to perform the fallback. Level 4 indicates a state in which driving is highly automated. A level 4 autonomous driving system performs DDT and DDT fallback. A level 4 autonomous driving system can hand over DDT to the driver after reaching a minimum risk condition (MRC) by performing DDT fallback, etc. Handing over DDT between the driving system 9 and a human driver is also known as delegation of authority. Level 5 indicates fully automated driving.

The conditions for executing level 3 and 4 autonomous driving may include some or all of the conditions indicated by the operational design domain (ODD). The ADS function may be defined within the scope of the ODD. The driving system 9 described in this embodiment is a driving system capable of executing level 3 or higher autonomous driving. In other words, the driving system 9 may be capable of executing autonomous driving up to level 3, up to level 4, or even level 5 autonomous driving. The function for implementing level 3 or higher autonomous driving is referred to as the autonomous driving function. The autonomous driving function may be positioned as one of the applications provided by the driving system 9.

The driving system 9 provides functions such as autonomous driving to the vehicle user of the vehicle 1 that is capable of participating in public road traffic. The vehicle user may be the driver of the vehicle 1. The vehicle user may be a passenger riding in the vehicle 1. If the vehicle 1 is a POV (Personally Owned Vehicle), the vehicle user may be the owner of the vehicle 1. If the vehicle 1 is used for MaaS (Mobility as a Service), the vehicle user may be an operator such as an operations manager that manages the operation of the vehicle 1.

The architecture of the driving system 9 may be selected to enable an efficient safety of the intended functionality (SOTIF) process. The architecture of the driving system 9 may be based on the sense-plan-act model. The sense-plan-act model comprises a sense element, a plan element, and an act element as its main system elements. The sense element, plan element, and act element interact with each other. Here, sense may be replaced with perception, plan may be replaced with determine, and act may be replaced with control.

At the technical level (or from a technical perspective), such an operating system 9 is implemented with at least a plurality of sensors 40 corresponding to the sensing function, at least one processing system 50 corresponding to the planning function, and a plurality of motion actuators 60 corresponding to the action function. At the functional level (or from a functional perspective), the sensing function, planning function, and action function are implemented. (See also Figures 3 and 4).

In detail, a detection unit 10 may be constructed in the operation system 9 as an entity that realizes a detection function, mainly consisting of multiple sensors 40 and a processing system 50. The processing system 50 related to the detection function may be configured to process detection information from the sensors 40 and generate an environmental model based on the detection information. A planning unit 20 and a risk confirmation unit 26 may be constructed in the operation system 9 mainly consisting of such a processing system 50. The planning unit 20 is an entity that realizes the planning function. The processing system 50 may also be capable of outputting control signals (e.g., drive signals) for multiple motion actuators 60. A behavior unit 30 may be constructed in the operation system 9 as an entity that realizes a behavior function, mainly consisting of such a processing system 50 and multiple motion actuators 60.

Here, the detection unit 10 may be realized in the form of a detection system serving as a subsystem distinguishable from the planning unit 20 and the action unit 30. The planner 20 may be realized in the form of a planning system serving as a subsystem distinguishable from the detection unit 10 and the action unit 30. The planning system may include a risk confirmation function. The risk confirmation function may be mounted in the operation system 9 independently of the detection unit 10, the planning unit 20, and the action unit 30. The action unit 30 may be realized in the form of an action system serving as a subsystem distinguishable from the detection unit 10 and the planner 20. The detection system, planning system, and action system may constitute components independent of each other. The term "subsystem" may be replaced with a module, unit, device, component, etc.

The detection unit 10 is responsible for detection functions, including localization (e.g., location estimation) of road users such as the vehicle 1 and other vehicles. The detection unit 10 detects the external environment, internal environment, vehicle state, and even the state of the driving system 9 of the vehicle 1. The detection unit 10 may fuse the detected information to generate an environmental model. The environmental model may also be referred to as a world model. The planning unit 20 applies the objectives and driving policy to the environmental model generated by the detection unit 10 to derive control actions. The action unit 30 executes the control actions derived by the planning unit 20.

<Physical Architecture>
An example of a physical architecture of a driving system 9 will be described with reference to FIG. 2 . The driving system 9 includes a plurality of sensors 40, a plurality of motion actuators 60, a plurality of HMI devices 70, and a processing system 50. HMI stands for Human Machine Interface. These components can communicate with each other via one or both of wireless and wired connections. These components may also be able to communicate with each other through an in-vehicle network such as CAN (registered trademark) or Ethernet (registered trademark). Communication between devices may be achieved by any type of communication, including wired and wireless.

The multiple sensors 40 include one or more external environment sensors 41. Furthermore, the multiple sensors 40 may include one or more internal environment sensors 42. Furthermore, the multiple sensors 40 may include one or more communication systems 43. Furthermore, the multiple sensors 40 may include a map database 44. The combination of devices included in the multiple sensors 40 may be designed as appropriate. In the present disclosure, data indicative of the environment outside or inside the vehicle that is perceived (or acquired) by the sensor 40 is also referred to as sensor data.

The external environment sensor 41 may include a sensor that detects objects present in the external environment of the vehicle 1. The external environment sensor 41 may include an object detection type sensor. Object detection type external environment sensors 41 include, for example, a camera, LiDAR (Light Detection and Ranging / Laser Imaging Detection and Ranging), laser radar, millimeter wave radar, ultrasonic sonar, acoustic sensors, etc. The acoustic sensor generates an electrical signal corresponding to external sound that is sound outside the vehicle. The acoustic sensor may be, for example, a condenser microphone. The output signal of the acoustic sensor can be used to detect warning sounds output by emergency vehicles. The driving system 9 may be implemented with a combination of multiple types of external environment sensors 41 to monitor the front, sides, and rear directions of the vehicle 1.

Furthermore, the external environment sensor 41 may detect atmospheric conditions and weather conditions in the environment external to the vehicle 1. The external environment sensor 41 may include a condition detection type sensor. The condition detection type external environment sensor 41 may include at least one of an outside air temperature sensor, a temperature sensor, and a raindrop sensor.

The internal environment sensor 42 may detect specific physical quantities related to the motion of the vehicle 1 (hereinafter referred to as motion physical quantities). The internal environment sensor 42 may include a motion physical quantity detection type sensor. The motion physical quantity detection type internal environment sensor 42 may include at least one of a speed sensor, an acceleration sensor, a gyro sensor, etc. The internal environment sensor 42 may detect the state of an occupant of the vehicle 1. The internal environment sensor 42 may include an occupant detection type sensor. The occupant detection type internal environment sensor 42 may include at least one of an actuator sensor, an interior monitor, a biological sensor, a seating sensor, an interior equipment sensor, etc. The interior monitor here may be a sensor or system that monitors the vehicle user (e.g., the driver) within the vehicle cabin. The actuator sensor is a sensor that detects the state of the occupant's operation of the motion actuator 60 related to the motion control of the vehicle 1. The actuator sensor may include at least one of an accelerator sensor, a brake sensor, a steering sensor, etc.

The communication system 43 obtains communication data usable by the driving system 9 from an external system via wireless communication. The external system refers to any other system that exists in the external environment of the vehicle 1. The communication system 43 may receive positioning signals from GNSS (Global Navigation Satellite System) satellites that exist in the external environment of the vehicle 1. The positioning type communication device in the communication system 43 may be a GNSS receiver, etc.

The communication system 43 may transmit and receive communication signals to and from an external system such as a server 96. The V2X-type communication device in the communication system 43 may be a dedicated short range communications (DSRC) communication device, a cellular V2X (C-V2X) communication device, or the like. Examples of communication with the V2X system include communication with the communication system of another vehicle (V2V), communication with the roadside device 92 (V2I), communication with a pedestrian's mobile terminal (V2P), and communication with a network such as a cloud server (V2N). The roadside device 92 may be infrastructure equipment such as a communication device installed in a traffic light. The architecture of V2X communication, including V2I communication, may be an architecture specified in ISO 21217, ETSI TS 102 940-943, IEEE 1609, etc.

The communication system 43 may receive vehicle status messages from other vehicles 2. The vehicle status messages may include the speed of the sender (other vehicles 2), current position, turn signal operation status, acceleration, etc. The vehicle status messages may include at least one of the shift position, brake pedal on/off, accelerator pedal on/off, and steering angle. The vehicle status messages may be CAM (Cooperative Awareness Message) or BSM (Basic Safety Message). Data received by the wireless communication device 15 may also be included in the sensor data. The communication system 43 corresponds to a wireless communication device.

Furthermore, the communication system 43 may send and receive communication signals to and from a mobile terminal 91. The mobile terminal 91 may be a smartphone, wearable device, tablet, etc. present in the vehicle. The mobile terminal 91 may be a smartphone or the like carried by the vehicle user. A terminal communication type communication device in the communication system 43 may be a Bluetooth (registered trademark) device, a Wi-Fi (registered trademark) device, an infrared communication device, etc. If the vehicle user's mobile terminal 91 has been associated with the vehicle 1 in advance, the communication system 43 may send and receive communication signals to and from a mobile terminal 91 present in the external environment.

The map DB 44 is a database that stores map data that can be used by the driving system 9. The map DB 44 is configured using at least one type of storage medium, such as a semiconductor memory, a magnetic medium, or an optical medium. The map DB 44 may include a database of a navigation unit that navigates the driving route to the destination of the vehicle 1. The map DB 44 may include a database of probe data (PD) maps generated using PD collected from each vehicle. The map DB 44 may include a database of high-precision maps with a high level of accuracy that are primarily used in autonomous driving system applications. The map DB 44 may include a database of parking lot maps that include detailed parking lot information, such as parking space information, that is used in autonomous parking or parking assistance applications.

The map DB 44 suitable for the driving system 9 may acquire and store the latest map data by communicating with a map server via the communication system 43. The map data is converted into two-dimensional or three-dimensional data representing the external environment of the vehicle 1. Such map data may include road data representing at least one of the position coordinates, shape, road surface conditions, and standard driving paths of road structures. The map data may also include marking data representing the position coordinates and/or shape of features such as road signs and road markings attached to roads. The marking data included in the map data may represent traffic signs, arrow markings, lane markings, stop lines, directional signs, landmark beacons, business signs, line pattern changes, etc. The map data may also include structure data representing at least one of the position coordinates and shapes of buildings and traffic lights facing the road. The marking data included in the map data may represent street lights, road edges, reflectors, poles, etc.

The motion actuator 60 is capable of controlling vehicle motion based on an input control signal. The drive-related motion actuator 60 is a power train including at least one of an engine and a drive motor. The braking-related motion actuator 60 may be a brake actuator. The steering-related motion actuator 60 may be a steering actuator.

The HMI device 70 is a device that realizes human-machine interaction, which is the interaction between the user of the vehicle 1 and the driving system 9. The driving system 9 may include multiple HMI devices 70. Of the multiple HMI devices 70, the part that realizes the operation input function by the occupant may be part of the detection unit 10. Of the multiple HMI devices 70, the part that realizes the information presentation function may be part of the action unit 30. On the other hand, the function realized by the HMI device 70 may be positioned as a function independent of the detection function, planning function, and action function.

The HMI device 70 may include an operation input device 70a that can input user operations to transmit the will or intention of the user of the vehicle 1 to the driving system 9. The operation input type HMI device 70 may be an accelerator pedal, brake pedal, shift lever, steering wheel, turn signal lever, mechanical switch, or a touch panel such as a navigation unit. Of these, the accelerator pedal controls the powertrain as a motion actuator 60. The brake pedal controls a brake actuator as a motion actuator 60. The steering wheel controls a steering actuator as a motion actuator 60. The operation input device 70a outputs an operation signal that corresponds to the operation of the vehicle user to the processing system 50.

The HMI device 70 may include an information presentation device 70b that presents visual information, auditory information, tactile information, or the like to the user of the vehicle 1. The HMI device 70 may include a visual information presentation device 70b, an auditory information presentation device 70b, a tactile information presentation device 70b, or a combination thereof. The visual information presentation type HMI device 70 may be, for example, a meter display, a navigation unit, a CID (center information display), a HUD (head-up display), or an illumination unit.

The HMI device 70 that presents auditory information may be a speaker or a buzzer, etc. The HMI device 70 that presents tactile information may be a steering wheel vibration unit, a driver's seat vibration unit, a steering wheel reaction force unit, an accelerator pedal reaction force unit, a brake pedal reaction force unit, an air conditioning unit, etc.

Furthermore, the HMI device 70 may realize HMI functions linked to a mobile terminal 91 such as a smartphone by mutually communicating with the terminal via the communication system 43. The vehicle user's mobile terminal 91 may be an additional or alternative information presentation device 70b. The driving system 9 may display information of the driving system 9 on the screen of the mobile terminal 91 via the communication system 43. Meanwhile, the HMI device 70 may present information obtained from the mobile terminal 91 to the vehicle user. The mobile terminal 91 may be used as an additional or alternative operation input device 70a.

Furthermore, the HMI device 70 may include an external HMI device that presents visual information, auditory information, and other information to other road users in the external environment of the vehicle 1. External HMI devices include, for example, turn signal lamps (in other words, direction indicators), hazard lamps, external displays, speakers, etc. An external display is a display whose display surface faces outside the vehicle 1. The external display may be provided on the rear window, side window, or side of the vehicle body, etc.

The processing system 50 may be an integrated processing system that performs processing related to the detection function, processing related to the planning function, and processing related to the action function in an integrated manner. The integrated processing system 50 may also perform processing related to the HMI device 70. A processing system dedicated to the HMI may be provided separately from the processing system 50. The processing system dedicated to the HMI may be an integrated cockpit system that performs processing related to each HMI device 70 in an integrated manner. The processing system 50 may be provided by an in-vehicle platform that can be used generally in AVs.

The processing system 50 may have at least one processing unit corresponding to processing related to the detection function, at least one processing unit corresponding to processing related to the planning function, and at least one processing unit corresponding to processing related to the behavioral function, separately.

The processing system 50 has an external communication interface 52, which is a communication interface for communicating with external devices. The external communication interface 52 is connected to at least one component related to processing by the processing system 50 via at least one of, for example, a LAN (Local Area Network), a wire harness, an internal bus, and a wireless communication circuit. The at least one component connected to the external communication interface 52 may be at least one component from a variety of components, such as a sensor 40, a motion actuator 60, and an HMI device 70. The external communication interface 52 may include at least one of a circuit for wired communication and a circuit for wireless communication.

The processing system 50 includes a main unit 51 that is primarily composed of one or more dedicated computers. By using the main unit 51, the processing system 50 may realize functions such as a detection function, a planning function, and an action function. The main unit 51 may also be referred to as an operation control device.

One of the one or more dedicated computers that make up the main unit 51 may be an integrated ECU that integrates the driving functions of the vehicle 1. The main unit 51 may include a determination ECU that determines DDT. The main unit 51 may include a monitoring ECU that monitors the driving of the vehicle 1. The main unit 51 may include an evaluation ECU that evaluates the driving of the vehicle 1. The main unit 51 may include a navigation ECU that navigates the driving route of the vehicle 1.

The dedicated computer constituting the main unit 51 may be a locator ECU that estimates the position of the vehicle 1. The dedicated computer may be an image processing ECU that processes image data detected by the external environment sensor 41. The dedicated computer may be an actuator ECU that controls the motion actuator 60 of the vehicle 1. The dedicated computer may be an HCU (HMI Control Unit) that comprehensively controls the HMI device 70. The one or more dedicated computers constituting the main unit 51 may include at least one external computer provided in an external center or mobile terminal 91 that can communicate via the communication system 43.

The dedicated computer that constitutes the main unit 51 has memory 51a and processor 51b. Memory 51a is a storage medium that non-temporarily stores computer programs and data that can be read by processor 51b. Memory 51a may include at least one type of storage medium, such as semiconductor memory, magnetic media, and optical media. Memory 51a may also include a rewritable volatile storage medium such as RAM (Random Access Memory). The programs stored in memory 51a may be programs for realizing at least some of the functions of the main unit 51, shown as blocks in FIG. 3. Processor 51b may include at least one type of core from a CPU (Central Processing Unit), GPU (Graphics Processing Unit), DFP (Data Flow Processor), and RISC (Reduced Instruction Set Computer)-CPU.

The dedicated computer that constitutes the main unit 51 may be a system on a chip (SoC) that integrates the memory 51a, processor 51b, and interface into a single chip. The dedicated computer may be constructed using at least one SoC.

The dedicated computer constituting the main unit 51 may include a communication interface 51c for communicating with other elements constituting the processing system 50. The communication interface 51c may include a circuit compatible with a communication method with other devices/circuits. The communication interface 51c may be a so-called input/output circuit or input/output port. The communication interface 51c may support any method of wired or wireless communication. Part or all of the external communication interface 52 may be included in the communication interface 51c. The communication interface 51c, the external communication interface 52, or both, correspond to the communication circuitry for the processor 51b. The risk confirmation unit 53, recording device 55, and software management unit 57, described below, may also each have a circuit equivalent to the communication interface 51c. Multiple units may be configured to share the communication interface 51c.

Furthermore, the processing system 50 may include at least one database for executing DDT. The database may be configured to include at least one type of non-transitory tangible storage medium, such as semiconductor memory, magnetic media, or optical media, and an interface that allows the main unit 51 and the like to access the storage medium.

The database for executing DDT may be a scenario database (hereinafter referred to as scenario DB) 59. The database may be a rule database (hereinafter referred to as rule DB) 58. At least one of the scenario DB 59 and the rule DB 58 may be configured integrally with the main unit 51. At least one of the scenario DB 59 and the rule DB 58 may not be provided in the processing system 50, but may be provided independently in the operation system 9. At least one of the scenario DB 59 and the rule DB 58 may be provided in an external system existing in the external environment, and configured to be accessible from the processing system 50 via the communication system 43.

Scenario DB 59 has a scenario catalog that stores multiple scenarios used in driving vehicle 1. Each scenario is assigned a unique scenario ID. The multiple scenarios included in the catalog may include a scenario in which the vehicle travels near a vehicle (e.g., a bus) that is stopped on the road and has the potential to depart. The multiple scenarios may also include a scenario in which the vehicle travels next to other road users, a scenario in which the vehicle travels behind other road users, a scenario in which the vehicle's path intersects with a VRU crossing the road, etc.

The driving system 9 can apply the situation in which the vehicle 1 is placed to one scenario or a combination of multiple scenarios selected from multiple scenarios. The scenario DB 59 may store multiple scenarios including at least one of a functional scenario, a logical scenario, and a concrete scenario. A functional scenario defines the highest-level qualitative scenario structure. A logical scenario is a scenario in which a quantitative parameter range is assigned to a structured functional scenario. A concrete scenario defines the safety judgment boundary that distinguishes between safe and unsafe states.

The rule DB 58 stores a rule set used for driving the vehicle 1. The rule set may include multiple rules. The rule set may also include a priority structure for the set of rules that is set based on the relative importance of the multiple rules. The rule set may also be an implementation of guidelines for strategic driving of the vehicle 1.

The multiple rules may include rules based on laws, regulations, and combinations thereof. The multiple rules may include rules based on preferences that are not influenced by laws, regulations, etc. The multiple rules may include rules based on exercise behavior based on past experience. The multiple rules may include rules based on characterization of the exercise environment. The multiple rules may include rules based on ethical concerns. The multiple rules may include rules based on basic principles of a safety model (e.g., the five principles of the RSS model). The multiple rules may include traffic rules. The traffic rules may be rules stipulated in the Road Traffic Act, or may be rules based on national or local customs.

The traffic rules and other rules stored in the rule DB 58 may be considered as information provided by the detection unit 10 to the planning unit 20 via the detection function, similar to the map information obtained from the map DB 44.

The processing system 50 may also include a recording device 55 that records at least one of sensing information, planning information, and behavioral information. The recording device 55 sequentially records event data related to the driving task of the vehicle 1. The event data is data that records events encountered by the vehicle 1. The event data may include at least one type of information related to the driving task, such as (1) information related to the operation of the motion actuators 60, (2) information related to the route or trajectory traversed or planned by the vehicle 1, (3) information related to the scenario encountered by the vehicle 1, (4) information related to the automation level or delegation of authority of the vehicle 1, and (5) information related to the execution of the DDT fallback or MRM of the vehicle 1.

The recording device 55 may include one or more large-capacity storage media 55c. The storage media 55c may include at least one type of storage medium selected from the group consisting of semiconductor memory, magnetic media, and optical media. The storage media 55c may be mounted on a board in a form that is not easily detachable or replaceable. The storage medium 55c may be an eMMC (embedded Multi Media Card) that uses flash memory, or the like. At least one of the multiple storage media 55c may be detachable and replaceable from the recording device 55. The storage medium 55c may be, for example, an SD card.

At least one of the recording device 55 and the storage medium 55c may correspond to an EDR (Event Data Recorder) or a DSSAD (Data Storage System for Automated Driving). The recording device 55 may have a function for selecting information to record from the event data. In this case, the recording device 55 may have a recording computer as a dedicated computer.

The recording computer has memory 55a and processor 55b. Memory 55a may include a storage medium that non-temporarily stores computer programs and data that can be read by processor 55b. Memory 55a may also include a rewritable volatile storage medium such as RAM. The recording computer may be an SoC in which memory 55a, processor 55b, and an interface are integrated into a single chip. The recording computer may have an SoC as a component.

The recording device 55 may access the storage medium 55c and perform recording in accordance with data write commands from each part of the driving system 9. The recording device 55 may also determine the information transmitted over the in-vehicle network, and, based on the judgment of the processor 55b provided in the recording device 55, access the storage medium 55c and perform recording.

Such a recording device 55 may not be provided in the processing system 50, but may be provided independently in the operating system 9. Part or all of the recording device 55 may be provided in an external system existing in the external environment, and configured to be accessible from the processing system 50 via the communication system 43.

Furthermore, the processing system 50 may include at least one risk confirmation unit 53. The risk confirmation unit 53 may be one aspect of an on-board implementation of RSS (Responsibility Sensitive Safety) as a safety model. The risk confirmation unit 53 may be an on-board checker for the planning function implemented by a dedicated computer. The risk confirmation unit 53 implements the risk confirmation section 26, which realizes the risk confirmation function, by hardware independent of the planning section 20.

The risk confirmation unit 53 may be primarily composed of a dedicated computer having memory 53a and processor 53b. The memory 53a may include a storage medium that non-temporarily stores computer programs and data that can be read by the processor 53b. The memory 53a may include a rewritable volatile storage medium such as RAM. The dedicated computer that constitutes the risk confirmation unit 53 may be an SoC that integrates the memory 53a, processor 53b, and interface into a single chip.

In this way, processing system 50 includes memories 51a, 53a, and 55a that store software. Processors 51b, 53b, and 55b are configured to operate the software to achieve autonomous driving, with authority transferable between the system itself and the user. The software here may be a computer program used in driving system 9. The software may include parameters for the computer program used in driving system 9. The software may include a trained model, sometimes referred to as AI, implemented by, for example, a neural network, etc., used in driving system 9.

The processing system 50 may include at least one software management unit 57. The software management unit 57 realizes software management functions. The software management unit 57 manages various software used within the driving system 9, such as the main unit 51. The software management unit 57 may also manage software used by the software management unit 57 itself. The software management unit 57 may also manage all software used in the vehicle 1. Software management may include software version management, download processing, installation processing, uninstallation processing, update processing, rollback processing, etc. Software management may also include software testing.

The software management unit 57 may be configured using a dedicated computer having memory 57a and processor 57b to realize the software management function. The memory 57a may include a storage medium that non-temporarily stores computer programs and data that can be read by the processor 57b. The memory 57a may also be provided with a rewritable volatile storage medium such as RAM. "SW" in Figure 2 stands for software.

Processors 51b, 53b, etc. execute processing related to the autonomous driving of the vehicle based on signals received via communication interface 51c or external communication interface 52. The processing related to the autonomous driving of the vehicle may be at least part of the processing executed by the detection unit 10, planning unit 20, action unit 30, and risk confirmation unit 26, which will be described in detail next. A configuration including either or both of processors 51b and 53b corresponds to a processing unit. The processing unit may include a processor and a memory.

<Logical architecture for autonomous driving>
3 and 4 show an example of a logical architecture in the driving system 9. Here, the description will focus on the processing by a computer program executed during automated driving at level 3 or higher. The detection unit 10 may include an environment recognition unit 11, a self-location recognition unit 12, and an internal recognition unit 13 as functional modules corresponding to sub-functions that further classify the detection function. The environment recognition unit 11, the self-location recognition unit 12, and the internal recognition unit 13 may also be realized by the processor 51b executing a computer program.

The environment recognition unit 11 individually processes the information obtained from each sensor 40 (sometimes referred to as sensor data) and recognizes the external environment, including other road users. The environment recognition unit 11 individually processes sensor data related to the external environment detected by each external environment sensor 41. The sensor data may be sensor data provided by millimeter-wave radar, sonar, LiDAR, etc. The environment recognition unit 11 may generate relative position data including the direction, size, and distance of an object relative to the vehicle 1 from the raw data received from the external environment sensors 41.

Furthermore, the sensor data may be image data provided from a camera, LiDAR, or the like. The image data may be a video signal. The environment recognition unit 11 processes the image data and extracts objects that appear within the angle of view of the image. Object extraction may include estimating the direction, size, and distance of the object relative to the vehicle 1. Object extraction may also include classifying the object using semantic segmentation.

Furthermore, the environment recognition unit 11 processes information acquired through the V2X function of the communication system 43. The environment recognition unit 11 processes information acquired from the map DB 44.

The environment recognition unit 11 may be further divided into multiple sensor recognition units, each optimized for a single sensor group. When a sensor recognition unit is associated with recognizing information from a single sensor group, it may fuse the information from that sensor group.

The self-location recognition unit 12 performs localization of the vehicle 1. The self-location recognition unit 12 acquires global position data of the vehicle 1 from the communication system 43 (e.g., a GNSS receiver). In addition, the self-location recognition unit 12 may acquire position information of objects extracted by the environment recognition unit 11. The self-location recognition unit 12 also acquires map information from the map DB 44. The self-location recognition unit 12 may integrate two or more types of information from among the global position data, object position information, map information, and other information to estimate the position of the vehicle 1 on the map. In this disclosure, information indicating the position of the vehicle 1 on the map estimated by the self-location recognition unit 12 is also referred to as estimated information of the position on the map.

The internal recognition unit 13 processes the sensor data detected by each internal environment sensor 42 and recognizes the vehicle state. The vehicle state may include the state of the physical motion quantities of the vehicle 1 detected by a speed sensor, acceleration sensor, gyro sensor, etc. The vehicle state may also include at least one of the following: the user's state, the user's operation state of the motion actuator 60, and the switch state of the HMI device 70.

The planning unit 20 may include a prediction unit 21, an operation planning unit 22, and a mode management unit 23 as functional modules corresponding to sub-functions that further classify the planning function. The prediction unit 21, the operation planning unit 22, and the mode management unit 23 may also be realized by the processors 51b and 53b executing computer programs.

The prediction unit 21 acquires information about the external environment recognized by the environment recognition unit 11 and the self-position recognition unit 12, the vehicle state recognized by the internal recognition unit 13, etc. The prediction unit 21 may interpret the environment based on the acquired information and estimate the current situation in which the vehicle 1 is located. The situation here may be an operational situation or may include the operational situation.

The prediction unit 21 may interpret the environment and predict the behavior of objects such as other road users. The objects in this case may be safety-relevant objects. The prediction of behavior in this case may include at least one of predicting the object's speed, predicting the object's acceleration, and predicting the object's trajectory. The prediction of behavior may be performed based on reasonably foreseeable assumptions. Information generated by the prediction unit 21 is also referred to as prediction information hereinafter. Furthermore, the prediction unit 21 may estimate the user's intention based on the predicted behavior, predicted potential hazards, and the acquired vehicle state. Information indicating the estimated result of the user's intention is also referred to as user intention information in this disclosure.

The driving planning unit 22 plans autonomous driving of the vehicle 1 based on at least one type of information such as estimated information on a map position, forecast information, user intention information, and functional constraint information described below. The driving planning unit 22 provides a route planning function, a behavior planning function, and a trajectory planning function. The route planning function is a function that plans at least one of a route to a destination and a medium-distance lane plan based on estimated information on a map position and destination information. The route planning function may further include a function that determines at least one of a lane change request and a deceleration request based on the medium-distance lane plan. Here, the route planning function may be a mission/route planning function in strategic functions, and may be a function that outputs a mission plan and a route plan. The strategic functions here may be functions that decide whether to operate or not, set a route to a destination, and adjust or select a rough operating schedule.

The behavior planning function is a function that plans the behavior of vehicle 1 based on at least one of the route to the destination, mid-distance lane planning, lane change request, deceleration request, prediction information, user intention information, and function constraint information. The behavior planning function may include a function that generates conditions related to state transitions of vehicle 1. The conditions related to state transitions of vehicle 1 may be triggering conditions. The conditions related to state transitions may include fallback conditions for executing DDT fallbacks.

The behavior planning function may include a function to determine the state transitions of the application that realizes DDT based on these conditions, and further a function to determine the state transitions of the driving action. As a result, the driving planning unit 22 plans the execution of DDT fallback, and if this does not involve the delegation of authority, the driving planning unit 22 may further execute a minimum risk maneuver (MRM) together with the motion control unit 31 to transition the vehicle 1 to a minimum risk state. In many cases, the minimum risk state may be a state in which the vehicle is stopped outside the lane (e.g., on the shoulder) or within the lane, but is not limited to this. The minimum risk state may also be a state in which the vehicle is following a preceding vehicle, or a state in which the vehicle is continuing to travel at a constant speed with its hazard lights on. The MRM plan may be created by the trajectory planning function instead of the behavior planning function. Information indicating the state transitions of the application determined by the driving planning unit 22 is also referred to as application state transition information.

Furthermore, the behavior planning function may include a function for determining longitudinal constraints on the path of vehicle 1 and lateral constraints on the path of vehicle 1 based on this state transition information. The behavior planning function may be a tactical behavior plan in the DDT function, and may output tactical behavior.

The trajectory planning function is a function that plans the driving trajectory of the vehicle 1 based on prediction information, longitudinal constraints on the path, and lateral constraints on the path. The trajectory planning function may include a function that generates a path plan. The path plan may include a speed plan, or the speed plan may be generated as a plan independent of the path plan. The trajectory planning function may include a function that generates multiple path plans and selects the optimal path plan from the multiple path plans, or a function that switches between path plans. The trajectory planning function may further include a function that generates backup data for the generated path plan. The trajectory planning function may be a trajectory planning function in the DDT function, and may output a trajectory plan. In the operation planning unit 22, the terms path and trajectory may be interchangeable. The operation planning unit 22 is configured to be able to output trajectory planning information, which is information indicating the trajectory plan (in other words, the path plan), to the motion control unit 31.

The mode management unit 23 monitors the driving system 9 and sets restrictions on driving-related functions. The mode management unit 23 may manage the operating mode of the driving system 9, for example, the state of the automation level. Management of the automation level may include management of switching between manual driving and automated driving, i.e., the transfer of authority between the user and the driving system 9, in other words, the takeover of driving. The mode management unit 23 may determine and implement a change in the automation level based on an operation signal input from the operation input device 70a. When the automation level is switched to a state below level 2, the mode management unit 23 may control the activation state of a driving assistance application corresponding to that automation level.

The driving system 9 of this embodiment may have operating modes corresponding to automation levels 0 to 4. That is, the driving system 9 is configured to be able to switch between multiple operating modes including level 0 mode, level 1 mode, level 2 mode, level 3 mode, and level 4 mode. The operating modes of the driving system 9 may be interpreted as operating modes of the main unit 51 or processor 51b. The operating modes may also be referred to as driving modes. The driving system 9 may have an operating mode corresponding to automation level 5. The combination of operating modes provided by the driving system 9 may be changed as appropriate.

Level 0 mode may be referred to as manual driving mode. Even in level 0 mode, the driving system 9 may perform processing to mitigate collision damage or avoid a collision, such as automatic emergency braking (AEB: Advanced Emergency Braking) or automatic steering avoidance (AES: Advanced Emergency Steering). Even in level 0 mode, the driving system 9 may continue to perform driving environment recognition processing in the background so that it can quickly start automatic driving or driving assistance in response to a request from the driver. Level 0 mode may also be a mode in which the driving system 9 stops operating completely.

Level 2 mode may be an operating mode that executes control equivalent to automation level 2.5. Level 2 mode may be subdivided into hands-on level 2 mode and hands-off level 2 mode. Hands-on level 2 mode is an operating mode that corresponds to automation level 2.0 and requires hands-on control by the vehicle user. Hands-off level 2 mode is an operating mode that corresponds to automation level 2.5 and allows hands-off control by the vehicle user. In this disclosure, hands-on means holding the steering wheel. Hands-off means taking your hands off the steering wheel. Eyes-on means monitoring the area outside the vehicle (mainly ahead) related to the direction of movement of the vehicle. Eyes-off means taking your eyes off the area outside the vehicle related to the direction of movement of the vehicle.

The mode management unit 23 may monitor the status of subsystems related to the driving system 9 and determine whether the system is malfunctioning. System malfunctions may include errors, unstable operating states, system failures, and breakdowns. The mode management unit 23 may determine a mode that conforms to the user's intention based on user intention information. The mode management unit 23 may set constraints on driving functions based on at least one of the system malfunction determination results, mode determination results, vehicle status, sensor abnormality (or sensor failure) signals output from the sensors 40, application state transition information, and trajectory planning. Information indicating constraints on driving functions is also referred to as function constraint information in this disclosure. The function constraint information generated by the operation of the mode management unit 23 can be referenced by the driving plan unit 22.

Furthermore, the mode management unit 23 may have the overall function of determining longitudinal constraints on the path of vehicle 1 and lateral constraints on the path of vehicle 1, in addition to constraints on driving functions. In this case, the operation planning unit 22 plans behavior and trajectories in accordance with the constraints determined by the mode management unit 23.

If the risk confirmation function is implemented as part of the planning unit 20, the risk confirmation function may be implemented as part of the functions realized by the prediction unit 21, operation planning unit 22, and mode management unit 23. On the other hand, the risk confirmation function may be implemented as a function independent of the planning unit 20 (see also Figure 4).

The behavior unit 30 may include a motion control unit 31 and an HMI output unit 71 as functional modules corresponding to sub-functions that further classify the behavioral functions. The motion control unit 31 and the HMI output unit 71 may each be realized by the processor 51b executing a computer program. The motion control unit 31 controls the motion of the vehicle 1 based on the trajectory plan provided by the driving plan unit 22. Specifically, the motion control unit 31 generates accelerator request information, shift request information, brake request information, and steering request information according to the trajectory plan, and outputs this to the motion actuator 60. The accelerator request information, shift request information, brake request information, and steering request information may function as control signals (in other words, control commands) for the motion actuator 60. The accelerator request information, shift request information, brake request information, and steering request information may be referred to as an accelerator request signal, a shift request signal, a brake request signal, and a steering request signal.

Here, the motion control unit 31 can directly obtain the vehicle state recognized by the detection unit 10 (particularly the internal recognition unit 13), such as at least one of the current speed, acceleration, and yaw rate of the vehicle 1, from the detection unit 10 and reflect this in the motion control of the vehicle 1.

The HMI output unit 71 outputs information about the HMI based on at least one of prediction information, user intention information, application state transition information, trajectory planning information, and function constraint information. The HMI output unit 71 may manage vehicle interactions. The HMI output unit 71 may generate an information presentation request based on the management status of vehicle interactions and control the information presentation function of the HMI device 70. Furthermore, the HMI output unit 71 may generate control requests for the wipers, sensor washing device, headlights, and air conditioning device based on the management status of vehicle interactions and control these devices.

<Risk confirmation>
Next, the risk confirmation function will be described in detail. An example in which the risk confirmation unit 26 is implemented independently of the planning unit 20 as shown in FIG. 4 will be described below. Such a risk confirmation unit 26 may be realized by the processor 53b of the risk confirmation unit 53 executing a computer program. Note that the risk confirmation function may also be realized by the processor 51b of the main unit 51 executing a computer program. The functional layout within the operation system 9 may be changed as appropriate.

The driving system 9 may implement a safety model for automated driving to realize the risk confirmation function. The safety model is a model for demonstrating that there are no unacceptable risks within a specific operational design domain. The safety model may correspond to a safety driving model, a safety-related model, or a formal model. The safety model in this embodiment may be, for example, an RSS model. In other embodiments, the safety model may be other models such as the SFF (Safety Force Field) model or Rulebooks, a more generalized model, or a composite model that combines multiple models.

The RSS model employs five rules (five principles). The first rule is, "Do not hit someone from behind." The second rule is, "Do not cut-in recklessly." The third rule is, "Right-of-way is given, not taken." The fourth rule is, "Be careful of area another one, you must do it." The fifth rule is, "If you can avoid an accident without causing another one, you must do it." These rules may correspond to driving policies.

Based on the five rules, particularly Rules 1 and 2, a safety envelope may be defined. For example, the safety envelope may refer to the longitudinal and lateral safety distances themselves relative to other road users, or it may refer to the conditions or concepts for calculating these safety distances. The safety distance can be said to be an example of a geometric approach to risk identification.

The longitudinal safety distance dmin may be the safety distance from the preceding vehicle FV. As shown in Figure 5, such longitudinal safety distance dmin may be the distance that will not result in a rear-end collision when the preceding vehicle FV, while traveling at speed vf, brakes at maximum deceleration βmax to a stop, and the following vehicle RV, as vehicle 1, accelerates with a response time ρ and maximum acceleration αmax, and then brakes at minimum deceleration βmin to a stop. The maximum acceleration αmax, maximum deceleration βmax, and minimum deceleration βmin may be understood as absolute values.

Here, the braking distance (Dfbrk) of the preceding vehicle FV is physically expressed by the following equation 1. In the equation, vf is the speed of the following vehicle RV at the time the preceding vehicle FV begins to brake (i.e., the initial speed).

The free running distance (Drrxn) of the vehicle 1 is expressed by the following equation 2.

The braking distance (Drbrk) of the vehicle 1 is expressed by the following equation 3.

Such a longitudinal safety distance dmin from the preceding vehicle may be expressed as the distance obtained by adding the braking distance (Drbrk) of vehicle 1 to the free running distance (Drrxn) of vehicle 1 and subtracting the braking distance (Dfbrk) of the preceding vehicle, as shown in the following equation 4a.

[Math. 4a] dmin=Drrxn+Drbrk-Dfbrk
Equation 4a may be expressed as the following Equation 4 by substituting Equations (1a), (2a), and (3a).

The longitudinal safety distance dmin may also be a safety distance assuming an oncoming vehicle. As shown in Figure 6, such a longitudinal safety distance dmin may be a distance that will prevent a head-on collision even if vehicle 1 and another vehicle 2 are traveling facing each other at speeds v1 and v2, respectively, accelerate with a predetermined reaction time ρ and maximum acceleration αmax, and then brake and stop at a minimum deceleration βmin. In this assumption, the other vehicle 2 corresponds to an oncoming vehicle or a vehicle traveling in the wrong direction from vehicle 1.

Here, the free running distance (d1rxn) of vehicle 1 is expressed by equation 5. In the equation, v1 is the initial longitudinal velocity of vehicle 1, and v2 is the initial longitudinal velocity of vehicle 1. Here, v1 and v2 can be interpreted as absolute values (i.e., values greater than or equal to 0).

The braking distance (d1brk) of vehicle 1 is expressed by the following equation 6.

The free running distance (d2rxn) of the other vehicle 2 is expressed by the following equation 7.

The braking distance (d2brk) of the other vehicle 2 is expressed by the following equation 8.

The safety distance dmin in the assumption shown in Figure 6 may be expressed as the sum of the free running distance of vehicle 1 (d1rxn), the braking distance of vehicle 1 (d1brk), the free running distance of vehicle OV2 (d2rxn), and the braking distance of vehicle OV2 (d2brk), as shown in Equation 9 below.

[Math. 9] dmin=d1rxn+d1brk+d2rxn+d2brk
The maximum acceleration of vehicle 1 and the maximum acceleration of other vehicle 2 may be different and may be represented as α1max and α2max, respectively. The minimum deceleration of vehicle 1 and the minimum deceleration of other vehicle 2 may be different and may be represented as β1min and β2min, respectively. The reaction time of vehicle 1 and the reaction time of other vehicle 2 may be different and may be represented as ρ1 and ρ2, respectively. α1max, α2max, β1min, and β2min may all be understood as absolute values.

Regarding velocity, v2 may be expressed as a negative value, taking into account the direction of the vector. When v2 is expressed as a negative value, d2rxn and d2brk may be calculated using formulas 10 and 11.

As shown in Figure 7, the lateral safe distance dmin may be set to a distance that prevents collision by leaving a minimum distance μ even if vehicle 1 and another vehicle 2 are traveling side by side at lateral velocities v1 and v2, respectively, accelerate at a predetermined reaction time ρ and maximum acceleration αmax, and then decelerate laterally at a minimum deceleration βmin.

Here, the lateral safety distance for the left-hand vehicle 1 may be determined using the same concept as the safety distance explained using Figure 6. The lateral safety distance may be the minimum distance μ plus the lateral free-running distance (d1rxn) and braking distance (d1brk) of vehicle 1 and the lateral free-running distance (d2rxn) and braking distance (d2brk) of the other vehicle 2. In other words, the lateral safety distance may be calculated using the following formula 12.

[Math. 12] dmin=μ+d1rxn+d1brk+d2rxn+d2brk
The d1rxn and d1brk for determining the lateral safety distance may be calculated by equations 5 and 6 using the reaction time, initial lateral velocity, maximum lateral acceleration, and minimum lateral velocity of the vehicle 1. The d2rxn and d2brk may be calculated by equations 7 and 8 (or equations 10 and 11) using the reaction time, initial lateral velocity, maximum lateral acceleration, and minimum lateral velocity of the other vehicle 2.

Specific values for parameters such as maximum acceleration, minimum deceleration, and reaction time may be set to reasonable and predictable values. Maximum acceleration and minimum deceleration may be expressed as absolute values. The speed of the road user (v2) may be the value detected by the external environment sensor 41 or the value received via vehicle-to-vehicle communication (i.e., the actual value). Note that a design value may be used for the speed of a road user who is assumed to be outside the field of view (FOV) of the external environment sensor 41. Since actual measured values are applied to the speed information, it may have a positive or negative attribute according to the direction of the speed vector.

Here, the coordinate system used in the safety model may be a lane-based coordinate system. As shown in Figure 8, this coordinate system processes the movement of the vehicle 1 in a direction along the lane LA by defining the center line of the lane LA, i.e., the lane axis ALA along the curve of the road. On the other hand, a road-user-based coordinate system may be used to define the longitudinal and lateral axes of each road user. This coordinate system is based on the center of gravity of the road user, and defines the longitudinal and lateral axes, and therefore the ordinate and abscissa, according to the azimuth angle of the road user.

The risk confirmation unit 26 implemented in the driving system 9 is arranged in parallel with the planning unit 20 and executes calculations. Specifically, the risk confirmation unit 26 acquires the environmental model, sensor data, etc. from the detection unit 10, evaluates risk based on this information, and outputs a response according to the risk to the action unit 30. This series of functions or processes may be referred to as risk confirmation or risk monitoring. Risk confirmation or monitoring may be interpreted as safety confirmation or monitoring. Risk monitoring can also be said to be monitoring of driving policies.

The risk confirmation unit 26 may include a situation extraction unit 27, a situation confirmation unit 28, and a response unit 29 as functional modules that further classify its functions. The situation extraction unit 27, the situation confirmation unit 28, and the response unit 29 may be realized by the processor 53b executing a computer program stored in the memory 53a.

The situation extraction unit 27 extracts a situation based on information obtained from the detection unit 10. Data indicating the situation (hereinafter referred to as situation data) may include a list of objects (hereinafter referred to as surrounding objects) present around the vehicle 1. The surrounding objects may include other road users. The surrounding objects may include features such as lane markings, signs, and guardrails. The situation data may include data indicating a potential conflict between the vehicle 1 and the surrounding objects. In this case, the situation data may include the probability of existence and attribute uncertainty for the vehicle 1 and the surrounding objects. The attributes may be position, orientation, and speed. The situation extraction unit 27 may extract multiple situations. The situation may be a traffic situation. The situation may be selected from a set of possible situations.

The situation confirmation unit 28 confirms whether the situation extracted by the situation extraction unit 27 is a safe situation or a dangerous situation. The situation confirmation unit 28 performs confirmation using a safety envelope, confirmation using another methodology, or both. The confirmation here may be referred to as risk confirmation or safety confirmation. In risk confirmation, the safety envelope may be set based on the acceptable collision risk.

Confirming the risk may include confirming the estimated result of the collision risk between the vehicle 1 and a surrounding object. The collision risk may include the collision risk over time, or may include the peak collision risk. The collision risk may be the collision probability. In other words, uncertainty can be taken into account when confirming the risk.

When the situation confirmation unit 28 performs risk confirmation, the situation confirmation unit 28 may compare the estimated collision risk value with the acceptable collision risk threshold. The acceptable collision risk threshold may be set in advance based on risk acceptance criteria. If the estimated collision risk value is below the acceptable collision risk threshold, the situation confirmation unit 28 may determine that the situation being confirmed is a safe situation. If the estimated collision risk value exceeds the acceptable collision risk threshold, the situation confirmation unit 28 may determine that the situation being confirmed is a dangerous situation.

This risk threshold may be, for example, a vertical safety distance or a horizontal safety distance. That is, in a geometric approach, the situation confirmation unit 28 may set a safety envelope with boundaries corresponding to the risk threshold in order to confirm the risk of collision between the vehicle 1 and surrounding objects. Then, if a surrounding vehicle crosses the boundary of the safety envelope and enters the range of the safety envelope, it may be determined that there has been a violation of the safety envelope. A violation of the safety envelope may be, for example, a failure to maintain a vertical or horizontal safety distance. If there is a violation of the safety envelope, the situation confirmation unit 28 may determine that the situation being confirmed is a dangerous situation. If there is no violation of the safety envelope, the situation confirmation unit 28 may determine that the situation being confirmed is a safe situation.

The situation confirmation unit 28 may set hypotheses about surrounding objects and confirm risks based on those hypotheses. In this case, multiple hypotheses may be used. The hypotheses may include assumptions about reasonably foreseeable behavior of surrounding objects. The hypotheses may also include predictions derived based on those assumptions. The assumptions may include at least one of kinematic-based assumptions and rule-based assumptions. The assumptions about behavior may include assumed values of one or more physical parameters related to movement, such as acceleration. For example, the assumed values may include the maximum deceleration of a preceding vehicle, the reaction time of the host vehicle, the maximum acceleration of the host vehicle, the minimum deceleration of the host vehicle, the minimum deceleration of an oncoming vehicle, or the lateral acceleration of a pedestrian.

The above assumptions may be derived using a function of time that changes during the identified scenario. Alternatively, the assumptions may not change during the identified scenario. The assumptions may vary depending on the category of road user. For example, the assumptions may change depending on whether the road user is a vulnerable road user or not. VRUs may be referred to as vulnerable road users. The assumptions may be adjusted to account for at least one of various road surface conditions and weather-related environmental conditions that are reasonably expected within the operational design domain. The assumptions may be adjusted to account for at least one of differences in road traffic laws between countries and differences in driving habits between regions.

Assumptions may affect the acceptable risk level. The acceptable risk level or risk threshold may be set in advance based on risk acceptance criteria/criterion. The quantitative standard for risk acceptance criteria may be that the probability of harm occurring is below a threshold. Risk acceptance criteria may be set based on positive risk balance, which is the primary measure of ethically acceptable risk levels. Risk acceptance criteria may be set by combining statistical approaches, such as traffic accident statistics, with a scenario-based approach.

The risk tolerance criteria may be determined based on a comparison of the capabilities or operation of the driving system 9 under reasonably foreseeable scenarios within the ODD with the behavior of a competent and careful driver or an experienced and attentive driver. The risk tolerance criteria may be set based on the capability of the driving system 9 being equal to or greater than the driving capabilities of a competent and careful driver or an experienced and attentive driver.

The acceptable risk level or risk threshold may be specified in advance by, for example, at least one of a government agency, a standardization organization, and an approval organization for the driving system 9. The acceptable risk level or risk threshold may be set in advance by, for example, a developer developing the driving system 9.

Furthermore, the driving system 9 or the risk confirmation unit 26 may be designed to change the risk threshold depending on the ODD. The driving system 9 or the risk confirmation unit 26 may be designed to change the risk threshold depending on the use case.

The situation confirmation unit 28 may also refer to a rule set stored in the rule DB 58 to determine an acceptable risk level. The situation confirmation unit 28 may also improve estimation accuracy by incorporating the rules of the rule set into the algorithm for calculating the risk value.

Figure 9 shows an example of a method for deriving and defining assumptions. The series of processes from S11 to S15 may be executed by the processor 53b of the risk confirmation unit 53. This series of processes may be executed at predetermined regular time intervals or based on a predetermined trigger. The predetermined trigger may be, for example, the latest situation data being provided from the situation extraction unit 27 to the situation confirmation unit 28.

First, in S11, the scenario that vehicle 1 is currently encountering is identified. The scenario may be identified by selecting a scenario from a catalog of scenarios stored in scenario DB 59, for example. One scenario may be selected. Alternatively, multiple scenarios may be selected. A more complex situation may be expressed by combining multiple scenarios. After processing S11, the process proceeds to S12.

S12 to S15 are repeated processes for each scenario. In S12, relevant scenes and road users as dynamic elements are identified and described at a high level. After processing S12, proceed to S13.

S13 to S15 are repeated processes for each road user. In S13, the kinematic properties that govern the movement of the road user are identified based on the scenario identified in S11. After processing S13, proceed to S14.

S14-15 are repeated for each identified kinematic property. In S14, the kinematic property is evaluated to determine whether it is safety-related. This evaluation may involve checking whether the kinematic property has the potential to cause other road users to move towards vehicle 1. Kinematic properties that have the potential to cause other road users to move towards vehicle 1 may be considered safety-related kinematic properties. Kinematic properties that are not safety-related are excluded from application to the scenario identified in S11. After processing S14, proceed to S15.

In S15, assumptions are made regarding the reasonably foreseeable behavior of other road users in the scenario identified in S11. These assumptions can be defined by setting boundaries of the reasonably foreseeable range of behavior of other road users in a particular driving situation. After processing in S15, the process returns to S12, S13, and S14 and repeats depending on the remaining processing status of other scenarios, road users, and kinematic characteristics. When processing has been completed for all scenarios, the process ends.

The assumptions here may be a function of time that change during the identified scenario. Alternatively, the assumptions may not change during the identified scenario. Here, a minimum set of assumptions about other road users may be defined.

The minimum set includes the reasonably foreseeable maximum assumed longitudinal velocity other road users could exhibit, the reasonably foreseeable maximum assumed lateral velocity other road users could exhibit, and the reasonably foreseeable maximum assumed longitudinal acceleration other road users in front of the vehicle could exhibit. reasonably foreseeable maximum assumed lateral acceleration that other road users can achieve; reasonably foreseeable maximum assumed longitudinal deceleration that other road users preceding the vehicle can achieve; reasonably foreseeable minimum assumed longitudinal deceleration that other road users traveling in the opposite direction to the vehicle or following the vehicle can achieve. reasonably foreseeable minimum assumed lateral deceleration, reasonably foreseeable maximum assumed heading angle, reasonably foreseeable maximum assumed rate of change of heading angle, Depending on the scenario, this may include one or more of the following characteristics: reasonably foreseeable maximum assumed lateral position fluctuation other road users could exhibit; reasonably foreseeable maximum assumed response time other road users could exhibit; and reasonably foreseeable maximum assumed response time other road users could exhibit.

The response unit 29 derives an appropriate response based on the confirmation result of the situation confirmation unit 28. The response unit 29 may output an appropriate response to the action unit 30 only if the situation is determined to be dangerous. The appropriate response may be a restriction on the control command of the motion actuator 60. The appropriate response may be a response to return the vehicle 1 to a safe state. The appropriate response may be an action related to reducing the safety envelope of the vehicle 1, such as braking, or an action to move the vehicle 1 away from the safety envelope of other road users, such as steering. The appropriate response may also include both steering and braking. The appropriate response may be the display of an image, the activation of lighting equipment, the output of an alarm sound, or the transmission of a radio signal.

Here, even if multiple unrelated dangerous situations are identified, the actions to be taken by the vehicle 1 must be consolidated into a single action. Therefore, the response unit 29 may resolve potential conflicts between appropriate responses to multiple unrelated dangerous situations and transmit the appropriate response to the action unit 30.

Furthermore, the risk confirmation unit 26 may be configured to generate and output event data. The event data may include at least one of situation data, risk confirmation results for the situation, and a derived appropriate response. The risk confirmation results may include at least one of a set safety envelope range and a risk threshold. The risk confirmation results may include assumptions that are the premise for risk confirmation. The assumptions here may include information indicating whether a scenario transition is included in the assumptions. The risk confirmation unit 26 may store the event data in the recording device 55. The risk confirmation unit 26 may also transmit the event data to an external system (e.g., server 96) using the communication system 43 and store it in an external database.

The event data including the risk confirmation results may be referenced by the planning unit 20 and used for trajectory planning and behavior planning. The risk confirmation unit 26 may output the risk confirmation results to the planning unit 20, and the planning unit 20 may formulate a trajectory plan and behavior plan based on the risk confirmation results.

The risk confirmation unit 26 may support operations in an emergency. The operation in an emergency may be a DDT fallback. The risk confirmation unit 26 may execute a DDT fallback if a dangerous situation continues or occurs after an appropriate response is output, in other words, if the risk is not sufficiently reduced.

The risk confirmation unit 26 may distinguish between the initiator of a dangerous scenario and the responder of a dangerous scenario. The risk confirmation unit 26 may distinguish between actions recommended for the initiator and actions recommended for the responder. In other words, if the vehicle 1 is the initiator, the risk confirmation unit 26 may derive an appropriate response according to the action recommended for the initiator, and if the vehicle 1 is the responder, it may derive an appropriate response according to the action recommended for the responder.

<Responding to stopped vehicles on the road>
10, the response of the driving system 9 in a scenario in which the host vehicle travels near a stopped vehicle 3 that has the potential to depart (hereinafter also referred to as a stopped vehicle-related scenario) will be described. The stopped vehicle-related scenario may include, for example, a situation in which a stopped vehicle 3 is present ahead of the host vehicle.

In the example shown in Figure 10, vehicle 1 is traveling on a road with one lane in each direction, and there is a stopped vehicle 3 ahead of vehicle 1 on ego lane EL. Ego lane EL is the lane in which vehicle 1 is traveling. Figure 10 shows the case in which stopped vehicle 3 is a bus, but stopped vehicle 3 may also be a road user other than a bus. Stopped vehicle 3 may also be a taxi. Stopped vehicle 3 may also be a parked passenger car or truck. Stopped vehicle 3 is partially or completely blocking ego lane EL. Stopped vehicle 3 may also be stopped with part of its body extending outside the ego lane EL (for example, onto the sidewalk 83 or shoulder of the road).

In Figure 10, 81 indicates the road edge. Here, the road edge 81 is the edge of the area where vehicles must travel (i.e., the roadway). The road edge 81 may be interpreted as, for example, the boundary between the roadway and the sidewalk 83. 82 is the center line. The center line 82 may be a marking type that allows vehicles to extend into the oncoming lane OL, such as a dashed line. The center line 82 may be interpreted as a type of lane marking.

In this scenario, vehicle 1 needs to use the oncoming lane OL (in other words, pass through) to get in front of stopped vehicle 3, or wait behind stopped vehicle 3 for it to depart. Using the oncoming lane OL does not necessarily mean that the entire body of vehicle 1 passes on the oncoming lane OL, but may also mean that only part of the body passes on the oncoming lane OL. Using the oncoming lane OL may also include traveling with part of the body extending into the oncoming lane OL and part of the body remaining in the ego lane EL. The dashed arrow in the figure shows an example of a trajectory that vehicle 1 may take when traveling to avoid stopped vehicle 3.

In this way, the stopped vehicle-related scenario may include an avoidance scenario in which vehicle 1 avoids a stopped vehicle (e.g., a bus) by using an oncoming lane OL. Furthermore, the avoidance scenario may include a scenario in which vehicle 1 passes beside stopped vehicle 3. Furthermore, the stopped vehicle-related scenario may include a waiting scenario in which vehicle 1 waits behind stopped vehicle 3 for the stopped vehicle 3 to depart. Depending on the situation, the scenario may transition from a waiting scenario to an avoidance scenario, or from an avoidance scenario to a waiting scenario.

For convenience, the lane in which the stopped vehicle 3 is located (i.e., the ego lane EL) is also referred to as the original lane BL. The original lane corresponds to a lane that is partially or completely blocked by the stopped vehicle 3. The lane in which the vehicle 1 temporarily travels during avoidance control is also referred to as the temporary traffic lane TL. In the example shown in FIG. 10, the temporary traffic lane TL is the oncoming lane OL. The temporary traffic lane TL and the oncoming lane OL correspond to adjacent lanes. In the present disclosure, driving control that goes around in front of the stopped vehicle 3 through an adjacent lane is also referred to as avoidance control. Avoidance control may also be referred to as overtaking control or slip-through control.

Here, an example of the processing of the driving system 9 to deal with a stopped vehicle 3 will be described using the flowchart in Figure 11. This series of processing steps S101 to S110 may be realized, for example, by the processor 51b of the main unit 51 executing a computer program stored in the memory 51a, and simultaneously the processor 53b of the risk confirmation unit 53 executing a computer program stored in the memory 53a. Some or all of the processing may be realized by the processor 51b of the main unit 51 executing a computer program stored in the memory 53a. References to the driving system 9 as the entity executing the processing hereinafter may be interpreted as processor 51b or 53b. Furthermore, depending on the context, references to the driving system 9 may be interpreted as the detection unit 10, the planning unit 20, the risk confirmation unit 26, or the action unit 30.

S101 is a step in which the driving system 9 updates the environmental model based on data received from the external environment sensor 41 via the communication interface 51c. S101 corresponds to a step in which information indicating the external environment, internal environment, vehicle state, and even the state of the driving system 9 of the vehicle 1 is updated. S101 may be performed by the detection unit 10. S101 may be performed periodically, or may be performed in response to receiving sensor data. In response to the execution of S101, the driving system 9 executes S102. Note that the processing from S102 onwards may be performed when the autonomous driving function is enabled.

S102 is a step in which the driving system 9 identifies a scenario based on the latest environmental model. Scenario identification may be performed based on signals received by the communication interface 51c. If, as a result of scenario identification, it is determined that the current situation corresponds to a specific scenario (S103 YES), S104 is executed. The specific scenario here may be a scenario related to a stopped vehicle. If it is determined that the current situation does not correspond to a specific scenario (S103 NO), this flow ends, and another process according to the scenario may be executed.

S104 is a step in which the driving system 9 acquires the type of stopped vehicle 3. The type of stopped vehicle 3 may be identified based on sensor data provided by the external environment sensor 41. When S104 is completed, processing proceeds to S105. Note that the driving system 9 may be configured to execute processing from S104 onwards based on the detection of a stopped vehicle 3 ahead on the ego lane.

S105 is a step in which the driving system 9 determines whether the stopped vehicle 3 is a school bus. Whether the stopped vehicle 3 is a school bus may be identified based on the color, shape, or text posted on the body of the stopped vehicle 3. If the stopped vehicle 3 is a school bus (S105 YES), processing proceeds to S111. On the other hand, if the stopped vehicle 3 is not a school bus (S105 NO), processing proceeds to S106. Note that S105 may also be a step in which it is determined whether the stopped vehicle 3 is a school bus and whether the school bus is displaying a STOP sign or flashing red lights. S105 may be executed only when the vehicle 1 is traveling in a specific area (mainly the United States). If the vehicle 1 is not traveling in a specific area, S105 may be omitted. S105 is an optional element.

S106 is a step in which the driving system 9 generates an avoidance trajectory. The avoidance trajectory is a trajectory for traveling in a manner that avoids the stopped vehicle 3. The avoidance trajectory may be generated so that a safe distance is maintained between the vehicle 1 and the stopped vehicle 3. The safe distance may be, for example, 1.0 m. The avoidance trajectory may be created or modified based on the expected behavior of other road users, as described below.

S107 is a step in which the behavior of each road user detected by the external environment sensor 41 is assumed. The road users detected by the external environment sensor 41 may include the stopped vehicle 3. While Figure 10 illustrates an example in which only the stopped vehicle 3 is present around the vehicle 1, in reality, other road users may also be present around the vehicle 1. If road users other than the stopped vehicle 3 are detected, the driving system 9 may also assume the behavior of road users other than the stopped vehicle 3. If a pedestrian on the sidewalk 83 is detected, the behavior of the detected pedestrian may be assumed. Furthermore, the presence of other road users hidden by the stopped vehicle 3 may be assumed. The driving system 9 may assume the behavior of other virtual road users hidden by the stopped vehicle 3. Other road users hidden by the stopped vehicle 3 may be oncoming vehicles, pedestrians, etc.

Although FIG. 11 illustrates an example in which S107 is executed after S106, S107 may be executed before S106. S107 may also be executed in conjunction with the identification of a scenario in S102. S107 may be a step of performing S13 to S15 for each other detected or anticipated road user. S107 may also be a step of calculating a safety envelope for each other detected or anticipated road user. S107 may also include calculating a range of potential behaviors for each other detected or anticipated road user. The range of potential behaviors of each other road user is, for example, a range that the other road user can reach within a predetermined time, and may be calculated from the current speed, direction, and reasonably foreseeable maximum acceleration. A design value according to the type of road user may be applied to the reasonably foreseeable maximum acceleration.

S108 is a step for confirming the risk when avoidance control is executed. As described above, risk confirmation may involve verifying whether a violation of the safety envelope may occur. Risk confirmation may also include determining whether there is a possibility that the distance between an oncoming vehicle and the host vehicle will be less than a predetermined value while avoidance control is being executed. Specifically, risk confirmation related to avoidance control may include determining whether an oncoming vehicle is present in a road section within a predetermined distance from the stopped vehicle 3.

Furthermore, checking the risk associated with avoidance control may include determining whether there is an oncoming vehicle that can reach the side of the stopped vehicle 3 within the avoidance time. The avoidance time here is the time required for the host vehicle to perform avoidance control. The avoidance time may be calculated assuming a worst-case scenario. In other words, the avoidance time may be the time it takes for vehicle 1, which is stopped behind the stopped vehicle 3, to start moving at a predetermined acceleration, pass the side of the stopped vehicle 3, and arrive in front of the stopped vehicle 3. The avoidance time may be dynamically set depending on the size or type of the stopped vehicle 3, or may be a fixed value such as 5 seconds.

Note that if the external environment sensor 41 has a sufficient view of the oncoming lane and no other vehicle 2 is detected in the oncoming lane, the avoidance time may be calculated using the current driving speed as the initial speed. The driving system 9 may be configured to be able to select a plan for avoidance control that involves passing alongside the stopped vehicle 3 without stopping behind it.

In response to the result of S108, the driving system 9 determines in S109 whether avoidance control is feasible. Avoidance control may be feasible when no unacceptable risk has been detected. Avoidance control may be feasible when no violation of the safety envelope is foreseen. Avoidance control may be feasible when it has been confirmed that there are no oncoming vehicles that can reach the side of the stopped vehicle 3 within the avoidance time. If a risk of collision or excessive close proximity to an oncoming vehicle is detected during avoidance control, it may be determined that avoidance control is not feasible. Determining that avoidance control is not feasible corresponds to deciding not to execute avoidance control.

S109 corresponds to a step of determining whether the conditions for executing avoidance control are met. As described above, the conditions for executing avoidance control include the traffic conditions in the oncoming lane, such as the size of the free space. Note that if a lit traffic light indicating a stop is detected ahead of the stopped vehicle 3, the driving system 9 may be configured to determine that avoidance control is not executable. If a stop line or pedestrian crossing is detected ahead of the stopped vehicle 3, the driving system 9 may be configured to determine that avoidance control is not executable. If the presence of an emergency vehicle is detected near vehicle 1, the driving system 9 may also be configured to determine that avoidance control is not executable. These provisions reduce the risk of unnecessary avoidance control being implemented. The presence of an emergency vehicle may be detected based on image information received from a camera, as well as wireless communication or sound information.

Furthermore, if the stopped vehicle 3 is stopped near the center of the lane, that is, if the stopped vehicle 3 is not pulled over to the shoulder, it may be temporarily stopped due to simple congestion, a traffic light indication, a pedestrian crossing, or other reasons. Given these circumstances, the driving system 9 may be configured to determine whether or not to perform avoidance control on the condition that the stopped vehicle 3 is stopped closer to the road edge 81 than the center of the lane. The driving system 9 may also be configured to determine that avoidance control is not executable if the stopped vehicle 3 is stopped near the center of the lane. Alternatively, the determination of whether or not to perform avoidance control may be based on whether or not the vehicle is near a bus stop. Based on the sensor data or map data of the external environment sensor 41, the driving system 9 may be configured to perform avoidance control more proactively than when a bus stop is not detected.

The decision as to whether to execute avoidance control, in other words, the confirmation of risk, may be made based on the results of predicting the behavior of the stopped vehicle 3. The driving system 9 may be configured to predict the departure of the stopped vehicle 3 by monitoring the lighting status of the lighting equipment of the stopped vehicle 3. The lighting equipment used for behavior prediction may be at least one of brake lights, hazard lights, and turn signals. The driving system 9 may predict that the stopped vehicle 3 will soon depart based on the extinguishing of the brake lights, the activation of the turn signals, and the extinguishing of the hazard lights.

If the driving system 9 detects pre-departure behavior by the stopped vehicle 3, it may predict that the stopped vehicle 3 will soon depart. The pre-departure behavior is a signal indicating that the stopped vehicle 3 will soon depart. The pre-departure behavior may include turning off the brake lights, activating the turn signals, or displaying a predetermined image. The pre-departure behavior may also be turning off the hazard lights, closing the doors, starting the engine, etc. The driving system 9 may predict that the stopped vehicle 3 will not soon depart based on the state of the stopped vehicle 3, such as whether the doors are open.

Furthermore, the driving system 9 may predict the behavior of the stopped vehicle 3 based on data received through vehicle-to-vehicle communication with the stopped vehicle 3. Predicting the behavior of the stopped vehicle 3 may involve estimating whether the stopped vehicle 3 will move off soon, whether it will remain stopped for a while, or how many seconds it will take for the stopped vehicle 3 to move off. For example, when the driving system 9 receives a vehicle status message from the stopped vehicle 3, it may predict the behavior of the stopped vehicle 3 using the vehicle status message. If the stopped vehicle 3 is predicted to move off, the driving system 9 may determine that avoidance control cannot be executed. The driving system 9 may determine that avoidance control can be executed based on the prediction that the stopped vehicle 3 will not move off soon.

The risk confirmation unit 26 may determine whether or not avoidance control can be performed. If it is determined that avoidance control can be performed (YES in S109), the driving system 9 starts avoidance control in S110. In other words, it starts driving the vehicle 1 toward the oncoming lane according to a pre-set avoidance trajectory.

On the other hand, if it is determined that avoidance control cannot be performed (S109 NO), the risk confirmation unit 26 outputs an appropriate response to the planning unit 20, prohibiting avoidance control or outputting a signal to instruct the vehicle to stop. If it is determined that avoidance control cannot be performed, the driving system 9 may be configured to plan and execute standby control in S111.

The waiting control may be to stop vehicle 1 behind stopped vehicle 3. The stopping position of vehicle 1 relative to stopped vehicle 3 in the longitudinal direction may be a predetermined position, such as 5 m behind stopped vehicle 3. The stopping position in the lateral direction may be along the center line so that the FOV of the external environment sensor 41 relative to the oncoming lane is wide. Of course, the stopping position in the lateral direction may be the center of the ego lane or directly behind stopped vehicle 3.

The driving system 9 may create an avoidance trajectory to avoid the potential movement range of the stopped vehicle 3. The potential movement range of the stopped vehicle 3 may be set based on a predetermined maximum acceleration, with the current speed set to 0. Taking into account the possibility that the stopped vehicle 3 may suddenly roll back, the potential movement range of the stopped vehicle 3 may be set in front of and behind the stopped vehicle 3. The driving plan unit 22 of the driving system 9 may obtain the risk confirmation results directly or indirectly from the risk confirmation unit 26, and create a driving plan for vehicle 1 relative to the stopped vehicle 3 to reduce risk.

Furthermore, the driving system 9 may generate a trajectory and speed plan near the front end of the stopped vehicle 3, taking into account the possibility that a VRU (e.g., a pedestrian) may be hidden in front of the stopped vehicle 3. The driving system 9 may create a driving trajectory and speed plan (and therefore a driving plan) assuming the presence of a pedestrian hidden by the stopped vehicle 3. The final speed may be set to a value smaller than the starting speed. Here, the final speed is the speed when crossing the front end of the stopped vehicle 3. The starting speed is the speed when crossing the rear end of the stopped vehicle 3. For example, the final speed may be set to a predetermined value (e.g., 30 km/h) or less.

The driving system 9 may periodically perform the determination of S109 even while stopped and waiting. The driving system 9 may also start avoidance control after stopping behind the stopped vehicle 3 based on the determination that avoidance control can be implemented.

The driving system 9 may decide to initiate avoidance control based on whether it has confirmed that there are no other road users in a specific area on the oncoming lane OL. If, after initiating avoidance control, it detects the presence of other road users on the oncoming lane OL, it may decide whether to discontinue avoidance control depending on the type or speed of the other road users.

The specific area on the oncoming lane OL may be a predetermined range including the sides of the stopped vehicle 3. The specific area may be a section on the oncoming lane OL that is within 50 m ahead of the rear end of the stopped vehicle 3. The length of the specific area may be determined according to the avoidance time. The length of the specific area may be determined based on a value obtained by multiplying the avoidance time by an estimated traveling speed of a virtual oncoming vehicle. The estimated traveling speed of the virtual oncoming vehicle may be a value obtained by adding a predetermined margin (e.g., 20 km/h) to the speed limit. The state in which it has been confirmed that there are no other road users in the specific area may be a state in which the specific area is included in the FOV of the external environment sensor 41 and the specific area has been determined to be an empty space based on the detection results. If part of the specific area is outside the FOV of the external environment sensor 41 or if other road users have been detected in the specific area, the driving system 9 may determine that it has not been confirmed that there are no other road users in the specific area.

In one embodiment, if the stopped vehicle 3 is a school bus, the driving system 9 operates to wait for the school bus to depart. This can increase the safety of children getting on and off the school bus. The driving system 9 also takes into account the risks involved in taking evasive action and initiates evasive action. If the driving system 9 detects an unacceptable risk in relation to avoidance control, it does not perform avoidance control but performs standby control. This can reduce the risk involved in avoiding the stopped vehicle 3. If the driving system 9 does not detect an unacceptable risk in relation to avoidance control, it performs avoidance control. This can increase convenience for vehicle users.

The driving system 9 may determine a response to a stopped vehicle 3 taking into account the type of stopped vehicle 3, not limited to school buses. The response to a stopped vehicle 3 may be to perform avoidance control or to wait. If the stopped vehicle 3 is an emergency vehicle, the driving system 9 may be configured to first perform wait control and then attempt avoidance control, or to perform a takeover request. The type of stopped vehicle 3, for example, whether the stopped vehicle 3 is an emergency vehicle, may be determined based on the appearance of the stopped vehicle 3 captured by a camera. By determining a response taking into account the type of stopped vehicle 3, it becomes possible to achieve autonomous driving in a wider variety of situations. As a result, the convenience of autonomous driving can be improved.

In one embodiment, the driving system 9 determines whether to initiate avoidance control based on the predicted behavior of the stopped vehicle 3. That is, the driving system 9 determines not to initiate avoidance control if the stopped vehicle 3 is predicted to depart. The driving system 9 also determines to initiate avoidance control based on the fact that the stopped vehicle 3 is still stopped and the stopped vehicle 3 is not predicted to depart. This configuration, which determines the start of avoidance control based on the predicted results, reduces the possibility that avoidance control will be suspended due to a conflict between avoidance control and the stopped vehicle 3's departure.

Furthermore, the driving system 9 may determine the conditions for executing avoidance control based on the amount of protrusion of the host vehicle into the oncoming lane OL when avoidance control is performed. The smaller the amount of protrusion, the more relaxed the conditions for executing avoidance control may be.

<Operation after avoidance control starts>
The avoidance control may mainly include the phases shown in Figures 12, 13, and 14. The initial phase shown in Figure 12 is a state in which a change in lateral position (i.e., steering) for avoidance has started, but the body of the vehicle 1 has not yet protruded into the oncoming lane OL.

The mid-phase shown in FIG. 12 is a state in which part or all of the body of vehicle 1 is in the oncoming lane OL, and the rear end of vehicle 1 is still located behind the front end of stopped vehicle 3. The mid-phase mainly corresponds to the phase in which vehicle 1 is traveling to the side of stopped vehicle 3. The mid-phase may be divided into two or more phases depending on the position of vehicle 1 relative to stopped vehicle 3. For example, the mid-phase may be divided into a first mid-phase and a second mid-phase. The first mid-phase may be a state in which the front end of vehicle 1 is located behind the longitudinal center of stopped vehicle 3. The second mid-phase may be a state in which the front end of vehicle 1 is located ahead of the longitudinal center of stopped vehicle 3. Here, "ahead" corresponds to the direction of travel set in ego lane EL.

The late phase shown in Figure 14 is a state in which the rear end of vehicle 1 is located ahead of stopped vehicle 3. The late phase may be divided into two or more phases depending on the position of vehicle 1 relative to center line 82. For example, the late phase may be divided into a first late phase and a second late phase. The first late phase may be a state in which part or all of vehicle 1 is still in the oncoming lane OL. The second late phase may be a state in which vehicle 1 has completely returned to the original lane BL. The second late phase corresponds to a phase in which avoidance control is almost complete.

<Example of operation during avoidance control>
The driving system 9 may monitor the behavior of the stopped vehicle 3 even while executing the avoidance control, and may discontinue the avoidance control depending on the situation. For example, if the departure of the stopped vehicle 3 is detected or predicted in the initial phase, the driving system 9 may decide to discontinue the avoidance control and return to the ego lane EL.

Figure 15 is a flowchart showing an example of the operation of the driving system 9 during avoidance control, and includes S201 to S205. The first step, S201, is a step in which the driving system 9 monitors the behavior of the stopped vehicle 3. Monitoring the behavior of the stopped vehicle 3 may involve analyzing sensor data related to the stopped vehicle 3 and determining whether the stopped vehicle 3 has started to move. The sensor data related to the stopped vehicle 3 may be data related to the stopped vehicle 3 detected by the external environment sensor 41, or may be data received from the stopped vehicle 3 via vehicle-to-vehicle communication. The sensor data related to the stopped vehicle 3 corresponds to the monitoring result.

Monitoring the behavior of the stopped vehicle 3 may include determining (or predicting) whether the stopped vehicle 3 is about to depart. S201 may be executed periodically while avoidance control is being performed. S201 may also be performed in response to receiving sensor data related to the stopped vehicle 3. Following S201, the driving system 9 executes S202.

S202 is a step in which, based on the result of S201, it is determined whether the stopped vehicle 3 has started moving. If it is detected that the stopped vehicle 3 has started moving (S202 YES), the driving system 9 performs the determination of S204. On the other hand, if it is detected that the stopped vehicle 3 is still stopped (S202 NO), the driving system 9 executes S203. Note that S202 may also include determining whether the stopped vehicle 3 is likely to start moving soon. If it is predicted that the stopped vehicle 3 is likely to start moving soon, the driving system 9 may execute S204. The driving system 9 may be configured to execute S203 if the stopped vehicle 3 is still stopped and is not predicted to start moving soon.

S203 is a step in which it is decided to continue avoidance control. In S203, the risk confirmation unit 26 does not output an appropriate response due to the behavior of the stopped vehicle 3.

In S204, the driving system 9 determines whether vehicle 1 is still in a phase where it can discontinue avoidance control with respect to the stopped vehicle 3. A phase where avoidance control can be discontinued is a phase where it is possible to return to behind the stopped vehicle 3 within the ego lane EL. For example, the phase where avoidance control can be discontinued may be the initial phase. The phase where avoidance control can be discontinued may include a state where vehicle 1 is behind the stopped vehicle 3 and the vehicle body has not yet protruded into the oncoming lane OL. The phase where avoidance control can be discontinued may also be a state where vehicle 1 is behind the stopped vehicle 3 and the amount of protrusion of the vehicle body into the oncoming lane OL is equal to or less than the reversible threshold. The reversible threshold may be a fixed value such as 0.5 m, or a variable determined according to the longitudinal distance between the stopped vehicle 3 and vehicle 1. The greater the longitudinal distance between the stopped vehicle 3 and vehicle 1, the greater the reversible threshold may be set to.

Whether or not avoidance control can be stopped may be determined using a safety distance. Here, the safety distance may be a longitudinal safety distance calculated by regarding the stopped vehicle 3 as a preceding vehicle. In S204, since the system has already perceived the departure of the stopped vehicle 3, the reaction time ρ may be set to 0 seconds and determined using Equation 3. If the vehicle is still at least the safety distance from the rear vehicle, the driving system 9 may determine that avoidance control can be stopped regardless of the lateral position of vehicle 1 (whether it has crossed the center line 82). In this way, the position at which avoidance control can be stopped may be determined based on the current speed of vehicle 1.

The safety distance used to determine whether to discontinue avoidance control may be calculated using a deceleration that is a predetermined amount greater than the minimum deceleration, rather than the minimum deceleration. For example, the deceleration (β) used to calculate the safety distance may be 2.5 m/sec^2 or 3.0 m/sec^2. In other embodiments, the safety distance may be a constant value that does not depend on the speed. The driving system 9 may simply determine that avoidance control can be discontinued if the vehicle is a predetermined distance or more behind the stopped vehicle 3. A case in which avoidance control cannot (or is difficult to) be discontinued may be a case in which the conditions for discontinuance are not met.

If the driving system 9 determines that the avoidance control is in a phase where it can be stopped (S204 YES), it decides to stop the avoidance control. In that case, the driving system 9 creates and executes a driving plan, such as steering, to return the vehicle 1 behind the stopped vehicle 3.

On the other hand, if the driving system 9 determines that the avoidance control is not in a phase where it can be stopped (S204 NO), it decides to continue the avoidance control. In other words, if stopping the avoidance control would actually compromise safety, it controls the vehicle 1 to complete the avoidance control. However, if another risk is detected along the way, the driving system 9 may implement an appropriate response determined according to the situation. Furthermore, the avoidance control may ultimately be interrupted based on the results of risk confirmation while the avoidance control is being performed.

By determining the continuity of avoidance control in this way while taking into account factors such as safety distance, the probability of contact/near crash with the stopped vehicle 3 can be reduced. A near crash here refers to a state immediately before a collision, and can also be described as excessive proximity.

The driving system 9 may be configured to discontinue avoidance control if the host vehicle, vehicle 1, is located behind the stopped vehicle 3 at the time the departure of the stopped vehicle 3 is detected, and to decide to continue avoidance control in other cases. Other cases may include when the host vehicle is located to the side of the stopped vehicle 3 or in front of the stopped vehicle 3. In other words, the driving system 9 may be configured to complete avoidance control without discontinuing it when it detects the departure of the stopped vehicle 3 in a situation where avoidance control has progressed to the middle phase or late phase. The driving system 9 may also decide to discontinue avoidance control if the timing of detecting the departure of the stopped vehicle 3 is up to the first middle phase. The driving system 9 may also decide to complete avoidance control from the second middle phase onwards. The above corresponds to an example of determining whether to continue avoidance control based on the position of vehicle 1 relative to the stopped vehicle 3 when the departure of the stopped vehicle 3 is detected (or predicted).

If the driving system 9 detects behavior related to the stopped vehicle 3 starting up while avoidance control is being executed, it may increase the driving speed compared to when behavior related to the stopped vehicle 3 starting up is not detected. The behavior related to the stopped vehicle 3 starting up may be behavior that can be used to determine whether the stopped vehicle 3 is about to start up, such as the brake lights turning off or the turn signals turning on. The behavior related to the stopped vehicle 3 starting up may also be a change in the position of the stopped vehicle 3 (i.e., starting up).

Whether or not to accelerate vehicle 1 in response to the departure of stopped vehicle 3 may be determined according to the progress of avoidance control at the time when behavior related to the departure of stopped vehicle 3 is detected (hereinafter referred to as the departure perception time). As described above, the progress of avoidance control may be classified according to the position of the host vehicle relative to stopped vehicle 3 and the traveling speed of the host vehicle. For example, if the host vehicle is in a phase where avoidance control can be stopped at the departure perception time, it may decide to decelerate without increasing the speed. Furthermore, if the host vehicle is in a phase where it is difficult to stop avoidance control at the departure perception time, it may decide to increase the traveling speed by a predetermined amount. For example, if vehicle 1 is traveling beside stopped vehicle 3 at the departure perception time, the driving system 9 may decide to increase the traveling speed by a predetermined amount.

The driving system 9 may be configured to determine whether to continue avoidance control by comparing the speed of the vehicle 1 when the departure of the stopped vehicle 3 is detected or predicted with a threshold value.

Figure 16 is a flowchart illustrating the operation of the driving system 9 corresponding to this technical concept, and includes steps S211 to S215. Steps S211 to S213 may be the same as steps S201 to S203.

S214 is an alternative/additional process to S204. In S214, the driving system 9 determines whether the current speed (Ve) of the vehicle 1 exceeds a predetermined continuation threshold (ThV). Ve in the figure represents the speed of the vehicle 1 when it detects the departure of the stopped vehicle 3. ThV in the figure represents the continuation threshold. The continuation threshold is a speed-related threshold used to determine whether to continue or discontinue avoidance control. The continuation threshold may be a design value, such as 40 km/h. The continuation threshold may be set to a value at which it is expected that avoidance control can be safely discontinued. If the speed of the vehicle 1 exceeds the continuation threshold (S214 YES), the driving system 9 may decide to continue avoidance control. If the speed of the vehicle 1 is equal to or less than the continuation threshold (S214 NO), the driving system 9 may decide to discontinue avoidance control. If it decides to discontinue avoidance control, the driving system 9 creates and executes a plan to return to the rear of the stopped vehicle 3 on the ego lane EL.

In the above configuration, avoidance control is discontinued in response to the departure of the stopped vehicle 3 if the speed is such that avoidance control can be safely discontinued. On the other hand, if the speed of vehicle 1 at the time of detection of the departure is such that avoidance control may not be able to be safely discontinued, avoidance control is continued. This reduces the risk of sudden braking being performed to discontinue avoidance control. Of course, the driving system 9 may also determine whether to continue or discontinue avoidance control by combining the position and speed of vehicle 1 at the time of detection of the departure. The driving system 9 may also determine whether to continue or discontinue avoidance control by combining other information, such as the automation level at the time of detection of the departure.

The avoidance control described above may also be performed when the automation level is 2 (effectively 2.5). The driving system 9 may change the conditions for suspending avoidance control depending on the automation level. If the driving system 9 detects that the stopped vehicle 3 has started moving while performing avoidance control in a mode with an automation level of 2, it may decide to continue the avoidance control as is. On the other hand, if the driving system 9 detects that the stopped vehicle 3 has started moving while performing avoidance control in a mode with an automation level of 3 or higher, it may suspend the avoidance control and return behind the stopped vehicle 3.

17 is a flowchart illustrating the operation of the driving system 9 corresponding to this technical concept, and includes steps S221 to S225. Steps S221 to S223 may be the same as steps S201 to S203. Step S224 may be an alternative or additional process to step S204. In step S224, the driving system 9 determines whether the current automation level (AD_LV) of the vehicle 1 is 3 or higher. If the automation level is 3 or higher (YES in step S224), the driving system 9 determines to discontinue avoidance control in step S225, and creates and executes a plan to return to the rear of the stopped vehicle 3 (i.e., the ego lane EL). On the other hand, if the automation level is lower than 3, the driving system 9 determines to continue avoidance control in step S223. If the automation level is lower than 3, the vehicle user is monitoring the surroundings, and therefore may perform driving operations that reduce risk at the vehicle user's discretion. If the automation level is lower than 3, the decision to continue avoidance control is left to the vehicle user, thereby guiding the vehicle 1 toward more appropriate behavior.

If the driving system 9 decides to continue avoidance control because the automation level is less than 3, it may issue a notification to the vehicle user related to the departure of the stopped vehicle 3. The notification related to the departure of the stopped vehicle 3 may be a process of notifying the vehicle user that the stopped vehicle 3 has started by outputting a voice message or displaying an image. The notification related to the departure of the stopped vehicle 3 may also be a process of requesting the vehicle user to check for safety by outputting a voice message or displaying an image. The notification related to the departure of the stopped vehicle 3 may also be a process of suggesting that the vehicle return to the ego lane EL (in other words, the original lane BL). If the driving system 9 detects the departure of the stopped vehicle 3 while executing avoidance control at level 2, the driving system 9 may issue the above notification, which may increase the vehicle user's attention and improve safety.

The driving system 9 may continue to monitor the behavior of the vehicle 3 even after deciding to discontinue avoidance control in S205 or the like ( FIG. 18 , S231). Then, if the vehicle 3 stops again within a predetermined time from starting (or within a predetermined distance from the starting point) (S232 YES), the driving system 9 may retry avoidance control (S234). For example, if the driving system 9 detects that the vehicle 3 has stopped again before the vehicle 1 has completely returned to the ego lane EL, it may resume avoidance control from that point. In other words, it may resume control to steer the vehicle toward the oncoming lane OL. Furthermore, if the driving system 9 detects that the vehicle 3 has stopped again after the vehicle 1 has completely returned to the ego lane EL, it may start avoidance control as usual.

If the vehicle 3 stopped on the road is a bus, there are two possible reasons why the vehicle 3 may stop again after starting: (1) arriving at a bus stop, or (2) detecting some kind of risk (pedestrians, etc.). If the vehicle 3 is a bus and a bus stop is detected near the re-stop point (YES in S233), the driving system 9 may retry avoidance control. On the other hand, if the vehicle 3 is a bus and no bus stop is present near the re-stop point (NO in S233), the retry of avoidance control may be canceled (S234). Alternatively, if the vehicle 3 is a bus and no bus stop is present near the re-stop point, the driving system 9 may be configured to execute avoidance control at a speed lower than the basic speed applied under normal circumstances. Here, "normal circumstances" may be interpreted as when a bus stop is detected or when changing lanes for the first time. The determination step of S233 is optional and may be omitted. If S233 is omitted, and if re-stopping of the vehicle 3 is detected (YES in S232), S234 may be executed.

The above process reduces the likelihood of avoidance control being executed when a pedestrian or other object is present in the blind spot of a bus or other vehicle. This can increase the safety of vulnerable road users such as pedestrians. The flow shown in Figure 18 may be executed only when vehicle 3 is a service car such as a bus or taxi, or a commercial vehicle.

Incidentally, it is predicted that buses will stop at every bus stop. If the stopped vehicle 3 is a bus, the driving system 9 may control the vehicle to pass by the bus at the next bus stop. If the vehicle 3 is a bus, the driving system 9 may monitor the behavior of the bus during avoidance control, as shown in S241 of FIG. 19. Then, if the departure of the bus is detected or predicted (S242 YES), the avoidance control may be interrupted (S243). The decision to interrupt avoidance control may be made depending on the progress of avoidance control or the speed of vehicle 1, as described above.

When avoidance control for a bus is discontinued, the driving system 9 may set the set value for the distance from the preceding vehicle to be longer than the basic value (S244). The basic value is the distance that is applied when there is no history of discontinuing avoidance control for a bus within a certain period of time in the past. The basic value may be a value that corresponds to the traveling speed of the vehicle 1 and the settings of the vehicle user. The processing of S244 above makes it easier to execute avoidance control the next time the bus stops at a bus stop.

During avoidance control, the driving system 9 may detect that another road user (hereinafter, an oncoming user) is approaching from the front in the oncoming lane OL. In such a case, the driving system 9 may determine its response depending on the type of oncoming user.

For example, if the detected oncoming user is a road user whose width is less than a predetermined value (e.g., 1 m), such as a pedestrian, cyclist, or motorcyclist, it may be decided to continue avoidance control. This is because when the oncoming user is a pedestrian, etc., a safe lateral distance is likely to be maintained even if the vehicle extends into the oncoming lane OL. Note that a road user whose width is less than a predetermined value may be read as a VRU.

On the other hand, if the detected oncoming user is a car, it may be decided to discontinue avoidance control. Even if the detected oncoming user is a car, avoidance control may be continued if the oncoming user is sufficiently far away from vehicle 1. The continuation of avoidance control when an oncoming user is detected may be determined based on the type, position, and speed of the oncoming user, and the progress of avoidance control.

Avoidance control when an oncoming user is detected may be performed at a slower speed than avoidance control when an oncoming user is not detected. The driving system 9 may also be configured to start deceleration when the detected longitudinal distance to the oncoming user falls below a predetermined value.

The above configuration can increase convenience for vehicle users while ensuring the safety of oncoming vehicles.

<Another example of operation of the driving system (1)>
Furthermore, as shown in FIG. 20 , when the driving system 9 determines that a specific scenario (here, a stopped vehicle-related scenario) applies (YES in S251), it determines in S252 whether the current automation level is 3 or higher. Determining the current automation level corresponds to determining the current mode, which is the current operating mode. Here, the "current" may refer to the time when it is determined that the scenario applies to a stopped vehicle-related scenario. "AD_LV" in the figure refers to the current automation level.

The driving system 9 may be configured to plan and execute standby control in S253 if a stopped vehicle 3 is detected (S252 YES) while driving in an operating mode of level 3 or higher. On the other hand, the driving system 9 may be configured to perform avoidance determination processing in S254 if a stopped vehicle 3 is detected (S252 NO) while driving in an operating mode below level 3 (e.g., level 2 mode). The avoidance determination processing is processing that includes determining whether avoidance control is possible and starting avoidance control based on the determination that it is possible. The avoidance determination processing may be processing that includes, for example, S104 to S111.

With the above configuration, in operation modes of level 3 or higher, the frequency of execution of avoidance control is reduced compared to level 2 mode. Avoidance control must be executed by predicting the movements of multiple road users, such as oncoming vehicles in addition to stopped vehicles 3. Therefore, avoidance control is more difficult for automated driving than following the road. During avoidance control, a handover of driving from the system to the vehicle user (i.e., takeover) is more likely to occur. With the above configuration, the execution of avoidance control is limited when the automation level is 3, thereby reducing the probability of a takeover request occurring. A takeover request is a process that uses the information presentation device 70b to request driving operations from the vehicle user. A takeover request may include the display of an image or audio output requesting driving operations.

<Another example of operation of the driving system (2)>
After detecting the stopped vehicle 3, the driving system 9 may execute standby control according to traffic conditions and stop the vehicle 1 behind the stopped vehicle 3. The situation in which the vehicle 1 stops behind the stopped vehicle 3 may include a situation in which there is no other vehicle between the stopped vehicle 3 and the vehicle 1, as well as a situation in which one or more other vehicles are present between the stopped vehicle 3 and the vehicle 1.

When vehicle 1 stops behind stopped vehicle 3, the driving system 9 may acquire the forward distance (FL) and determine whether to execute avoidance control based on the forward distance. The forward distance here is the vertical length of the open space in front of vehicle 1.

For example, when vehicle 1 stops behind stopped vehicle 3, the driving system 9 acquires the forward distance (FL) as shown in S261 of FIG. 21. If the forward distance (FL) is greater than a predetermined space threshold (ThFL) (YES in S262), the driving system 9 executes avoidance determination processing in S263. On the other hand, if the forward distance (FL) is equal to or less than the space threshold (ThFL) (NO in S262), the driving system 9 plans and executes waiting control in S264.

"FL" in the figure refers to the vertical length of the open space in front of vehicle 1, i.e., the distance between vehicles ahead. Also, "ThFL" in the figure refers to the space threshold. The space threshold may be set to a distance that ensures a sufficient FOV of the external environment sensor 41 for the oncoming lane OL. For example, the space threshold may be set to 10 m. The space threshold may be adjusted according to the lateral distance between the center line and another vehicle in front of vehicle 1, or the lateral distance between the center of vehicle 1 and the center of another vehicle in front of vehicle 1.

For example, if the preceding vehicle suddenly stops while vehicle 1 is following the preceding vehicle, the preceding vehicle and vehicle 1 will be stopped with a narrow inter-vehicle distance between them. In other words, the forward inter-vehicle distance will be a relatively small value. When the forward inter-vehicle distance is equal to or less than the space threshold, there are many blind spots for the external environment sensor 41, and the uncertainty of the environmental recognition results is high. Therefore, safety can be improved by performing waiting control instead of overtaking control. Furthermore, when the forward inter-vehicle distance is sufficiently large, the FOV for the oncoming lane OL is also good, and the uncertainty of the environmental recognition results is relatively small. Therefore, avoidance control can be executed based on the results of the avoidance judgment processing. The above control can improve convenience for vehicle users while ensuring safety. Furthermore, when the forward inter-vehicle distance is less than a predetermined value, waiting control is simply selected without checking the behavior of the stopped vehicle 3 or oncoming users. This also reduces the processing load on the driving system 9. The driving system 9 may also be configured to issue a takeover request when the forward vehicle distance (FL) is equal to or less than the space threshold (ThFL) (S262 NO).

<Another example of operation of the driving system (3)>
As shown in FIG. 22 , when the driving system 9 determines that a specific scenario (here, a stopped vehicle-related scenario) applies (YES in S271), the driving system 9 may acquire an estimated stop time of the detected stopped vehicle 3 (S272). The detected stopped vehicle 3 may also be referred to as a target. The estimated stop time of the stopped vehicle 3 may be an estimated value of the remaining time from when the stopped vehicle 3 is detected until the stopped vehicle 3 starts moving. In other embodiments, the estimated stop time may be an estimated value of the time from when the stopped vehicle 3 stops until it starts moving. The estimated stop time may be estimated based on the type of the stopped vehicle 3. For example, if the stopped vehicle is a route bus, the estimated stop time may be set to 30 seconds. If the stopped vehicle 3 is a taxi carrying passengers, the estimated stop time may be set to 45 seconds. If the stopped vehicle 3 is a delivery vehicle, the estimated stop time may be set to 2 minutes. If the stopped vehicle 3 is a vehicle used for moving work, the estimated stop time may be set to one hour or more.

The driving system 9 may obtain the expected stopping time of the stopped vehicle 3 by communicating wirelessly with the stopped vehicle 3. The driving system 9 may also obtain the expected stopping time of the stopped vehicle 3 by querying a specific server about the expected stopping time of the stopped vehicle 3. For example, the expected stopping time of a route bus may be obtained by querying a server that manages the operation of the bus. The value of the expected stopping time held by the driving system 9 may be updated over time. In other words, the expected stopping time may be counted down from the time the stopped vehicle 3 is detected.

If the preceding vehicle is a bus, the driving system 9 may be configured to record the bus stopping point and bus stopping time. The driving system 9 may also be configured to determine the expected bus stopping time based on records of past bus stops. The records of bus stops may be collected on a server and shared among multiple driving systems 9.

The driving system 9 may calculate the expected stopping time based on the lighting status or transition of lighting status of lighting devices such as turn signal lamps, brake lamps, and hazard lamps. If the driving system 9 detects that the hazard lamps of the stopped vehicle 3 are on, it may determine the expected stopping time to be long (e.g., 60 seconds). If the driving system 9 detects that the turn signal lamp of the stopped vehicle 3 facing the road edge is flashing, it may also determine the expected stopping time to be long. The road edge direction is the direction toward the road edge to which the vehicle should approach when stopping to stop and open and close its doors. In areas where traffic is on the right, the right side corresponds to the road edge direction, and in areas where traffic is on the left, the left side corresponds to the road edge direction. In the example shown in FIG. 10 , the right side of the vehicle 1 corresponds to the road edge direction. In this disclosure, the direction opposite the road edge direction is also referred to as the road center direction. If the driving system 9 detects that the turn signal lamp of the stopped vehicle 3 facing the road center is flashing, it may determine the expected stopping time to be short (e.g., 10 seconds). The driving system 9 may also determine that the expected stopping time is short if it detects that the brake lights of the stopped vehicle 3 have transitioned from an off state to an on state.

The driving system 9 also calculates the required avoidance time in consideration of the traffic conditions in the oncoming lane OL (S273). The required avoidance time is the time required to avoid (in other words, pass by or overtake) the stopped vehicle 3. The required avoidance time may vary depending on the traffic conditions in the oncoming lane OL. If avoidance control can be implemented without stopping the vehicle 1, the required avoidance time may be determined according to the current driving speed. A case in which avoidance control can be implemented without stopping the vehicle 1 corresponds to a case in which there are no oncoming vehicles, etc. The required avoidance time when avoidance control can be implemented without stopping may be a fixed value, such as 10 seconds.

Depending on the traffic conditions in the oncoming lane, vehicle 1 may need to stop temporarily behind stopped vehicle 3. The required avoidance time when vehicle 1 is forced to stop temporarily behind stopped vehicle 3 may be a predetermined expected value, such as 30 seconds. The required avoidance time when a temporary stop is included may be the sum of the actual avoidance time and the departure waiting time. The actual avoidance time is the time required from starting from a stopped state to getting in front of the stopped vehicle 3, and may be the sum of the times required for the initial phase, middle phase, and final phase. The actual avoidance time may be calculated based on the basic value of acceleration for avoidance control and the longitudinal length of the stopped vehicle 3. The departure waiting time is determined according to the traffic conditions in the oncoming lane OL. The departure waiting time may be calculated based on the position and number of oncoming vehicles included in the FOV of the external environment sensor 41 at the time vehicle 1 stops behind stopped vehicle 3. The departure waiting time may be updated periodically.

When the driving system 9 detects a stopped vehicle 3, it obtains the expected stopping time and the required time for avoidance using the method described above or any other method. Then, the driving system 9 compares the expected stopping time with the required time for avoidance to determine whether to avoid the stopped vehicle 3 or wait (S274). For example, the driving system 9 may determine to perform avoidance control if the expected stopping time is greater than the required time for avoidance by a predetermined value or more (S275). In this case, avoidance control may be started when the conditions for executing avoidance control are met. On the other hand, if the value obtained by subtracting the required time for avoidance from the expected stopping time is less than a predetermined value, the driving system 9 determines to stop and wait behind the stopped vehicle 3 without performing avoidance control (S276). This is because if the waiting time is short, there is little need for avoidance control. In Figure 22, "TL1" represents the expected stopping time, "TL2" represents the required time for avoidance, and "ThTL" represents the predetermined value.

Note that even while waiting in S276, if the conditions for executing avoidance control are met and preparatory movements for starting by the stopped vehicle 3 have not yet been detected, the driving system 9 may start avoidance control at that timing. This is because the expected stopping time may deviate from the actual stopping time. Preparatory movements for starting may include turning off the brake lights, turning on the blinker lights toward the center of the road, closing the doors, or making an announcement that the vehicle is about to start. Preparatory movements for starting may be referred to as signs of starting. Preparatory movements for starting may be detected based on sensor data (for example, camera images or external sound information).

<Another example of operation of the driving system (4)>
23 shows an example of the operation of the driving system 9 in a scenario in which a stopped vehicle 3 attempts to start while vehicle 1 is executing avoidance control. As described above, the driving system 9 monitors the behavior of the stopped vehicle 3 even after starting avoidance control (S281). The driving system 9 may be configured to, in principle, stop avoidance control if it detects the stopped vehicle 3 starting or a preparatory movement for starting while executing avoidance control (S282).

However, if the driver of vehicle 3 notices vehicle 1 attempting to pass vehicle 3, vehicle 3 may cancel its departure and give up the right of way to vehicle 1. In such a case, vehicle 1 may resume or retry avoidance control. That is, the driving system 9 continues to monitor the behavior of vehicle 3 even after deciding to discontinue avoidance control in S283 (S284), and if vehicle 3 takes a predetermined action to give up the right of way to vehicle 1 (S285 YES), it may resume or continue avoidance control (S286).

The predetermined action of vehicle 3 yielding the right of way may be an action indicating that the departure is canceled. For example, if vehicle 3's brake lights turn off and then come on again within a few seconds (e.g., 3 seconds), the driving system 9 may determine that vehicle 3 has given way to vehicle 1. Also, if vehicle 3's turn signal light toward the center of the road turns on and then the brake light turns on within a few seconds, the driving system 9 may determine that vehicle 3 has given way to vehicle 1.

In this way, the driving system 9 may execute avoidance control if the vehicle transitions back to a complete stop state within a predetermined time after the vehicle 3 starts or performs a preparatory action for starting. A complete stop state is a stopped state in which there is no preparatory action for starting. For example, this is a state in which the vehicle is stopped with the hazard lights on, a state in which the blinker lights toward the road edge are on, or a state in which the door is open. The driving system 9 may also assume that the vehicle is in a complete stop state for a predetermined time after the brake lights transition from an off state to an on state.

As described above, in a scenario where it is highly likely that stopped vehicle 3 has given way to vehicle 1, the driving system 9 may be configured to execute avoidance control. This can smooth the flow of traffic. Note that if the driving system 9 does not detect any behavior of vehicle 3 that would cause it to stop moving after avoidance control is stopped (S285 NO), it will cause vehicle 1 to wait behind vehicle 3 (S287).

<Another example of operation of the driving system (5)>
The driving system 9 may be configured to be able to detect a siren (also referred to as an alarm sound) of an emergency vehicle using an acoustic sensor. When the stopped vehicle 3 is an emergency vehicle, the driving system 9 may determine whether to perform avoidance control depending on whether the emergency vehicle serving as the stopped vehicle 3 is emitting a siren. When the emergency vehicle serving as the stopped vehicle 3 is emitting a siren, the driving system 9 causes the vehicle 1 to wait behind the stopped vehicle 3 without performing avoidance control. On the other hand, when the emergency vehicle serving as the stopped vehicle 3 is not emitting a siren, the driving system 9 may perform avoidance control in response to the establishment of a condition for executing avoidance control. Note that when the stopped vehicle 3 is an emergency vehicle, even if a siren is not being emitted, the driving system 9 may be configured to temporarily stop (i.e., wait temporarily) behind the stopped vehicle 3 in preparation for a person running out into the road, etc.

Furthermore, the driving system 9 may be configured not to perform avoidance control if an emergency vehicle with a siren is detected behind the vehicle 1, even if the stopped vehicle 3 itself is not an emergency vehicle. In a scenario in which the driving system 9 detects a stopped vehicle 3 ahead and an emergency vehicle with a siren behind the vehicle 1, the driving system 9 may be configured to stop the vehicle 1 along the edge of the road behind the stopped vehicle 3.

Furthermore, the driving system 9 may be configured not to perform avoidance control even when an emergency vehicle with a siren emitting is detected in the oncoming lane OL, even if the stopped vehicle 3 itself is not an emergency vehicle. In a scenario in which the driving system 9 detects a stopped vehicle 3 ahead and an emergency vehicle with a siren emitting is detected in the oncoming lane OL, the driving system 9 may be configured to have the vehicle 1 wait behind the stopped vehicle 3. These operations reduce the risk of the vehicle 1 obstructing the passage of the emergency vehicle. Emergency vehicles here may include ambulances, fire engines, police cars, etc. Emergency vehicles may also include specialized work vehicles for repairing infrastructure facilities such as electricity, gas, or water.

<Dynamic adjustment of inter-vehicle distance in preparation for avoidance control>
The driving system 9 may change the set value of the following distance depending on whether the preceding vehicle is a specific type of vehicle that may stop periodically. FIG. 24 shows an example of a process for changing the set value of the following distance depending on the type of the preceding vehicle. A typical example of a specific type of vehicle is a route bus. Route buses may include trolleys, etc. In areas where passing by stopped school buses is not prohibited, school buses may also be included in the specific type of vehicle. Delivery vehicles may also be included in the specific type of vehicle.

When the driving system 9 detects a preceding vehicle, it analyzes the camera image to obtain the type of the preceding vehicle (S291). It then determines whether the preceding vehicle is a specific type of vehicle (S292). If the driving system 9 is following a specific type of vehicle (S291 YES), it increases the set value of the inter-vehicle distance from the basic value (S293). In other words, in response to the preceding vehicle being a specific type of vehicle, the driving system 9 increases the set value of the inter-vehicle distance from the basic value. The amount of increase in the inter-vehicle distance may be 5 m, 10 m, or the like. The inter-vehicle distance may be specified by the inter-vehicle time, which may be 1 second, for example. The inter-vehicle time is a parameter that represents the time from when the preceding vehicle passes a certain point until the vehicle Hv passes the same point.

In this way, the driving system 9 increases the following distance when the preceding vehicle is a specific type of vehicle compared to when the preceding vehicle is not a specific type of vehicle. By increasing the following distance, visibility of oncoming traffic in the lane OL can be improved. It also makes it easier to stop closer to the center line in preparation for avoidance control.

Furthermore, the driving system 9 may obtain information on predicted stopping points, which are locations where the preceding vehicle is likely to stop, by referring to map data. If the preceding vehicle is a route bus, the predicted stopping points may be bus stops. When driving while following a school bus, the driving system 9 may be configured to record the stopping points and stopping times of the school bus. The driving system 9 may also be configured to identify predicted stopping points of the school bus based on records of past school bus stops. Records of school bus stops may be collected on a server and shared among multiple driving systems 9.

The driving system 9 may be configured to change the set value of the inter-vehicle distance when the preceding vehicle is a specific type of vehicle and the distance from vehicle 1 to the predicted stopping point is within a predetermined value. For example, when driving in a situation where the driving system 9 is following a specific type of vehicle, the driving system 9 may change the set value of the inter-vehicle distance from the basic value to a value that is a predetermined amount larger based on the fact that the distance from vehicle 1 to the predicted stopping point is within a predetermined value. When the distance from vehicle 1 to the predicted stopping point is larger than the predetermined value, the driving system 9 may apply the basic value as the set value of the inter-vehicle distance. The predicted stopping point used here may be an expected stopping point that corresponds to the preceding vehicle. If the preceding vehicle is a route bus, the driving system 9 does not use the predicted stopping point for the school bus, but uses the predicted stopping point for the route bus.

According to the above operation example, when the vehicle is traveling away from the predicted stopping point for the preceding vehicle, the normal inter-vehicle distance is maintained. On the other hand, when the vehicle approaches the predicted stopping point for the preceding vehicle, the inter-vehicle distance is increased. This allows vehicle 1 to be stopped while maintaining a safe inter-vehicle distance even if the preceding vehicle has stopped, improving visibility of the road beyond the stopped preceding vehicle.

In relation to the above, if the predicted stopping point is included in the FOV of the external environment sensor 41, the driving system 9 may verify whether there are pedestrians waiting for the preceding vehicle at the predicted stopping point. For example, if the preceding vehicle is a route bus, the driving system 9 may determine whether there are people at the bus stop based on the sensor data of the external environment sensor 41.

When the driving system 9 detects a person waiting at a bus stop while following a route bus, it may perform lateral position adjustment for avoidance control. Lateral position adjustment is adjusting the driving position of the vehicle 1 in the lateral direction (in other words, the road width direction). The lateral position during normal driving may be the lane center. The lateral position may be defined as the center of the body of the vehicle 1, for example, the center of the front end in the vehicle width direction. Lateral position adjustment for avoidance control may be shifting the lateral position of the vehicle 1 a predetermined amount from the lane center in the avoidance direction. The avoidance direction is the direction from the center of the ego lane EL toward the center line or oncoming lane OL. In this disclosure, driving the vehicle 1 along the lane with the center of the vehicle 1 closer to the center line than the lane center is also referred to as offset driving for avoidance control.

The offset amount in offset driving, i.e., the amount of deviation of the center of vehicle 1 from the center of the lane, may be a constant value such as 0.5 m. The offset amount may also be dynamically adjusted based on the center line. Offset driving may be a control that drives vehicle 1 along the road while maintaining a distance between vehicle 1 and the center line that is less than a predetermined value (e.g., 0.3 m).

When the lateral position is closer to the lane center in the avoidance direction, visibility into the oncoming lane OL is better than when vehicle 1 is in the lane center. Blind spots caused by stopped vehicles 3 are reduced, improving the detectability of other road users, such as oncoming vehicles. This can also increase the reliability of the recognition result that there are no oncoming vehicles.

The driving system 9 may be configured to maintain the center of the lane without adjusting the lateral position for avoidance control when no person is detected at the stop ahead while following a route bus. Note that even when no person is detected at the stop ahead while following a route bus, the driving system 9 may adjust the lateral position for avoidance control when a warning of an impending stop is displayed on the rear display of the route bus.

<Road structure>
The above-described control may also be applied when the vehicle 1 is traveling on a community road, as shown in Figure 25. A community road here may be a road without lane markings including a center line, for example, a road with a width less than a predetermined value. A community road may also be referred to as a narrow street.

The above-described control may also be applied when the vehicle 1 is traveling on a road with two or more lanes in each direction, as shown in Figure 26. In this disclosure, of the lanes that have the same traveling direction, the lane adjacent to the road edge 81 is also referred to as the first lane L1. Furthermore, the lane adjacent to the first lane L1 that has the same traveling direction as the first lane is referred to as the second lane L2. The second lane L2 is located on the opposite side of the road edge 81 from the first lane L1. The temporary traffic lane TL used for avoidance control may be the second lane L2. In Figure 26, 84 indicates the lane marking that marks the boundary between the first lane L1 and the second lane L2.

As shown in FIG. 27, the driving system 9 may be configured to change the intersection timing depending on whether the temporary traffic lane TL and the original lane BL are traveling in the same direction. The intersection timing here refers to the timing at which the boundary between the original lane and the temporary traffic lane is crossed. That is, when the driving system 9 detects a stopped vehicle 3, it acquires road configuration data in S301. Note that S301 may also be executed in response to a decision to perform avoidance control. The road configuration data may be data indicating whether the lane next to the ego lane EL is an oncoming lane or a same-direction lane. If it is determined that the temporary traffic lane is a same-direction lane, the driving system 9 sets the intersection timing earlier in S303. On the other hand, if it is determined that the temporary traffic lane is an oncoming lane, the driving system 9 sets the intersection timing earlier in S304. Here, an earlier intersection timing may be, for example, 20 or 30 meters behind the stopped vehicle 3. A later intersection timing may be, for example, 5 or 10 meters behind the stopped vehicle 3.

<Setting control parameters related to speed adjustment>
The driving system 9 may be configured to be able to perform not only avoidance control but also overtaking control. Overtaking control is control for overtaking a preceding vehicle that is traveling by changing lanes. The overtaking control and avoidance control may be aspects of automatic driving or driving assistance by the driving system 9.

The driving system 9 may have registered therein setting data for control parameters to be applied during overtaking control and setting data for control parameters to be applied during avoidance control. The control parameters may include a base value for acceleration, an upper limit for acceleration, a base value for speed, an upper limit for speed, and an upper limit for steering speed. The various base values may be understood as values to be applied in situations where there are no special circumstances. The setting data may be stored in memory 51a.

The base and upper limits of acceleration for avoidance control may be set smaller than the base and upper limits of acceleration for overtaking control. Furthermore, the base and upper limits of speed for avoidance control may be set smaller than the base and upper limits of speed for overtaking control. In other words, avoidance control may be set to be executed more slowly than overtaking control.

In other embodiments, the base and upper limits of acceleration for avoidance control may be set to be greater than the base and upper limits of acceleration for overtaking control. Control parameters for cases in which avoidance control is initiated from a stopped state may be registered in the main unit 51 separately from control parameters for cases in which avoidance control is initiated from a moving state (without stopping).

Furthermore, the control parameters may include a parameter that specifies the crossing timing, which is the timing at which a lane mark is crossed for avoidance or overtaking. When the temporary traffic lane is a same-direction lane, the crossing timing for avoidance control may be set to be earlier than the crossing timing for overtaking control. A same-direction lane is a lane that travels in the same direction as the ego lane EL.

For example, if the crossing timing in overtaking control is 20 m, the crossing timing in avoidance control when the temporary traffic lane is a same-direction lane may be set to 30 m behind the stopped vehicle 3. Furthermore, when the temporary traffic lane is an oncoming lane, the crossing timing in avoidance control may be set to a relatively short value, such as 5 m behind the stopped vehicle 3. The crossing timing in overtaking control may be rephrased as the lane change timing.

<System Configuration>
In one embodiment, some or all of the risk confirmation units 26 may be provided in multiple locations for redundancy. In this case, the multiple risk confirmation results may be integrated into a final result by majority vote, and this final result may be reflected in the control of the motion actuator 60.

In one embodiment, the main unit 51 and the risk confirmation unit 53 may be integrated into one or both of a hardware configuration and a software configuration. When the risk confirmation function is integrated with the planning function, the planning unit 20 may set a safety envelope as an allowable limit for the target inter-vehicle distance and target position, and may create a trajectory plan and a behavior plan to avoid reaching the allowable limit. Furthermore, when the allowable limit is reached (i.e., when a violation of the safety envelope occurs), the planning unit 20 may be configured to plan an appropriate response to this.

The driving system 9 may be any of various types of ADS. The driving system 9 may also be an advanced driver-assistance system (ADAS). In one embodiment, the driving system 9 may be equipped with multiple risk confirmation units 26a, 26b, and 26c that form a redundant system, as shown in FIG. 28. The risk confirmation unit 26a is a camera-based risk confirmation unit 26 that acquires the situation and confirms the risk based on images captured by the camera 41a. The risk confirmation unit 26b is a radar-based risk confirmation unit 26 that acquires the situation and confirms the risk based on sensor data output from the millimeter-wave radar 41b. The risk confirmation unit 26c is a LiDAR-based risk confirmation unit 26 that acquires the situation and confirms the risk based on sensor data output from the LiDAR 41c. In this configuration, to ensure hardware redundancy, the planning unit 20, risk confirmation unit 26a, risk confirmation unit 26b, and risk confirmation unit 26c may each be realized by hardware that is independent of each other (e.g., separate computers or SoCs).

The detection unit 10 may include three types of sensors as the multiple external environment sensors 41: one or more cameras 41a, one or more millimeter-wave radars 41b, and one or more LiDARs 41c. Furthermore, the detection unit 10 may have a sensor fusion unit 41d that fuses the detection results of the cameras 41a, millimeter-wave radars 41b, and LiDARs 41c. The external environment recognition results generated by fusing the detection results in the sensor fusion unit 41d may be input to the planning unit 20.

The confirmation results from the risk confirmation units 26a, 26b, and 26c are aggregated in the majority voting unit 26x. The majority voting unit 26x may be a module that arbitrates conflicts between the outputs of multiple risk confirmation units 26. The majority voting unit 26x may be configured to ultimately determine the appropriate response by majority vote and input it to the planning unit 20.

The route plan, behavior plan, and trajectory plan created by the planning unit 20 may be modified or rewritten based on the appropriate response determined and output as a result of the aggregated risk confirmation. The operation system 9 shown in FIG. 28 has three redundant systems for safety, and therefore may be considered an ADS with a three-way redundant majority vote.

The operation system 9 may be a dual-redundant ADS as shown in Figure 29. A dual-redundant ADS means an ADS that has two risk confirmation units 26. In a dual-redundant ADS, if one of the risk confirmation units 26 as a subsystem fails, a DDT fallback may be executed.

The risk confirmation function can be implemented not only in vehicles with automation level 3 or higher, but also in vehicles with automation levels 0 to 2. For example, the driving system 9 may be an ADAS. The risk confirmation unit 53 may perform risk confirmation even when the automation level is set to 0 to 2. Furthermore, even when the automation level is set to 0 to 2, the risk confirmation unit 53 may intervene in the control of the motion actuator 60 by outputting an appropriate response if a violation of the safety envelope occurs. For vehicle V2 driven by a vehicle user, the appropriate response may be to issue a warning to the vehicle user using the information presentation device 70b instead of intervening in the control of the motion actuator 60. Both intervention in the control of the motion actuator 60 and a warning may be implemented.

<Additional remarks (1)>
This specification discloses several technical ideas described in the following paragraphs. Some paragraphs may be written in a multiple dependent form, with the subsequent paragraph alternatively citing the preceding paragraph. These multiple dependent forms define several technical ideas. This disclosure also includes methods, programs, and recording media having programs recorded thereon that correspond to the following operating systems.

[Technical thought 1]
A driving system configured to be able to perform control to autonomously drive a vehicle (1),
a communication circuit (51c) for receiving a signal indicative of an external environment;
a processing unit (51b, 53b) that executes processing related to autonomous driving of the vehicle based on the signal received by the communication circuit,
The processing unit
Identifying whether the scenario corresponds to a scenario in which the vehicle is traveling near another vehicle that is stopped, based on the signal received by the communication circuit;
A driving system configured to: determine a response to the other vehicle depending on the type or behavior of the other vehicle if it is determined that the current situation corresponds to the scenario.

[Technical philosophy 2]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
The driving system described in Technical Idea 1 is configured to determine whether to continue the avoidance control depending on the position of the host vehicle at the time the departure of the other vehicle is detected when the departure of the other vehicle is detected after the avoidance control has been started.

[Technical philosophy 3]
The processing unit
When the start of the other vehicle is detected, if the distance between the host vehicle and the other vehicle in the longitudinal direction is equal to or greater than a safe distance, the avoidance control is stopped;
A driving system according to Technical Idea 2, configured to determine to continue the avoidance control if, at the time when the departure of the other vehicle is detected, the distance between the host vehicle and the other vehicle in the longitudinal direction is less than the safe distance.

[Technical thought 4]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
Detecting a start of the other vehicle based on information indicating a behavior of the other vehicle;
A driving system described in any one of Technical Ideas 1 to 3, which is configured to decide to discontinue the avoidance control if, at the time the departure of the other vehicle is detected, the host vehicle has not crossed the lane mark, or if the amount by which the host vehicle crosses the lane mark is less than a predetermined value.

[Technical philosophy 5]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
A driving system described in any one of Technical Ideas 1 to 4, which is configured to determine whether to continue the avoidance control depending on the speed of the host vehicle at the time the departure of the other vehicle is detected when the departure of the other vehicle is detected after the avoidance control has been started.

[Technical philosophy 6]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
determining to stop the avoidance control based on detection of the start of the other vehicle after the avoidance control is started;
A driving system described in any one of technical ideas 1 to 5, which is configured to decide to retry the avoidance control if it detects that the other vehicle has stopped again after deciding to discontinue the avoidance control.

[Technical Thought 7]
The processing unit
Based on the determination that the current situation corresponds to the scenario, monitor the lighting state of the lighting equipment of the other vehicle;
A driving system according to any one of technical ideas 1 to 6, configured to predict the departure of the other vehicle based on the monitoring results of the lighting state.

[Technical Thought 8]
The processing unit
Based on the determination that the current situation corresponds to the scenario, wireless communication is performed with the other vehicle using a wireless communication device;
A driving system described in any one of technical ideas 1 to 7, configured to predict the departure of the other vehicle based on data received via wireless communication with the other vehicle.

[Technical philosophy 9]
When the departure of the other vehicle is predicted, it is determined not to start avoidance control, which is control to avoid the other vehicle;
The driving system according to Technical Idea 7 or 8, which is configured to determine to start the avoidance control when the departure of the other vehicle is not predicted.

[Technical Thought 10]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle, in which the vehicle moves around in front of the other vehicle through an adjacent lane that is a lane next to the lane blocked by the other vehicle;
A driving system described in any one of technical ideas 1 to 9, which is configured to change the timing of crossing the boundary line between the lane blocked by the other vehicle and the adjacent lane depending on whether the adjacent lane has the same direction of travel as the lane blocked by the other vehicle.

[Technical Thought 11]
The processing unit
a control to avoid another vehicle, the control including going around in front of the other vehicle through an adjacent lane next to the lane in which the other vehicle is present;
and an overtaking control for overtaking a preceding vehicle by changing lanes.
A driving system described in any one of technical ideas 1 to 10, wherein when the adjacent lane is traveling in the same direction as the lane blocked by the other vehicle, the timing of crossing the boundary line to the adjacent lane in the avoidance control is set to a timing earlier than the timing of changing lanes in the overtaking control.

[Technical Thought 12]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
A driving system described in any one of technical ideas 1 to 11, which is configured to create a plan during the avoidance control assuming that there is a vulnerable road user in front of the other vehicle.

[Technical Thought 13]
The processing unit
Based on the determination that the current situation corresponds to the scenario, it is determined whether there are other road users in the oncoming lane;
determining, based on the detection that the other road user is not present in the specific area on the oncoming lane, to initiate avoidance control, which is control to go around in front of the other vehicle through the oncoming lane;
A driving system described in any one of technical ideas 1 to 12, which is configured to determine whether to terminate the avoidance control depending on the type or speed of the other road user if it detects the presence of the other road user in the oncoming lane after the avoidance control has been started.

[Technical Thought 14]
The processing unit
A driving system described in any one of Technical Ideas 1 to 13, which is configured to, if the other vehicle is a school bus, not perform avoidance control, which is control to avoid the other vehicle, but to create a plan to stop behind the other vehicle.

[Technical Thought 15]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
monitoring the behavior of the other vehicle while the avoidance control is being performed;
A driving system described in any one of technical ideas 1 to 14, which is configured to decide to increase the driving speed when behavior related to the other vehicle's departure is detected during the execution of the avoidance control, compared to when behavior related to the other vehicle's departure is not detected.

[Technical Thought 16]
The processing unit
determining whether the other vehicle is a bus;
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the bus, which is the other vehicle;
When a behavior related to the start of the other vehicle is detected during execution of the avoidance control, the avoidance control is stopped,
A driving system according to any one of Technical Ideas 1 to 15, configured to increase a set value of the distance between the vehicle and the preceding vehicle by a predetermined amount.

[Technical Thought 17]
It has multiple operating modes with different levels of automation for driving operations,
The plurality of operation modes include a level 2 mode, which is an operation mode corresponding to the automation level 2, and a level 3 mode, which is an operation mode corresponding to the automation level 3;
The processing unit
If the current situation is determined to correspond to the scenario and the operation mode is the level 2 mode, start avoidance control, which is control to avoid the other vehicle;
A driving system described in any one of technical ideas 1 to 16, which is configured to identify that the current situation corresponds to the scenario and, if the operating mode is the level 3 mode, not initiate avoidance control, which is control to avoid the other vehicle.

[Technical Thought 18]
It has multiple operating modes with different levels of automation for driving operations,
The plurality of operation modes include a level 2 mode, which is an operation mode corresponding to the automation level 2, and a level 3 mode, which is an operation mode corresponding to the automation level 3;
The processing unit
If the current situation is identified as corresponding to the scenario and the operation mode is the level 2 mode or the level 3 mode, starting avoidance control that is control to avoid the other vehicle;
monitoring the behavior of the other vehicle while the avoidance control is being performed;
If the operation mode is the level 2 mode when the behavior related to the start of the other vehicle is detected during the execution of the avoidance control, the avoidance control is continued,
A driving system described in any one of technical ideas 1 to 17, which is configured to stop the avoidance control if the operating mode is the level 3 mode when behavior related to the departure of the other vehicle is detected while the avoidance control is being executed.

[Technical Thought 19]
The processing unit
When the vehicle is stopped based on the fact that the current situation corresponds to the scenario, the length of the empty space in the vertical direction in front of the vehicle is acquired;
A driving system described in any one of technical ideas 1 to 18, which is configured so that if the length of the available space in the vertical direction is less than a predetermined value, avoidance control, which is control to avoid the other vehicle, is not initiated, and the vehicle remains stopped until the available space becomes equal to or greater than a predetermined value, or the user of the vehicle is requested to take over driving.

[Technical Thought 20]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an estimated stopping time of the other vehicle is estimated;
calculating a required avoidance time, which is an estimated value of the time required for the host vehicle to avoid the other vehicle and move in front of the other vehicle;
A driving system described in any one of Technical Ideas 1 to 19, which is configured to determine whether to execute avoidance control, which is control to move in front of the other vehicle to avoid the other vehicle, based on the result of comparing the expected stopping time and the avoidance required time.

[Technical Thought 21]
the signal indicating the external environment includes information about a preceding vehicle;
The processing unit
Identifying whether the preceding vehicle corresponds to a specific type of vehicle that may stop for passenger pick-up/drop-off or delivery based on the signal indicating the external environment received by the communication circuit;
A driving system described in any one of technical ideas 1 to 20, which is configured to increase the inter-vehicle distance from the preceding vehicle to a value greater than the basic value based on determining that the preceding vehicle is a vehicle of the specific type.

[Technical Thought 22]
the signal indicating the external environment includes information about a preceding vehicle;
The processing unit
Identifying whether the preceding vehicle corresponds to a specific type of vehicle that may stop for passenger pick-up/drop-off or delivery based on the signal indicating the external environment received by the communication circuit;
Based on the determination that the preceding vehicle corresponds to the specific type of vehicle, an expected stopping point at which the preceding vehicle is likely to stop is acquired;
A driving system described in any one of technical ideas 1 to 21, which is configured to increase the inter-vehicle distance from the preceding vehicle to a predetermined basic value when the remaining distance to the predicted stopping point becomes less than a predetermined value when the vehicle is traveling behind the preceding vehicle of the specific type.

[Technical Thought 23]
the signal indicating the external environment includes information about a preceding vehicle and a pedestrian;
The processing unit
Identifying whether the preceding vehicle is a specific type of vehicle that may stop to let passengers in or out based on the signal indicating the external environment received by the communication circuit;
Based on the determination that the preceding vehicle corresponds to the specific type of vehicle, an expected stopping point at which the preceding vehicle is likely to stop is acquired;
determining whether a pedestrian is waiting at the predicted stopping point based on the signal indicating the external environment received using the communication circuit;
A driving system described in any one of technical ideas 1 to 22, which performs lateral position adjustment to shift the lateral driving position in an avoidance direction from the center of the lane upon determining that a pedestrian is waiting at the expected stopping point.

[Technical Thought 24]
The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated, which is a control to avoid the other vehicle and move in front of the other vehicle;
determining to stop the avoidance control based on detection of a preparatory movement for starting of the other vehicle after starting the avoidance control;
A driving system described in any one of technical ideas 1 to 23, which is configured to decide to retry the avoidance control if an action of the other vehicle that cancels the start is detected after deciding to discontinue the avoidance control.

[Technical Thought 25]
the signal indicating the external environment includes image information indicating the appearance of the other vehicle and sound information outside the vehicle;
The processing unit
If it is determined that the current situation corresponds to the scenario, determining whether the other vehicle is an emergency vehicle based on the image information;
Detecting an alarm sound emitted by an emergency vehicle based on the sound information;
A driving system described in any one of technical ideas 1 to 24, which is configured so that when the other vehicle is an emergency vehicle and the warning sound is detected, the system does not perform avoidance control, which is control to avoid the other vehicle and go around in front of the other vehicle, but stops the vehicle behind the other vehicle.

<Additional remarks (2)>
The various flowcharts shown in this disclosure are all examples, and the number of steps constituting the flowcharts and the execution order of the processes can be changed as appropriate. The controls shown in each flowchart can be combined/executed in parallel to the extent that there is no contradiction. Terms such as acquisition, determination, detection, generation, and calculation can be used interchangeably. The acquisition of certain data by a certain device also includes the device generating the data based on a signal input from another device/sensor. The number of computers included in the driving system 9 and the functions they are responsible for can be changed as appropriate.

The apparatus, system, and methods described herein may be realized by a special-purpose computer comprising a processor programmed to perform one or more functions embodied in a computer program. The apparatus and methods described herein may be realized using dedicated hardware logic circuits. The apparatus and methods described herein may be realized by a combination of a processor that executes a computer program and one or more hardware logic circuits. The processor (51b, 53b, 55b, 57b) may include at least one of a CPU, MPU, GPU, DFP, and RISC-CPU as a core. Some or all of the functions of the special-purpose computer described above may be realized in hardware. Some or all of the functions of the special-purpose computer referred to in the embodiments may be realized using at least one of a SoC, an IC (Integrated Circuit), and an FPGA (Field-Programmable Gate Array). The computer program includes instructions executed by a computer. The computer program may be stored on at least one computer-readable non-transitory tangible storage medium. The computer program storage medium may be a variety of media, such as a hard-disk drive (HDD), a solid-state drive (SSD), or flash memory.

Claims (26)

A driving system configured to be able to perform control to autonomously drive a vehicle (1),
a communication circuit (51c) for receiving a signal indicative of an external environment;
a processing unit (51b, 53b) that executes processing related to autonomous driving of the vehicle based on the signal received by the communication circuit,
The processing unit
Identifying whether the current situation corresponds to a scenario in which the vehicle is traveling near another vehicle that is stopped, based on the signal received by the communication circuit;
A driving system configured to determine a response to the other vehicle based on the type or behavior of the other vehicle based on the identification that the current situation corresponds to the scenario. The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
2. The driving system according to claim 1, wherein, when the departure of the other vehicle is detected after the avoidance control has been initiated, the driving system is configured to determine whether or not to continue the avoidance control depending on the position of the host vehicle at the time the departure of the other vehicle is detected. The processing unit
When the start of the other vehicle is detected, if the distance between the host vehicle and the other vehicle in the longitudinal direction is equal to or greater than a safe distance, the avoidance control is stopped;
3. The driving system according to claim 2, wherein the driving system is configured to determine to continue the avoidance control if, at the time when the start of the other vehicle is detected, the distance between the host vehicle and the other vehicle in the longitudinal direction is less than the safe distance. The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
Detecting a start of the other vehicle based on information indicating a behavior of the other vehicle;
2. The driving system according to claim 1, wherein the driving system is configured to determine to discontinue the avoidance control if, at the time when the start of the other vehicle is detected, the host vehicle has not crossed the lane mark, or if the amount by which the host vehicle crosses the lane mark is less than a predetermined value. The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
2. The driving system according to claim 1, wherein, when the start of the other vehicle is detected after the avoidance control has been initiated, the driving system is configured to determine whether or not to continue the avoidance control depending on the speed of the host vehicle at the time the start of the other vehicle is detected. The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
determining to stop the avoidance control based on detection of the start of the other vehicle after the avoidance control is started;
2. The driving system according to claim 1, wherein the driving system is configured to determine to retry the avoidance control when the other vehicle is detected to have stopped again after determining to stop the avoidance control. The processing unit
monitor the lighting status of the lighting equipment of the other vehicle;
The driving system according to claim 1 , configured to predict the start of the other vehicle based on the monitoring result of the lighting state. The processing unit
wireless communication with the other vehicle using a wireless communication device;
The driving system according to claim 1 , configured to predict a start of the other vehicle based on data received by wireless communication with the other vehicle. When the departure of the other vehicle is predicted, it is determined not to start avoidance control, which is control to avoid the other vehicle;
9. The driving system according to claim 7, wherein the driving system is configured to determine to start the avoidance control when the start of the other vehicle is not predicted. The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle, in which the vehicle moves around in front of the other vehicle through an adjacent lane that is a lane next to the lane blocked by the other vehicle;
The driving system of claim 1, configured to change the timing of crossing the boundary line between the lane blocked by the other vehicle and the adjacent lane depending on whether the adjacent lane is traveling in the same direction as the lane blocked by the other vehicle. The processing unit
a control to avoid another vehicle, the control including going around in front of the other vehicle through an adjacent lane next to the lane in which the other vehicle is present;
and an overtaking control for overtaking a preceding vehicle by changing lanes.
2. The driving system of claim 1, wherein when the adjacent lane is traveling in the same direction as the lane blocked by the other vehicle, the timing of crossing the boundary line to the adjacent lane in the avoidance control is set to be earlier than the timing of changing lanes in the overtaking control. The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
The driving system according to claim 1 , configured to create a plan during the avoidance control assuming that there is a vulnerable road user ahead of the other vehicle. The processing unit
Based on the determination that the current situation corresponds to the scenario, it is determined whether there are other road users in the oncoming lane;
determining, based on the detection that the other road user is not present in the specific area on the oncoming lane, to initiate avoidance control, which is control to go around in front of the other vehicle through the oncoming lane;
2. The driving system according to claim 1, wherein, when the presence of the other road user in the oncoming lane is detected after the avoidance control has been started, the driving system is configured to determine whether or not to terminate the avoidance control depending on the type of the other road user. The processing unit
The driving system according to claim 1, wherein, when the other vehicle is a school bus, the driving system is configured to create a plan to stop behind the other vehicle without executing avoidance control to avoid the other vehicle. The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the other vehicle;
monitoring the behavior of the other vehicle while the avoidance control is being performed;
2. The driving system according to claim 1, wherein, when a behavior related to the other vehicle's departure is detected while the avoidance control is being executed, the driving system is configured to determine to increase the driving speed compared to when a behavior related to the other vehicle's departure is not detected. The processing unit
determining whether the other vehicle is a bus;
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated to avoid the bus, which is the other vehicle;
When a behavior related to the start of the other vehicle is detected during execution of the avoidance control, the avoidance control is stopped,
2. The driving system according to claim 1, wherein the driving system is configured to increase a set distance between the vehicle and the preceding vehicle by a predetermined amount. It has multiple operating modes with different levels of automation for driving operations,
The plurality of operation modes include a level 2 mode, which is an operation mode corresponding to the automation level 2, and a level 3 mode, which is an operation mode corresponding to the automation level 3;
The processing unit
If the current situation is determined to correspond to the scenario and the operation mode is the level 2 mode, start avoidance control, which is control to avoid the other vehicle;
The driving system of claim 1, wherein the system is configured not to initiate avoidance control, which is control to avoid the other vehicle, when the current situation is identified as falling under the scenario and the operating mode is the level 3 mode. It has multiple operating modes with different levels of automation for driving operations,
The plurality of operation modes include a level 2 mode, which is an operation mode corresponding to the automation level 2, and a level 3 mode, which is an operation mode corresponding to the automation level 3;
The processing unit
If the current situation is identified as corresponding to the scenario and the operation mode is the level 2 mode or the level 3 mode, starting avoidance control that is control to avoid the other vehicle;
monitoring the behavior of the other vehicle while the avoidance control is being performed;
If the operation mode is the level 2 mode when the behavior related to the start of the other vehicle is detected during the execution of the avoidance control, the avoidance control is continued,
The driving system according to claim 1, wherein the avoidance control is stopped if the operation mode is the level 3 mode when the behavior of the other vehicle related to the start of the other vehicle is detected during the execution of the avoidance control. The processing unit
When the vehicle is stopped based on the fact that the current situation corresponds to the scenario, the length of the empty space in the vertical direction in front of the vehicle is acquired;
The driving system of claim 1, wherein if the length of the free space in the vertical direction is less than a predetermined value, avoidance control, which is control to avoid the other vehicle, is not initiated, and the vehicle remains stopped until the free space becomes equal to or greater than a predetermined value, or the system is configured to request the user of the vehicle to take over driving. The processing unit
Based on the determination that the current situation corresponds to the scenario, an estimated stopping time of the other vehicle is estimated;
calculating a required avoidance time, which is an estimated value of the time required for the host vehicle to avoid the other vehicle and move in front of the other vehicle;
2. The driving system according to claim 1, configured to determine whether to execute avoidance control, which is control to move in front of the other vehicle to avoid the other vehicle, based on a result of comparing the expected stopping time and the avoidance required time. the signal indicating the external environment includes information about a preceding vehicle;
The processing unit
Identifying whether the preceding vehicle corresponds to a specific type of vehicle that may stop for passenger pick-up/drop-off or delivery based on the signal indicating the external environment received by the communication circuit;
2. The driving system according to claim 1, wherein the driving system is configured to increase the inter-vehicle distance from the preceding vehicle to a value greater than a basic value based on the determination that the preceding vehicle corresponds to the specific type of vehicle. the signal indicating the external environment includes information about a preceding vehicle;
The processing unit
Identifying whether the preceding vehicle corresponds to a specific type of vehicle that may stop for passenger pick-up/drop-off or delivery based on the signal indicating the external environment received by the communication circuit;
Based on the determination that the preceding vehicle corresponds to the specific type of vehicle, an expected stopping point at which the preceding vehicle is likely to stop is acquired;
2. The driving system of claim 1, wherein when the vehicle is traveling behind the preceding vehicle of the specific type and the remaining distance to the predicted stopping point becomes less than a predetermined value, the driving system is configured to increase the inter-vehicle distance from the preceding vehicle to a value greater than a predetermined basic value. the signal indicating the external environment includes information about a preceding vehicle and a pedestrian;
The processing unit
Identifying whether the preceding vehicle is a specific type of vehicle that may stop to let passengers in or out based on the signal indicating the external environment received by the communication circuit;
Based on the determination that the preceding vehicle corresponds to the specific type of vehicle, an expected stopping point at which the preceding vehicle is likely to stop is acquired;
determining whether a pedestrian is waiting at the predicted stopping point based on the signal indicating the external environment received using the communication circuit;
The driving system according to claim 1, wherein, upon determining that a pedestrian is waiting at the predicted stopping point, a lateral position adjustment is performed to shift the lateral driving position from the center of the lane in an avoidance direction. The processing unit
Based on the determination that the current situation corresponds to the scenario, an avoidance control is initiated, which is a control to avoid the other vehicle and move in front of the other vehicle;
determining to stop the avoidance control based on detection of a preparatory movement for starting of the other vehicle after starting the avoidance control;
2. The driving system according to claim 1, wherein the driving system is configured to determine to retry the avoidance control when an action of the other vehicle that cancels the start of the vehicle is detected after the decision to discontinue the avoidance control has been made. the signal indicating the external environment includes image information indicating the appearance of the other vehicle and sound information outside the vehicle;
The processing unit
If it is determined that the current situation corresponds to the scenario, determining whether the other vehicle is an emergency vehicle based on the image information;
Detecting an alarm sound emitted by an emergency vehicle based on the sound information;
2. The driving system according to claim 1, wherein, when the other vehicle is an emergency vehicle and the warning sound is detected, the driving system is configured to stop the own vehicle behind the other vehicle without performing avoidance control, which is a control to avoid the other vehicle and go around in front of the other vehicle. A method executed by a processor included in a driving system configured to be able to autonomously drive a vehicle (1), comprising:
Identifying whether the current situation corresponds to a scenario in which the vehicle is traveling near another vehicle that is stopped, based on a signal indicating the external environment received by the communication circuit;
and determining a response to the other vehicle depending on the type or behavior of the other vehicle based on the current situation being identified as falling under the scenario.