DE102023004958A1 - System for reducing the effects of impact on an ego vehicle and method therefor - Google Patents

Abstract

The present disclosure provides a system and method for reducing the impact of an impact on the ego vehicle (410). It includes identifying the presence of an object (420) within an area of interest (Aol) from the current position of the ego vehicle (410) and estimating a crash accordingly. Furthermore, it involves determining a best collision point when an accident is assumed to be imminent and then predicting an optimal trajectory for the ego vehicle (410) to reach the determined collision point, taking into account one or more parameters associated with the ego vehicle (410) and the object (420), wherein the best collision point is predetermined based on a passive simulation performed using real crash scenarios. It also includes calculating the required lateral position shift and yaw rate associated with the ego vehicle (410) based on the predicted trajectory to reduce the impact on the ego vehicle (410).

Description

The present disclosure relates to the field of advanced driver assistance systems (ADAS). In particular, the present disclosure provides a system and method for reducing the effects of an impact on an ego vehicle.

Car manufacturers are launching more and more variants of autonomous vehicles. These vehicles are controlled by coding embedded in them to provide the driver/owner with the convenience and benefits of freedom. These vehicles, as can be seen, use algorithms for route setting and pre-programmed situations to avoid probable collisions through the use of sensors and the lidar/radar principle. However, the decision-making ability to replace the general steering behavior of a human with steering wheel control is limited to what has been instructed in such situations, leaving gaps that need to be filled to avoid collisions under illustrative circumstances.

Many techniques have been developed to circumvent the problems mentioned above, for example, the patent document US10836383B2 a collision-impending steering control system and method comprising a collision-impending steering control system having a controller in electrical communication with the steering mechanism and configured to adjust a steering sequence to change the vehicle trajectory when an obstacle is detected at a distance from the vehicle that is less than a calculated safe stopping distance, by calculating the predicted optimal vehicle path around the obstacle and a steering sequence determined using feedback from the controller to follow the predicted optimal path around the obstacle. However, the cited document does not focus on reducing the effects of an impact on the vehicle when the impact is unavoidable.

Patent document KR101465649B1 refers to a method of controlling a vehicle and includes: determining a target position for avoiding an obstacle or changing a route based on the current position of the vehicle by calculating a changed spatial or temporal vehicle trajectory by calculating a parameter using the steering angle control pattern model extracted from the driving behavior data based on the determined target position. However, the cited document does not focus on reducing the impact of an impact on the vehicle when the impact is unavoidable.

The patent document US20130030651A1 discloses a collision avoidance system using differential braking in the event that normal steering control fails. The system detects whether a collision with an object ahead of the vehicle is imminent and, if so, determines an optimal path for the vehicle to avoid the object. The system may determine that automatic steering is required to take the optimal path to avoid the target, and if the system does not determine that automatic steering is required and detects that normal steering has failed, the system uses differential braking to steer the vehicle along the path. However, the cited document does not focus on reducing the effects of an impact on the vehicle when the impact is unavoidable.

There is therefore a need to provide an accurate and efficient solution that focuses on reducing the impact of an impact on a vehicle when the accident is imminent.

A general object of the present disclosure is to provide an accurate and efficient system and method that eliminates the above-mentioned limitations of existing systems and methods and reduces the impact effects on the ego vehicle when impact is imminent.

An object of the present disclosure is to provide a system and method in which the use of passive safety simulation data improves the utilization of the vehicle structure to absorb more energy and minimize repairability costs in the event of a collision.

Another object of the present disclosure is to provide a system and method that determines a best collision point so that the effects of the impact are reduced.

Yet another object of the present disclosure is to provide an intelligent and intelligent system and method that ensures minimal damage to the vehicle and the occupants inside.

Aspects of the present disclosure relate to the field of Advanced Driver Assistance Systems (ADAS, ADAS). In particular, the present disclosure provides a system and method for reducing the effects of an impact on an ego vehicle.

One aspect of the present disclosure relates to a system for reducing the effects of an impact on an ego vehicle. The system includes a controller operatively coupled to a learning machine, the controller including a processor coupled to a memory, the memory storing one or more instructions executable by the processor to: identify, through a monitoring unit communicating with the controller, the presence of an object within an area of interest (AOL) from the current position of the ego vehicle and estimate a crash accordingly; if an accident is deemed imminent, determine a best collision point to minimize damage to the ego vehicle; considering one or more parameters associated with the ego vehicle and the object, predict an optimal trajectory for the ego vehicle to reach the determined collision point; and calculate, based on the predicted trajectory, the required lateral position shift and yaw rate associated with the ego vehicle to reduce the effects of the impact on the ego vehicle; wherein the best collision point is predetermined based on a passive simulation performed using real crash scenarios.

In one aspect, the learning engine may be trained using a training and test dataset related to the passive simulation performed using multiple real-world crash scenarios, with the output of the learning engine used as feedback to the system. Further, based on the output, the system may calculate the collision point, the required lateral position shift, and the yaw rate associated with the ego vehicle.

In another aspect, the one or more parameters may include the distance between the ego vehicle and the object, the size of the vehicle, the relative speed, the time of impact, the impact zone, the direction of approach, and the object type.

In one aspect, the system may estimate that the collision between the ego vehicle and the object is imminent when the distance between the ego vehicle and the identified object is less than a safe distance or the relative speed between the ego vehicle and the identified object exceeds a threshold speed.

In another aspect, after estimating the impact, the controller may actuate an actuator operatively coupled to a steering assembly of the ego vehicle, wherein the actuator element, when actuated, may facilitate the controller in maneuvering the steering assembly to reach the determined collision point.

Another aspect of the present disclosure relates to a method for reducing the impact of an impact on an ego vehicle. The method includes: identifying, by a monitoring unit, the presence of an object within an area of interest (Aol) from the current position of the ego vehicle and estimating an impact accordingly; determining, at a controller operatively coupled to a learning machine, a best collision point to cause as little damage to the ego vehicle as possible when a crash is believed to be imminent; predicting, at the controller, an optimal trajectory for the ego vehicle to reach the determined collision point, taking into account one or more parameters associated with the ego vehicle and the object; and calculating, at the controller, the required lateral position shift and yaw rate associated with the ego vehicle, based on the predicted trajectory to reduce the impact of the impact on the ego vehicle; where the best collision point is predetermined based on a passive simulation performed using real crash scenarios.

In one aspect, the method may include training the learning machine using a training and test dataset related to the passive simulation performed using multiple real-world crash scenarios, using the output of the learning machine as feedback, and wherein the method may further include calculating the collision point, the required lateral positional displacement, and the yaw rate associated with the ego vehicle based on the output.

In another aspect, the one or more parameters may include the distance between the ego vehicle and the object, the relative speed, the time of impact, the impact zone, the direction of approach, and the object type.

In another aspect, the method may include estimating the imminent collision between the ego vehicle and the object when the distance between the ego vehicle and the identified object is less than a safety distance or the relative speed between the ego vehicle and the identified object exceeds a threshold speed.

In another aspect, the method may include, after estimating the impact, actuating an actuator operatively coupled to a steering assembly of the ego vehicle, wherein the actuator, when actuated, facilitates the controller in maneuvering the steering assembly to reach the determined collision point.

Various objects, features, aspects and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments taken in conjunction with the accompanying drawing figures in which like numerals represent like parts.

• 1 veranschaulicht eine beispielhafte Netzwerkarchitektur des vorgeschlagenen Systems zur Verringerung der Auswirkungen eines Aufpralls auf ein Ego-Fahrzeug, um seine Gesamtfunktionsweise in Übereinstimmung mit einer Ausführungsform der vorliegenden Offenbarung zu veranschaulichen.
• 2 zeigt beispielhafte Funktionseinheiten eines Controllers, der mit dem vorgeschlagenen System verbunden ist, in Übereinstimmung mit einer beispielhaften Ausführungsform der vorliegenden Offenbarung.
• 3 veranschaulicht ein Flussdiagramm, das das Training des vorgeschlagenen Systems für unmittelbar bevorstehende Crashbedingungen unter Verwendung einer passiven Sicherheitssimulation gemäß einer Ausführungsform der vorliegenden Offenbarung darstellt.
• 4 veranschaulicht einen beispielhaften Zustand eines unmittelbar bevorstehenden Frontalaufpralls gemäß einer Ausführungsform der vorliegenden Offenbarung.
• Die 5A und 5B veranschaulichen Flussdiagramme, die ein schrittweises Arbeiten des vorgeschlagenen Systems gemäß einer Ausführungsform der vorliegenden Offenbarung darstellen.
• 6 ist ein Flussdiagramm, das das vorgeschlagene Verfahren zur Verringerung des Aufpralls auf ein Ego-Fahrzeug gemäß einer Ausführungsform der vorliegenden Offenbarung darstellt.
• 7 veranschaulicht ein beispielhaftes Computersystem, in dem oder mit dem Ausführungsformen der vorliegenden Erfindung in Übereinstimmung mit Ausführungsformen der vorliegenden Offenbarung verwendet werden können.

The accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

• 1 illustrates an exemplary network architecture of the proposed system for reducing the impact of an impact on an ego vehicle to illustrate its overall operation in accordance with an embodiment of the present disclosure.
• 2 shows exemplary functional units of a controller connected to the proposed system, in accordance with an exemplary embodiment of the present disclosure.
• 3 illustrates a flowchart depicting training of the proposed system for imminent crash conditions using passive safety simulation according to an embodiment of the present disclosure.
• 4 illustrates an exemplary imminent frontal impact condition according to an embodiment of the present disclosure.
• The 5A and 5B illustrate flowcharts depicting step-by-step operation of the proposed system according to an embodiment of the present disclosure.
• 6 is a flowchart illustrating the proposed method for reducing impact on an ego vehicle according to an embodiment of the present disclosure.
• 7 illustrates an exemplary computer system in or with which embodiments of the present invention may be used in accordance with embodiments of the present disclosure.

Following is a detailed description of embodiments of the disclosure illustrated in the accompanying drawings. The embodiments are detailed enough to clearly communicate the disclosure. However, the level of detail offered is not intended to limit the expected variations of embodiments; on the contrary, the intent is to cover all modifications, equivalents, and alternatives that fall within the spirit and scope of the present disclosures as defined by the appended claims.

Embodiments discussed herein relate to the field of advanced driver assistance systems (ADAS). In particular, the present disclosure provides a system and method for reducing the effects of an impact on an ego vehicle.

Referring to FIG. 1, an exemplary network architecture of the proposed system 100 (referred to interchangeably herein as system 100) may be implemented in a vehicle (also referred to herein as ego vehicle) to reduce the effects of an impact on the ego vehicle.

According to an embodiment, the system 100 may include a monitoring unit 102 configured to identify the presence of an object within an area of interest (AoI) from the current position of the ego vehicle. In an exemplary embodiment, the monitoring unit 102 may include a plurality of sensors positioned at predefined positions on the ego vehicle and configured to detect the presence of an object within the AoI. In an exemplary embodiment, the monitoring unit 102 may be equipped with sensors including but not limited to proximity sensor, RADAR, camera and LiDAR.

According to one embodiment, the monitoring unit 102 may also analyze one or more parameters associated with the identified object, including but not limited to the size of the vehicle, relative speed, time of impact, impact zone, direction of approach, and object type.

According to one embodiment, the system 100 may include a controller 106 that may be in communication with the monitoring unit 102. The controller 106 may also be operatively coupled to a learning machine 104, wherein the learning machine 104 may be equipped with a CNN (Convolutional Neural Network) architecture and/or a RNN (Recurrent Neural Network) architecture.

In one embodiment, the controller 106, along with the learning engine 104, may be configured to estimate a crash based on the identified object and one or more parameters associated with the ego vehicle and the corresponding object. In one embodiment, the one or more parameters associated with the ego vehicle may already be present with the controller 106, or the controller 106 may obtain them immediately, where the one or more parameters associated with the ego vehicle may include size and type of the ego vehicle, real-time speed and acceleration of the ego vehicle, and the like. In one example, size and type of the ego vehicle may already be fed into the controller 106 from the time of manufacture, and real-time speed and acceleration of the ego vehicle may be obtained immediately from corresponding sensors coupled to the controller 106.

According to one embodiment, the system 100 may estimate that the collision between the ego vehicle and the object is imminent when the distance between the ego vehicle and the identified object is less than a safety distance. In another embodiment, the system 100 may estimate that the collision between the ego vehicle and the object is imminent when the relative speed between the ego vehicle and the identified object exceeds a threshold speed.

In one embodiment, when it is estimated that a crash is imminent, the system 100 may determine a best collision point to cause minimal damage to the ego vehicle. In one implementation, the system 100 may predict an optimal trajectory for the ego vehicle to reach the determined collision point by considering the one or more parameters associated with the ego vehicle and the object. Furthermore, the best collision point is predetermined based on passive simulation using real-world crash scenarios.

In another embodiment, based on the predicted trajectory, the system 100 may calculate the required lateral position shift and yaw rate associated with the ego vehicle to reduce the effects of the impact on the ego vehicle.

According to one embodiment, the controller 106 may be in communication with a steering assembly 110 of the ego vehicle to facilitate maneuvering of the ego vehicle according to the predicted trajectory. In a preferred embodiment, the controller 106 may be in communication with the steering assembly 110 via an actuator 108, wherein the actuator 108 is actuated when it is estimated that the crash is imminent. Furthermore, the actuator element 108, when actuated, may enable the controller 106 to maneuver the steering assembly 110 to reach the determined collision point.

In one embodiment, the learning engine 104 may be trained using a training and test data set related to the passive simulation performed using multiple real-world crash scenarios, wherein the output of the learning engine 104 is used as feedback to the system 100, and further wherein the system 100 determines the collision point, the required lateral position shift, and the yaw rate associated with the ego vehicle based on the output of the learning engine 104.

According to one embodiment, the controller 106 may be in communication with the monitoring unit 102, the learning machine 104, the actuator device 108 and the control arrangement 110 via a network 112. Furthermore, the network 112 may be a wireless network, a wired network or a combination thereof, which may be implemented as one of the various types of networks, such as intranet, local area network (LAN), wide area network (WAN), Internet and the like. Furthermore, the network 112 may be either a dedicated network or a shared network.

The shared network may represent an association of different types of networks that may use a variety of protocols, such as Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like.

In one embodiment, the controller 106 may be implemented using any one or a combination of hardware components and software components, such as a cloud, a server 114, a computer system, a computing device, a network device, and the like. Further, the controller 106 may interact with the monitoring unit 102, the learning engine 104, the actuator 108, and the steering assembly 110 via a website or application that may reside in the proposed system 100. In one implementation, the system 100 may be accessed via a website or application that may be configured with any operating system, including but not limited to Android™ _' iOS™, and the like.

Referring to FIG. 2, block diagram 200 illustrates example functional units of controller 106, which may include one or more processors 202. The one or more processors 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and/or any devices that manipulate data based on operating instructions. Among other capabilities, the processor(s) 202 are configured to fetch and execute computer-readable instructions stored in a memory 204 of controller 106. Memory 204 may store one or more computer-readable instructions or routines that may be retrieved and executed to create or share the data units over a network service. Memory 204 may include any non-transitory storage device, including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, and the like.

According to one embodiment, the controller 106 may also include one or more interfaces 206. The interface(s) 206 may include a variety of interfaces, for example, interfaces for data input and output devices referred to as I/O devices, storage devices, and the like. The interface(s) 206 may facilitate communication of the monitoring device 206 with various devices coupled to the controller 106. The interface(s) 206 may also provide a communication path for one or more components of the controller 106. Examples of such components include, but are not limited to, the processing engine(s) 208 and the database 210.

According to one embodiment, the processing engine(s) 208 may be implemented as a combination of hardware and programming (e.g., programmable instructions) to implement one or more functionalities of the processing engine(s) 208. In the examples described herein, such combinations of hardware and programming may be implemented in a variety of ways. For example, the programming for the processing engine(s) 208 may consist of executable processor instructions stored on a non-transitory machine-readable storage medium, and the hardware for the processing engine(s) 208 may include a processing resource (e.g., one or more processors) to execute such instructions.

In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) 208. In such examples, the controller 106 may include the machine-readable storage medium storing the instructions and the processing resource for executing the instructions, or the machine-readable storage medium may be separate but accessible to the system 100 and the processing resource. In other examples, the processing engine(s) 208 may be implemented by an electronic circuit. The database 210 may contain data that is either stored or generated as a result of functionality implemented by one of the components of the processing engine(s) 208. In one embodiment, the processing engine(s) 208 may include a crash estimation unit 212, a collision point determination unit 214, a simulation unit 216, and other units 218. Furthermore, the other unit(s) 218 may implement functionalities that complement applications/functions executed by the controller 106.

According to one embodiment, the crash estimation unit 212 may estimate a crash based on the object identified by the monitoring unit 102 and one or more parameters associated with the ego vehicle and the corresponding object. In one embodiment, the one or more parameters associated with the identified object and the ego vehicle include, but are not limited to, the distance between the ego vehicle and the identified object, the size of the vehicle, the relative speed, the time of impact, the impact zone, the direction of approach, and the object type.

According to one embodiment, the crash estimation unit 212 may consider the distance between the ego vehicle and the identified object among the one or more parameters, and accordingly, the crash estimation unit 212 may estimate that the collision between the ego vehicle and the object is imminent when the distance between the ego vehicle and the identified object is less than a safe distance.

In another embodiment, the crash estimation unit 212 may consider the relative speed between the ego vehicle and the identified object among the one or more parameters, and accordingly, the crash estimation unit 212 may estimate that the collision between the ego vehicle and the object is imminent when the relative speed between the ego vehicle and the identified object exceeds a threshold speed.

In another embodiment, the crash estimation unit 212 may take into account the relative speed and distance between the ego vehicle and the identified object, and further, the crash estimation unit 212 may estimate that the collision between the ego vehicle and the object is imminent when the relative speed between the ego vehicle and the identified object exceeds a threshold speed and the distance between the ego vehicle and the identified object is less than a safe distance.

In yet another embodiment, if the relative speed between the ego-vehicle and the identified object is below a threshold speed and/or the distance between the ego-vehicle and the identified object is greater than a safe distance, then the crash estimation unit 212 may estimate that the collision can be avoided.

According to an embodiment, when the crash estimation unit 212 estimates that a crash is imminent, the collision point determination unit 214 may determine a best collision point to cause minimal damage to the ego vehicle. In an embodiment, the collision point determination unit 214 may predict an optimal trajectory for the ego vehicle to reach the determined collision point by considering the one or more parameters associated with the ego vehicle and the object.

In another embodiment, the collision point determination unit 214 may calculate the required lateral position displacement and yaw rate associated with the ego vehicle based on the predicted trajectory.

According to an embodiment, the simulation unit 216 may facilitate the execution of a passive simulation that may be performed using real crash scenarios. Furthermore, the collision point determination unit 214 may predetermine the best collision point based on the passive simulation that is performed using real crash scenarios.

In one embodiment, the crash estimation unit 212, together with the other unit(s) 218, may facilitate maneuvering of the ego vehicle according to the predicted trajectory. In a preferred embodiment, the crash estimation unit 212 may actuate the actuator element 108, which may be in communication with the steering assembly 110, wherein the actuator element 108 is actuated upon estimation by the crash estimation unit 212 that the crash is imminent. Furthermore, the collision point determination unit 214, when actuated, may enable the actuator device 108 to facilitate maneuvering of the steering assembly 110 of the ego vehicle to reach the determined collision point.

Referring to FIG. 3, flowchart 300 illustrates training the proposed system 100 for imminent crash conditions using passive safety simulation. In one embodiment, real-world crash scenarios may be collected at block 302, such as from cases in accident research based on regulations or load case assessments. Furthermore, unavoidable crash scenarios may be used to perform passive safety simulations at block 304. In an exemplary embodiment, the passive safety simulations may be performed based on the structural crash algorithm of the system 100.

In one embodiment, data derived from the passive simulations may be applied to determine a best collision point to have minimal damage to the ego vehicle as well as the identified object, i.e. to arrive at decisions to achieve a win-win outcome. The data derived from the passive simulations may be fed into block 306 where driving algorithms are executed and sensor configuration based on the crash/accident based data is performed.

In another embodiment, post-crash data may be obtained as output from block 306, and this post-crash data may be fed as feedback to the learning engine 104, which includes various artificial intelligence (AI) and machine learning (ML) based algorithms. The learning engine 104 and the associated algorithms may be updated by training and testing on the post-crash data, and therefore the system 100 may be continuously improved.

In another embodiment, at block 308, the post-impact data may be used to maneuver the ego vehicle to achieve the best collision point to have minimal damage to the ego vehicle as well as the identified object, i.e., to have a win-win position for passengers inside the ego vehicle and other road users.

Therefore, the system 100 uses passive safety simulation data to improve programming/decision making for various unavoidable crash scenarios for autonomous vehicles, which can improve crash safety.

Referring to FIG. 4, an exemplary condition 400 relating to an imminent frontal crash may be observed. Here, the system 100 may determine various parameters such as the direction of approach, the impact zone - front left corner, front center, and front right corner, and may further determine the expected impact point in the event of an imminent frontal collision between the ego vehicle, e.g., the system car 410, and the potential crash object 420.

Referring to Figure 5A, flowchart 500 illustrates step-by-step operation of the proposed system 100. In one embodiment, at block 502, input may be obtained from a passive simulation, where data is generated from simulating real-world accident scenarios, such as cases in accident research based on regulations or load case assessments. Further, the input from the passive simulations may be used together with the input from the ego-vehicle coding to determine a best collision point to cause minimal damage to the ego-vehicle, say the car, at block 504.

In another embodiment, pre-checks for activation of the system 100 may be performed at block 516, e.g. checking the impact time in relation to the current situation and the object, the impact zone - front left corner, front center and front right corner - and checking if the electric power steering (EPAS) is in working state, the approach direction, ESP operating state, object type - car or truck. In an exemplary embodiment, it may include checking if the relative speed of the object, which may be, for example, more than 15 km/h, is . Furthermore, it may include checking if the time until impact of the object is less than 0.3 seconds and the acceleration ^{is less than 3 m/sec 2} . In addition, it may include checking the ESM operation mode, gear, speedometer speed (e.g. should be more than 15 km/h), cycling radius (e.g. should be more than 15 km/h), robustness level of the object and the like.

In one embodiment, data from block 504 and block 516 may be fed to block 506 where the required lateral position shift may be calculated. In another embodiment, trajectory planning may be performed at block 508 based on the calculated required Y shift. In another embodiment, based on the optimal trajectory, the yaw rate is controlled by the yaw rate controller at block 510 and another yaw rate request is transmitted to the yaw rate arbitrator at block 512 and another yaw rate is updated.

In one embodiment, at block 514, the actuator 108 may be actuated and further the controller 106 may control the maneuvering of the steering assembly 110 (EPAS 110).

Referring to FIG. 5B, as shown, a passive simulation associated with trajectory planning may be performed at 522 and a passive simulation associated with the yaw rate controller function may be performed at 524. In another embodiment, a passive simulation associated with the yaw rate arbitrator function may be performed at 526.

Referring to FIG. 6, the proposed method 600 for reducing the impact of an impact on an ego vehicle (also referred to herein as method 600) may include the step 602 of identifying the presence of an object within an area of interest (Aol) by a monitoring unit from the current position of the ego vehicle and estimating an impact accordingly.

In another embodiment, the method 600 may include the step 604 of determining, at a controller operatively coupled to a learning machine, a best collision point to cause minimal damage to the ego vehicle when a collision is believed to be imminent. Further, the method 600 may include the step 606 of predicting, at the controller, an optimal trajectory for the ego vehicle to reach the determined collision point considering one or more parameters associated with the ego vehicle and the object. In an exemplary embodiment, the one or more parameters may include the distance between the ego vehicle and the object, the relative speed, the time of impact, the impact zone, the direction of approach, and the object type.

In one implementation, the best collision point can be predetermined based on a passive simulation of real crash scenarios.

In another embodiment, the method 600 may include the step 608 of calculating, at the controller, the required lateral position shift and yaw rate associated with the ego vehicle based on the predicted trajectory to reduce the effects of the impact on the ego vehicle.

According to one embodiment, the method 600 may include the step of training the learning machine using a training and test dataset related to the passive simulation performed using multiple real crash scenarios, wherein the output of the learning machine may be used as feedback, and further the method 600 may include calculating the collision point based on the output, the required lateral position displacement, and the yaw rate associated with the ego vehicle.

In another embodiment, method 600 may include estimating imminent collision between the ego vehicle and the object when the distance between the ego vehicle and the identified object is less than a safe distance or the relative speed between the ego vehicle and the identified object exceeds a threshold speed.

Further, after estimating the impact, method 600 may include actuating an actuator operatively coupled to a steering assembly of the ego vehicle, wherein the actuator, when actuated, may facilitate the controller in maneuvering the steering assembly to reach the determined collision point.

Referring to Figure 7, block diagram 700 illustrates a computer system including an external storage device 710, a bus 720, main memory 730, read-only memory 740, a mass storage device 750, a communications port 760, and a processor 770. One of ordinary skill in the art will recognize that a computer system may include more than one processor and communications ports. Examples of processor 770 include, but are not limited to, one or more Intel® Itanium® or Itanium 2 processors, or AMD® Opteron® or Athlon MP processors®, Motorola processors®, FortiSOC system-on-a-chip processors™, or other future processors. Processor 770 may include various modules associated with embodiments of the present invention. The communications port 760 may be any RS-232 port for use with a modem-based dial-up connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber optic, a serial port, a parallel port, or other existing or future ports. The communications port 760 may be selected depending on a network, such as a local area network (LAN), a wide area network (WAN), or any network to which a computer system is connected.

In one embodiment, memory 730 may be random access memory (RAM) or any other dynamic storage device well known in the art. Read-only memory 740 may be one or more static storage devices, such as, but not limited to, a programmable read only memory (PROM) chip for storing static information, such as boot or BIOS instructions for processor 770. Mass storage 760 may be any current or future mass storage solution that may be used to store information and/or instructions. Example Mass Storage Solution Examples of storage devices include Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, such as with Universal Serial Bus (USB) and/or Firewire interfaces), such as those from Seagate (such as the Seagate Barracuda 7102 family) or Hitachi (such as the Hitachi Deskstar 7K1000), one or more optical disks, Redundant Array of Independent Disks (RAID) storage, such as an array of hard disks (such as SATA arrays), available from various vendors, including Dot Hill Systems Corp., LaCie, Nexsan Technologies, Inc., and Enhance Technology, Inc.

In one embodiment, bus 720 communicatively couples processor(s) 770 to the other memory, storage, and communication blocks. Bus 720 may be, for example, a peripheral component interconnect (PCI/PCI-X) bus, small computer system interface (SCSI) bus, USB, or the like for connecting expansion cards, drives, and other subsystems, as well as other buses, such as a front-side bus (FSB), that connects processor 770 to the software system.

In another embodiment, operator and management interfaces, such as a display, keyboard, and cursor control device, may also be coupled to bus 720 to support direct operator interaction with the computer system. Other operator and management interfaces may be provided via network connections connected via communications port 760. External storage device 710 may be any type of external hard drives, floppy disk drives, IOMEGA Zip Drives®, Compact Disc - Read Only Memory (CD-ROM), Compact Disc - Re-Writes (CD-RW), Digital Video Disk - Read Only Memory (DVD-ROM). The components described above are only intended to illustrate various possibilities. In no way should the exemplary computer system mentioned above limit the scope of the present disclosure.

While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the following claims. The invention is not limited to the described embodiments, versions, or examples, which are included to enable a person of ordinary skill in the art to make and use the invention when combined with information and knowledge available to one of ordinary skill in the art.

The present disclosure provides an accurate and efficient system and method that reduces the impact of impact on the host vehicle when impact is imminent.

The present disclosure provides a system and method in which the use of passive safety simulation data improves the utilization of the vehicle structure to absorb more energy and minimize repairability costs in the event of a collision.

The present disclosure provides a system and method that determines a best collision point so that the effects of the impact are reduced.

The present disclosure provides an intelligent and intelligent system and method that ensures minimal damage to the vehicle and the occupants inside.

QUOTES INCLUDED IN THE DESCRIPTION

This list of documents listed by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions.

Cited patent literature

• US 10836383 B2 [0003]
• KR 101465649 B1 [0004]
• US 20130030651 A1 [0005]

Claims (10)

A system (100) for reducing the impact of an impact on an ego vehicle, the system (100) comprising: a controller (106) operatively coupled to a learning machine (104), the controller (106) comprising one or more processors (202) coupled to a memory (204), the memory (204) storing one or more instructions executable by the one or more processors (202) to: identify, through a monitoring unit (102) in communication with the controller (106), the presence of an object within an area of interest (Aol) from the current position of the ego vehicle and estimate a crash accordingly; if an accident is believed to be imminent, determine a best collision point to minimize damage to the ego vehicle; predict, taking into account one or more parameters associated with the ego-vehicle and the object, an optimal trajectory for the ego-vehicle to reach the determined collision point; and based on the predicted trajectory, calculate the required lateral position shift and the yaw rate associated with the ego-vehicle to reduce the effects of the impact on the ego-vehicle; wherein the best collision point is predetermined based on a passive simulation performed using real crash scenarios. System (100) after Claim 1 wherein the learning machine (104) is trained using a training and test data set related to the passive simulation performed using a plurality of real-world crash scenarios, wherein the output of the learning machine (104) is used as feedback to the system (100), and wherein the system (100) calculates the collision point, the required lateral position displacement, and the yaw rate associated with the ego vehicle based on the output. System (100) after Claim 1 , wherein the one or more parameters include the distance between the ego vehicle and the object, the size of the vehicle, the relative speed, the time of impact, the impact zone, the direction of approach, and the object type. System (100) after Claim 3 , wherein the system (100) estimates that the collision between the ego vehicle and the object is imminent if the distance between the ego vehicle and the identified object is less than a safety distance or the relative speed between the ego vehicle and the identified object exceeds a threshold speed. System (100) after Claim 4 , wherein the controller (106), upon estimation of the impact, actuates an actuator (108) which is operatively coupled to a steering arrangement (110) of the ego vehicle, wherein the actuator (108), upon actuation of the controller (106), actuates the controller (106) to reach the determined collision point. A method (600) for reducing the impact of an impact on an ego vehicle, the method (600) comprising: identifying (602), by a monitoring unit, the presence of an object within an area of interest (Aol) from the current position of the ego vehicle and estimating a crash accordingly; determining (604), at a controller operatively coupled to a learning machine, a best collision point to cause minimal damage to the ego vehicle when a collision is believed to be imminent; predicting (606) at the controller an optimal trajectory for the ego vehicle to reach the determined collision point, taking into account one or more parameters associated with the ego vehicle and the object; and calculating (608) at the controller the required lateral position shift and yaw rate associated with the ego vehicle based on the predicted trajectory to reduce the impact of the impact on the ego vehicle; wherein the best collision point is predetermined based on a passive simulation performed using real crash scenarios. Procedure (600) according to Claim 6 wherein the method (600) comprises training the learning machine using a training and test data set related to the passive simulation performed using a plurality of real-world crash scenarios, using the output of the learning machine as feedback, and wherein the method (600) comprises calculating the collision point, the required lateral position displacement, and the yaw rate associated with the ego vehicle. Procedure (600) according to Claim 6 , where the one or more parameters specify the distance between between the ego vehicle and the object, relative speed, impact time, impact zone, approach direction, and object type. Procedure (600) according to Claim 8 , wherein the method (600) comprises estimating the imminent collision between the ego vehicle and the object when the distance between the ego vehicle and the identified object is less than a safety distance or the relative speed between the ego vehicle and the identified object exceeds a threshold speed. Procedure (600) according to Claim 9 wherein the method comprises, after estimating the impact, actuating an actuator operatively coupled to a steering assembly of the ego vehicle, the actuator, when actuated, enabling the controller to maneuver the steering assembly to reach the determined collision point.

Images