CN115203969A - Control method, device, equipment and storage medium for automatic driving simulation scene - Google Patents

Abstract

The disclosure provides a control method of an automatic driving simulation scene, and relates to the technical field of artificial intelligence, in particular to the technical field of automatic driving and the technical field of auxiliary driving. The specific implementation scheme is as follows: acquiring a state information set of a plurality of scene objects, wherein the state information set comprises a plurality of pieces of state information, the state information corresponds to switching conditions, and the switching conditions correspond to switching actions; generating an automatic driving simulation scene according to the state information set of the scene objects; and in response to determining that any scene object of the plurality of scene objects meets the switching condition, controlling any scene object to perform a switching action corresponding to the switching condition such that any scene object switches to a target state in the autopilot simulation scene, wherein the target state is indicated by state information corresponding to the switching condition. The disclosure also provides a control device, an electronic device and a storage medium for the automatic driving simulation scene.

Description

Control method, device, device and storage medium for automatic driving simulation scene

technical field

The present disclosure relates to the technical field of artificial intelligence, and in particular, to the technical field of automatic driving and the technical field of assisted driving. More specifically, the present disclosure provides a control method, device, electronic device and storage medium for an automatic driving simulation scene.

Background technique

With the development of artificial intelligence technology, the application scenarios of automatic driving and assisted driving are increasing. In simulation scenarios, the effectiveness or accuracy of autonomous driving modes can be verified.

SUMMARY OF THE INVENTION

The present disclosure provides a control method, apparatus, device, and storage medium for an automatic driving scenario.

According to an aspect of the present disclosure, there is provided a control method for an automatic driving simulation scene, the method includes: acquiring a state information set of a plurality of scene objects, wherein the state information set includes a plurality of state information, and the state information corresponds to a switching condition , the switching condition corresponds to the switching action; according to the state information set of the multiple scene objects, the automatic driving simulation scene is generated; and in response to determining that any scene object in the multiple scene objects satisfies the switching condition, the execution and switching of any scene object are controlled The switching action corresponding to the condition makes any scene object switch to the target state in the automatic driving simulation scene, wherein the target state is indicated by the state information corresponding to the switching condition.

According to another aspect of the present disclosure, there is provided a control device for an automatic driving simulation scene, the device comprising: an acquisition module configured to acquire a state information set of multiple scene objects, wherein the state information set includes a plurality of state information, The state information corresponds to the switching condition, and the switching condition corresponds to the switching action; the generating module is used to generate an automatic driving simulation scene according to the set of state information of the plurality of scene objects; and the control module is used to respond to determining the plurality of scene objects. Any scene object satisfies the switching condition, and controls any scene object to perform the switching action corresponding to the switching condition, so that any scene object switches to the target state in the automatic driving simulation scene, wherein the target state is the state corresponding to the switching condition. information indicated.

According to another aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor. The at least one processor executes to enable the at least one processor to perform the methods provided in accordance with the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a method provided in accordance with the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method provided in accordance with the present disclosure.

It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present disclosure. in:

1 is a schematic diagram of an exemplary system architecture of a control method and apparatus to which an automatic driving simulation scenario can be applied according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of a control method for an automatic driving simulation scenario according to an embodiment of the present disclosure;

3 is a schematic diagram of a control method for an automatic driving simulation scenario according to an embodiment of the present disclosure;

4A is a flowchart of controlling any scene object to perform a switching action corresponding to a switching condition according to an embodiment of the present disclosure;

4B is a schematic diagram of controlling any scene object to perform a switching action corresponding to a switching condition according to an embodiment of the present disclosure;

5A is a flowchart of controlling any scene object to perform a switching action corresponding to a switching condition according to another embodiment of the present disclosure;

5B is a schematic diagram of controlling any scene object to perform a switching action corresponding to a switching condition according to another embodiment of the present disclosure;

FIG. 6 is a block diagram of a control device of an automatic driving simulation scenario according to an embodiment of the present disclosure; and

FIG. 7 is a block diagram of an electronic device to which a control method of an automatic driving simulation scenario can be applied according to one embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

Autonomous driving simulation technology is a means of testing autonomous driving algorithms. The low cost and high test efficiency of autonomous driving simulation technology are crucial to the iterative development of autonomous driving algorithms.

For example, a simulation scenario can be established based on the drive test data. In this simulation scenario, the speed, position and shape of obstacles are determined. The scene where the road test vehicle is located can be reproduced. In this simulation scenario, the behavior of the obstacle is fixed, and the behavior of the obstacle can reflect the interaction between the obstacle and the test vehicle. In this simulation scenario, it is difficult for obstacles to respond reasonably according to the behavior changes of the autonomous vehicle, and a large number of interactive behaviors that are rarely or unreasonable in the real scene occur, resulting in errors in the test results.

For example, simulation scenarios can also be designed manually. Scenarios designed based on human experience can be used for specific target testing. In this simulation scenario, the behavior of obstacles is also fixed. When certain conditions are met, certain actions can be triggered. The expression of the simulation scene may be a parametric expression. The structure and behavior of this simulation scenario are relatively simple. In this simulation scenario, the behavior of obstacles is relatively simple and the diversity is poor, making it difficult to achieve other test objectives.

The construction and simulation of the scene are generally open, and there is no unified standard. The expressiveness and ease of use of the scene determine the effectiveness and efficiency of the simulation. The stronger the expressiveness and readability of the scene, the wider the scope of application of the simulation and the more accurate the evaluation.

In some embodiments, parameters such as trajectory can be independently designed for one obstacle without considering other obstacles. The scene thus established is relatively simple, and the complexity of the scene is low. When using this scenario for testing, the coverage of the test functions is low, and the test results will fluctuate with the changes of the autopilot controller of the vehicle under test.

In some embodiments, simulation scenarios may be constructed based on scenario scripts. The scheme of the scene script is more complicated, and it adopts a similar idea as the movie script, and comprehensively considers all objects such as obstacles and ground objects in the whole scene. Based on the scenario scenario, multiple scenario segments can be designed using the OpenScenario technology. However, editing the scene script requires the designer to have a deep understanding of the scene system, and the readability is relatively poor and the difficulty is high, which is not conducive to rapid application. In addition, in the simulation scene constructed based on the scene script, there are a large number of invalid scene fragments. A large number of scenes in the scene system cannot be expressed, and can only be generalized through certain parameters and selected from a large number of scenes, which is inefficient and wastes resources seriously.

FIG. 1 is a schematic diagram of an exemplary system architecture to which a simulation testing method and apparatus for an autonomous driving vehicle can be applied according to an embodiment of the present disclosure.

It should be noted that FIG. 1 is only an example of a system architecture to which the embodiments of the present disclosure can be applied, so as to help those skilled in the art to understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used for other A device, system, environment or scene.

As shown in FIG. 1 , the system architecture 100 according to this embodiment may include sensors 101 , 102 , and 103 , a network 120 , a server 130 , and a Road Side Unit (RSU) 140 . The network 120 is the medium used to provide the communication link between the sensors 101 , 102 , 103 and the server 130 . Network 120 may include various connection types, such as wired and/or wireless communication links, and the like.

The sensors 101, 102, 103 may interact with the server 130 through the network 120 to receive or send messages and the like.

The sensors 101 , 102 , 103 may be functional elements integrated on the vehicle 110 , such as infrared sensors, ultrasonic sensors, millimeter-wave radars, information collection devices, and the like. The sensors 101 , 102 , and 103 may be used to collect status data of perceived objects (eg, pedestrians, vehicles, obstacles, etc.) around the vehicle 110 and surrounding road data.

The vehicle 110 may communicate with the roadside unit 140, receive information from the roadside unit 140, or send information to the roadside unit.

The RSU 140 may be deployed on a signal light, for example, so as to adjust the duration or frequency of the signal light.

The server 130 may be disposed at a remote end capable of establishing communication with the vehicle-mounted terminal, and may be specifically implemented as a distributed server cluster composed of multiple servers, or may be implemented as a single server.

The server 130 may be a server that provides various services. For example, a map application, a data processing application, etc. may be installed on the server 130 . Taking the server 130 running the data processing application as an example: the status data and road data of obstacles transmitted from the sensors 101 , 102 and 103 are received through the network 120 . One or more of the status data of obstacles and road data can be used as the data to be processed. And process the data to be processed to obtain the target data.

It should be noted that, the control method of the automatic driving scene provided by the embodiment of the present disclosure may generally be executed by the server 130 . Correspondingly, the control apparatus for the automatic driving scene provided by the embodiment of the present disclosure may also be provided in the server 130 .

It will be appreciated that the numbers of sensors, networks and servers in FIG. 1 are merely illustrative. There can be any number of sensors, networks and servers depending on the implementation needs.

It should be noted that the sequence numbers of the respective operations in the following methods are only used as representations of the operations for the convenience of description, and should not be regarded as representing the execution order of the respective operations. The methods need not be performed in the exact order shown unless explicitly stated.

FIG. 2 is a flowchart of a control method for an automatic driving scenario according to an embodiment of the present disclosure.

As shown in FIG. 2, the method 200 may include operations S210 to S230.

In operation S210, state information sets of a plurality of scene objects are acquired.

In an embodiment of the present disclosure, the scene objects may include dynamic scene objects and static scene objects.

For example, dynamic scene objects may include obstacles and traffic indicating devices. For another example, the obstacles may be various objects on the road such as pedestrians, motor vehicles, and non-motor vehicles. As another example, the traffic indicating device may be a traffic light.

For example, static scene objects include lane lines and figures. For another example, the types of lane lines may be various types such as long solid lines and dashed lines. For another example, features may include buildings, fences, and the like.

In this embodiment of the present disclosure, the state information set includes a plurality of state information, the state information corresponds to a switching condition, and the switching condition corresponds to a switching action.

For example, the state information may include at least one of position information, speed information, and shape information. In an example, taking the scene object Obj_A as an example of a motor vehicle, one state information of the scene object Obj_A may be: in lane 1, moving at a speed of 60 km/h. The switching condition Con_A1 may be: in lane 2, moving at a speed of 60 km/h for 10 minutes. The switching action Act_A1 may be: changing lanes to lane 1 .

In operation S220, an automatic driving simulation scene is generated according to a set of state information of a plurality of scene objects.

For example, various simulation tools can be used to generate a scene in time and space according to the state information set of multiple scene objects to obtain an automatic driving simulation scene.

In operation S230, in response to determining that any scene object among the plurality of scene objects satisfies the switching condition, control any scene object to perform a switching action corresponding to the switching condition, so that any scene object is switched to the target state in the automatic driving simulation scene .

For example, the plurality of scene objects may include scene object Obj_A, scene object Obj_B, and so on.

In the embodiment of the present disclosure, the target state is indicated by the state information corresponding to the switching condition.

For example, after it is determined that the scene object Obj_A moves on the lane 2 at a speed of 60 km/h for 10 minutes, it may be determined that the scene object Obj_A satisfies the switching condition Con_A1. Next, the scene object Obj_A can be controlled to perform the switching action Act_A1, that is, the scene object Obj_A can be controlled to change lanes to lane 1, so that the scene object Obj_A moves on the lane 1 at a speed of 60 km/h. For another example, the target state may include target position information "lane 1" and target speed information "60 km/h".

Through the embodiments of the present disclosure, after the switching condition is satisfied, the scene object can be controlled to perform the switching action, so that the scene related to the scene object in the scene system can be effectively expressed, and the efficiency of the scene simulation is improved.

In some embodiments, the set of state information includes at least one of initial state information, control state information, specific state information, and end state information.

In the embodiment of the present disclosure, the initial state information is used to indicate the initial state of the scene object in the automatic driving simulation scene.

In the embodiment of the present disclosure, the control state information is used to indicate the control state of the scene object related to the simulation test target in the automatic driving simulation scene.

In the embodiment of the present disclosure, the specific state information is used to indicate the specific state of the scene object in the automatic driving simulation scene.

In the embodiment of the present disclosure, the end state information is used to indicate the end state of the scene object in the automatic driving simulation scene. A detailed description will be given below with reference to FIG. 3 .

FIG. 3 is a schematic diagram of a control method for an automatic driving simulation scenario according to an embodiment of the present disclosure.

As shown in FIG. 3 , the state information set includes initial state information, a plurality of control state information, preset state information and end state information of the scene object Obj_B.

For example, the initial state information of the scene object Obj_B may indicate the initial state 301 of the scene object Obj_B in the automatic driving simulation scene. The initial state 301 may be the default state of the scene object Obj_B. The initial state 301 may include initial position information and initial velocity information of the scene object Obj_B. The initial position information of the scene object Obj_B may indicate that the scene object Obj_B is in lane 1, and the initial speed information of the scene object Obj_B may indicate that the moving speed of the scene object Obj_B is 40 km/h.

For example, the control state information State_B1 may indicate a control state of the scene object Obj_B in the automatic driving simulation scene, and the control state may be: moving on the lane 1 at a speed of 60 km/h. The switching condition Con_B0 corresponding to the control state information State_B1 may be: driving in the lane 1 at 40 km/h for 30 seconds. The switching action Act_B1 3021 corresponding to the switching condition Con_B0 may be: acceleration to 60 km/h. In one example, after it is determined that the scene object Obj_B moves on the lane 1 at a speed of 40 km/h for 30 seconds, it may be determined that the scene object Obj_B satisfies the switching condition Con_B0. Next, the scene object Obj_B can be controlled to perform the switching action Act_B1 3021, that is, the scene object Obj_B can be controlled to accelerate to 60 km/h, so that the scene object Obj_B moves on the lane 1 at a speed of 60 km/h.

For another example, the control state information State_B2 may indicate a control state of the scene object Obj_B in the automatic driving simulation scene, and the control state may be: moving on the lane 2 at a speed of 60 km/h. The switching condition Con_B12 corresponding to the control state information State_B2 may be: the distance from other scene objects is less than or equal to 1 meter. The switching action Act_B2 3022 corresponding to the switching condition Con_B12 may be: changing lanes to lane 2 . In one example, after it is determined that the distance between the scene object Obj_B and, for example, the scene object A is less than or equal to 1 meter, it may be determined that the scene object Obj_B satisfies the switching condition Con_B12. Next, the scene object Obj_B can be controlled to perform the switching action Act_B2 3022, that is, the scene object Obj_B can be controlled to change lanes to lane 2, so that the scene object Obj_B moves on the lane 2 at a speed of 60 km/h.

For another example, the control state information State_B3 may indicate a control state of the scene object Obj_B in the automatic driving simulation scene, and the control state may be: moving on the lane 1 at a speed of 50 km/h. The switching condition Con_B13 corresponding to the control state information State_B3 may be: the travel time on the lane 1 is greater than or equal to 30 seconds. The switching action Act_B3 3023 corresponding to the switching condition Con_B13 may be: decelerate to 50 km/h. In one example, after it is determined that the time that the scene object Obj_B travels on the lane 1 is greater than or equal to 30 seconds, it may be determined that the scene object Obj_B satisfies the switching condition Con_B13. Next, the scene object Obj_B can be controlled to perform the switching action Act_B3 3023, that is, the scene object Obj_B can be controlled to decelerate to 50 km/h, so that the scene object Obj_B moves on the lane 1 at a speed of 50 km/h.

For another example, the control state information State_B4 may indicate a control state of the scene object Obj_B in the automatic driving simulation scene, and the control state may be: moving on the lane 1 at a speed of 70 km/h. The switching condition Con_B34 corresponding to the control state information State_B4 may be: there is no other scene object ahead. The switching action Act_B4 3024 corresponding to the switching condition Con_B34 may be: acceleration to 70 km/h. In one example, after it is determined that there is no other object in front of the scene object Obj_B, it may be determined that the scene object Obj_B satisfies the switching condition Con_B34. Next, the scene object Obj_B can be controlled to perform the switching action Act_B4 3024, that is, the scene object Obj_B can be controlled to accelerate to 70 km/h, so that the scene object Obj_B moves on the lane 1 at a speed of 70 km/h.

For another example, the specific state information of the scene object Obj_B may indicate the specific state 303 of the scene object in the automatic driving simulation scene. The specific state 303 may be: decelerating movement in a preset lane. There may be multiple switching conditions corresponding to the specific state 303 .

In an example, one switching condition among the multiple switching conditions may be: the scene object Obj_B conflicts with other scene objects. As described above, the plurality of scene objects may include dynamic scene objects and static scene objects. In this embodiment, lane 1 can be used as a static scene object. The state information of lane 1 can be assumed as follows: the speed of scene objects traveling on lane 1 should be less than or equal to 65 km/h. After the switching action Act_B4 3024 is executed, the speed of the scene object Obj_B is 70 km/h, which conflicts with the lane 1, and the scene object Obj_B can be controlled to change lanes to the preset lane and slow down to move, so that the scene object Obj_B is on the preset lane Slow down the movement.

In an example, one switching condition among the multiple switching conditions may be: the scene object Obj_B moves on the lane 1 at a speed of 70 km/h for 1 minute. After it is determined that the scene object Obj_B moves on the lane 1 at a speed of 70 km/h for 1 minute, it can be determined that the scene object Obj_B satisfies the switching condition. Next, the scene object Obj_B can be controlled to change lanes to the preset lane and decelerate, so that the scene object Obj_B decelerates and moves on the preset lane.

For another example, the end state information of the scene object Obj_B may indicate the end state 304 of the scene object in the automatic driving simulation scene. The end state 304 may be: stationary in the preset lane. The switching condition corresponding to the end state 304 may be: the moving speed on the preset lane is 0. The switching action corresponding to the switching condition may be: static. In one example, after it is determined that the moving speed of the scene object Obj_B on the preset lane is 0, the scene object Obj_B may be controlled to be stationary, so that the scene object Obj_B is in an end state. It can be understood that the preset lane can be other lanes than lane 1 and lane 2. It can be understood that the switching action "still" may correspond to turning off the engine (turning off) in a real scene.

Through the embodiments of the present disclosure, when determining whether a scene object satisfies the switching condition, the state information of other scene objects (such as the scene object Obj_A and lane 1) can be used as parameters, which strengthens the connection between the scene objects in the simulation scene and improves the It reduces the complex length of the scene and helps to expand the application scope of the simulation test.

In some embodiments, switching conditions may be represented by operators and associated parameters.

For example, the switching condition Con_B12 described above can be expressed as:

Distance＜=1m (Formula 1)

"<=" is an operator representing less than or equal to, and 1m is a parameter value related to the switching condition Con_B12. Distance is used to represent the distance between the scene object Obj_B and other scene objects.

For another example, the operators may also include: "&", "|", "!", ">", "<", "==", "<=", "()". "&" is the bitwise AND operator, "|" is the bitwise OR operator, "!" is the logical NOT operator, ">" is the greater than operator, "<" is the less than operator, and "==" is the Equal operator, "<=" is less than or equal operator, "()" is parenthesis operator.

For another example, the relevant parameters may include the speed of each scene object, the value corresponding to the signal displayed by the traffic light, the weather parameter (for example, humidity), the illumination parameter, and so on. The relevant parameters may also include map information and the like.

In some embodiments, in some implementations of operation S210 above, acquiring the state information sets of the multiple scene objects includes: acquiring the state information of the vehicle to be tested and the state information sets of the multiple scene objects.

In the embodiment of the present disclosure, the vehicle to be tested moves in the automatic driving simulation scene based on the automatic driving mode.

For example, the state information of the vehicle to be tested may include information of the initial state of the vehicle to be tested and information of the end state of the vehicle to be tested. The initial state information of the vehicle to be tested may include initial speed information, initial acceleration information, and initial position information of the vehicle to be tested, and the like. The end state information of the vehicle to be tested may include information of the end position of the vehicle to be tested, and the like.

For another example, the vehicle to be tested may be the vehicle 110 described above.

For another example, the vehicle to be tested may also be referred to as the host vehicle.

It can be understood that each switching condition described above is related to the state of the scene object. In the embodiment of the present disclosure, the switching condition may also be related to the state of the vehicle to be tested.

In some embodiments, the switching conditions may further include: time switching conditions, distance switching conditions, speed switching conditions, direction switching conditions, weather switching conditions, traffic signal switching conditions, forward state switching conditions, and the like.

For example, the time switching conditions may include scene time switching conditions. After the scene is generated, after the preset time period has elapsed, it can be determined that the relevant scene object satisfies the scene time switching condition.

For example, the distance switching condition may include the host vehicle distance switching condition. After determining that the distance between the relevant scene object and the vehicle to be tested is the preset distance value, it can be determined that the relevant scene object satisfies the host vehicle distance switching condition.

For example, the speed switching conditions may include host vehicle speed switching conditions. After determining that the speed of the vehicle to be tested is the preset speed value, it can be determined that the relevant scene object satisfies the host vehicle speed switching condition.

For example, the direction switching conditions may include host vehicle turn signal switching conditions. After it is determined that the turn signal of the vehicle to be tested is turned on, it can be determined that the relevant scene object satisfies the switching condition of the turn signal of the host vehicle.

For example, for the weather switching condition, in the case that the weather in the scene is determined to be a preset weather (eg, cloudy), it may be determined that the relevant scene object satisfies the weather switching condition.

For example, for the traffic signal switching condition, after it is determined that the signal displayed by the traffic signal light is the preset signal, it is determined that the relevant scene object satisfies the traffic signal switching condition.

For example, forward state switching conditions may include forward state active switching conditions and forward state passive switching conditions. In one example, after it is determined that the scene object is in a preset state (eg, the speed is 50 km/h) and the signal displayed by the traffic light is the preset signal, it may be determined that the scene object satisfies the forward state passive switching condition. In another example, after it is determined that the scene object ends a certain switching action (for example, the end of a lane change), it can be determined that the scene object satisfies the forward state active switching condition.

In some embodiments, a switching action may describe a basic behavioral action of a scene object.

In this embodiment of the present disclosure, the switching action may be the same action as the scene object itself, or may be an interaction action between multiple scene objects.

In the embodiment of the present disclosure, the switching action may correspond to a parameterized model.

In an embodiment of the present disclosure, the switching action may include standing still, following a track, moving along a lane, changing lanes, following a vehicle, switching weather, switching signal lights, and the like.

For example, the weather in the scene can be used as a scene object, and the scene object can be controlled to perform a switching action from cloudy to rainy.

For example, a traffic light can be used as a scene object, and the scene object can be controlled to perform switching actions such as a red light changing to a green light.

In some embodiments, in some implementations of operation S220 above, generating the automatic driving simulation scene according to the state information sets of the plurality of scene objects includes: generating an initial automatic driving simulation according to the state information sets of the plurality of scene objects scene; and generating an automatic driving simulation scene according to the state information of the vehicle to be tested and the initial automatic driving simulation scene.

For example, in an autonomous driving simulation scenario, the vehicle to be tested moves from the initial position to the end position according to the set initial speed and initial acceleration. During the moving process, the automatic driving controller of the vehicle to be tested can adjust the speed, acceleration and position of the vehicle to be tested according to information such as the position of the scene objects.

In some embodiments, the method 200 may further include: determining whether the scene object satisfies the switching condition according to the state information of the vehicle to be tested and the state information of the plurality of scene objects.

In the embodiment of the present disclosure, whether the scene object satisfies the switching condition may be determined by using the trigger of the state machine.

For example, triggers can read the status of scene objects (such as the position, speed, acceleration, shape, etc. of obstacles) and scene environment information (such as lanes, intersections, crosswalks, etc.) in real time. Then, according to the read state and scene environment information, it is determined whether the scene object satisfies the switching condition.

In some embodiments, in some implementations of operation S230, controlling any scene object to perform a switching action corresponding to the switching condition includes: determining target trajectory information of any scene object according to state information corresponding to the switching condition; and In the automatic driving simulation scene, any scene object is controlled to move according to the target trajectory indicated by the target trajectory information. The detailed description will be given below in conjunction with FIG. 4A and FIG. 4B .

4A is a flowchart of controlling any scene object to perform a switching action corresponding to a switching condition according to an embodiment of the present disclosure.

As shown in FIG. 4A , the scene object can be controlled to perform the switching action corresponding to the switching condition, so that any scene object is switched to the target state. A detailed description will be given below in conjunction with operations S431 to S434.

In operation S431, the scene time is determined.

For example, the state of the scene object may be determined according to a preset time interval, so as to determine whether the scene object satisfies the switching condition. In one example, the scene object Obj_C may be a motor vehicle. One state information of the scene object Obj_C may be: moving on lane 2. The switching condition corresponding to the state information pair may be: the time t required for the scene object Obj_C to change lanes is less than the collision time TTC between the scene object Obj_C and the vehicle to be tested. The switching action corresponding to the switching condition may be: lane change.

In operation S432, the first forward state of the scene object is determined.

For example, the velocity and position of the scene object Obj_C may be determined as the first forward state. According to the first forward state, it is determined whether the scene object Obj_C satisfies the switching condition. In one example, the first forward state of the scene object Obj_C includes: the scene object Obj_C is moving at a speed V ₂ , and the scene object Obj_C is located between lane 1 and lane 2 . Furthermore, the vehicle to be tested is moving on lane ₂ at speed V1. The lane line between lane 1 and lane 2 is dashed.

In operation S433, the scene object is controlled to perform a switching action corresponding to the switching condition.

For example, if it is determined that the time t required for the scene object Obj_C to change lanes from lane 1 to lane 2 is less than the collision time TTC between the scene object Obj_C and the vehicle to be tested, the scene object Obj_C can be controlled to change lanes to lane 2. In one example, the target trajectory of changing lanes to lane 2 may be determined according to the position and speed of the scene object Obj_C. Next, the scene object Obj_C can be controlled to move according to the target trajectory.

In operation S434, the second forward state of the scene object is determined.

For example, the second forward state of the scene object may be determined after the lane change action is completed. In one example, the second forward state of the scene object Obj_C includes: the scene object Obj_C is moving at a speed V ₂ , and the scene object Obj_C is located in lane 2 .

Further detailed description will be given below with reference to FIG. 4B .

4B is a schematic diagram of controlling any scene object to perform a switching action corresponding to a switching condition according to an embodiment of the present disclosure.

As shown in FIG. 4B , the state of the scene object may be determined according to preset time intervals, so as to determine whether the scene object satisfies the switching condition. In one example, scene object 410 may be a motor vehicle. One state information for scene object 410 may be: moving on lane 2 440 . The switching condition corresponding to the state information pair may be: the time t required for the scene object 410 to change lanes is less than the collision time TTC between the scene object 410 and the vehicle to be tested 420 . The switching action corresponding to the switching condition may be: lane change. It can be understood that the scene object 410 may be the scene object Obj_C described above.

As shown in FIG. 4B, the vehicle under test 420 is moving at _a speed V1. The lane line 434 between lane 1 430 and lane 2 440 may be a dashed line. Vehicle 410 under test is moving on lane 2 440 . Lane 1 430 has a width of X ₀ .

Scene object 410 is moving at velocity V ₂ , and scene object 410 is located between lane 1 430 and lane 2 440 . The distance between the right edge of the scene object 410 and the lane line 434 is offset.

According to the position and speed of the scene object 410 and the position and speed of the vehicle under test 420, it can be determined that the time t required for the scene object 410 to change from lane 1 430 to lane 2 440 is less than the time t between the scene object 410 and the vehicle under test 420 Time to Collision TTC. Thereby, it can be determined that the scene object 410 satisfies the switching condition. The scene object 410 can be controlled to change lanes to lane 2 440 . In one example, the target trajectory 412 for lane change to lane 2 440 may be determined based on the position and velocity of the scene object 410 . Next, the scene object 410 can be controlled to move according to the target trajectory 412 .

In other embodiments, in some implementations of operation S230, controlling any scene object to perform a switching action corresponding to the switching condition includes: determining, according to state information corresponding to the switching condition, target trajectory information of any scene object and target speed information; and in the automatic driving simulation scene, control any scene object to move according to the target trajectory indicated by the trajectory information and the speed indicated by the target speed information.

For example, as shown in FIG. 4B , after it is determined that the scene object 410 satisfies the switching condition, the scene object 410 may be controlled to change lanes to lane 2 440 . In another example, the target trajectory 412 and target speed for lane change to lane 2 440 may be determined based on the position and speed of the scene object 410 . Next, the scene object 40 can be controlled to move according to the target trajectory 412 and the target speed.

It can be understood that the scene objects shown in FIG. 4A and FIG. 4B are obstacles, and in the embodiment of the present disclosure, the scene objects are not limited thereto, and detailed description will be given below with reference to FIG. 5A and FIG. 5B .

5A is a flowchart of controlling any scene object to perform a switching action corresponding to a switching condition according to another embodiment of the present disclosure.

As shown in FIG. 5A , the scene object can be controlled to perform the switching action corresponding to the switching condition, so that any scene object is switched to the target state. A detailed description will be made below in conjunction with operations S531' to S534'.

In operation S531', the scene time is determined.

For example, the state of the scene object may be determined according to a preset time interval, so as to determine whether the scene object satisfies the switching condition. In one example, the scene object Obj_D may be a traffic light. The state information of the scene object Obj_D may be: showing a preset traffic signal. The switching condition corresponding to the state information pair may be: the longitudinal distance between the vehicle to be tested and the lane stop line of the lane where it is located is a preset distance value d. The switching action corresponding to the switching condition may be: stop showing the traffic signal cyclically and show a preset traffic signal (eg, showing a yellow signal light).

In operation S532', the first forward state of the scene object is determined.

For example, shape information of the scene object Obj_D may be determined as the first forward state. According to the first forward state, it is determined whether the scene object Obj_D satisfies the switching condition. It can be understood that the shape information includes the color currently displayed by the scene object. In one example, the first forward state of the scene object Obj_D includes: cycling through different traffic signals. Furthermore, the vehicle to be tested is moving on lane ₃ at speed V1. The distance between the vehicle to be tested and the lane stop line of lane 3 is a preset distance value d.

In operation S533', the scene object is controlled to perform a switching action corresponding to the switching condition.

For example, after determining that the distance between the vehicle to be tested and the lane stop line of lane 3 is the preset distance value d, the scene object Obj_D can be controlled to stop cyclically displaying traffic signals and display the preset traffic signals.

In operation S534', the second forward state of the scene object is determined.

For example, the second forward state of the scene object may be determined after the act of presenting the preset traffic signal is completed. In one example, the second forward state of the scene object Obj_D includes: the scene object Obj_D shows a designated traffic signal (eg, showing a red signal light) after the preset traffic signal. Next, the scene object Obj_D can return to a state where different traffic signals are displayed in a loop.

Further detailed description will be given below in conjunction with FIG. 5B .

5B is a schematic diagram of controlling any scene object to perform a switching action corresponding to a switching condition according to another embodiment of the present disclosure.

As shown in FIG. 5B , the state of the scene object 560 may be determined according to preset time intervals, so as to determine whether the scene object 560 satisfies the switching condition. In one example, scene object 560 may be a traffic light. The state information of the scene object 560 may be: showing a preset traffic signal. The switching condition corresponding to the state information pair may be: the longitudinal distance between the vehicle to be tested and the lane stop line of the lane where it is located is a preset distance value d. The switching action corresponding to the switching condition may be: stop showing the traffic signal cyclically and show a preset traffic signal (eg, showing a yellow signal light). It can be understood that the scene object 560 may be the scene object Obj_D described above.

As shown in FIG. 5B , the vehicle 520 under test is moving on lane 3 550 at speed V ₁ . The distance between the vehicle to be tested 520 and the lane stop line 551 of the lane 3550 is a preset distance value d.

After determining that the distance between the vehicle to be tested 520 and the lane stop line 551 of lane 3 550 is the preset distance value d, the scene object 560 may be controlled to display a preset traffic signal.

After completing the act of presenting the preset traffic signal, the second forward state of the scene object 560 may be determined. At this time, the scene object 560 may present a designated traffic signal (eg, a red signal light) after the preset traffic signal. Next, the scene object 560 may return to a state in which the different traffic signals are cycled through.

FIG. 6 is a block diagram of a control device of an automatic driving simulation scenario according to an embodiment of the present disclosure.

As shown in FIG. 6 , the apparatus 600 may include an acquisition module 610 , a generation module 620 and a control module 630 .

The obtaining module 610 is configured to obtain state information sets of multiple scene objects. For example, the state information set includes a plurality of state information, the state information corresponds to the switching condition, and the switching condition corresponds to the switching action.

The generating module 620 is configured to generate an automatic driving simulation scene according to a set of state information of multiple scene objects.

The control module 630 is configured to control any scene object to perform a switching action corresponding to the switching condition in response to determining that any scene object in the plurality of scene objects satisfies the switching condition, so that any scene object switches to the automatic driving simulation scene. target state. For example, the target state is indicated by the state information corresponding to the switching condition.

In some embodiments, the state information set includes at least one of initial state information, control state information, specific state information and end state information; the initial state information is used to indicate the initial state of the scene object in the automatic driving simulation scene; the control state The information is used to indicate the control state of the scene object related to the simulation test target in the automatic driving simulation scene; the specific state information is used to indicate the specific state of the scene object in the automatic driving simulation scene; the end state information is used to indicate that the scene object is in the automatic driving simulation scene. The end state in the simulation scene.

In some embodiments, the acquiring module includes: an acquiring unit, configured to acquire state information of the vehicle to be tested and state information sets of multiple scene objects.

In some embodiments, the generation module includes: a first generation unit for generating an initial automatic driving simulation scene according to a set of state information of a plurality of scene objects; and a second generation unit for generating an initial automatic driving simulation scene according to the state information of the vehicle to be tested and The initial automatic driving simulation scenario generates an automatic driving simulation scenario.

In some implementations, the apparatus 600 further includes: a determination module, configured to determine whether the scene object satisfies the switching condition according to the state information of the vehicle to be tested and the state information of the plurality of scene objects.

In some embodiments, the control module includes: a first determination unit for determining target trajectory information of any scene object according to state information corresponding to the switching condition; and a first control unit for in the automatic driving simulation scene , control any scene object to move according to the target trajectory indicated by the target trajectory information.

In some embodiments, the control module includes: a second determination unit, configured to determine target trajectory information and target speed information of any scene object according to state information corresponding to the switching condition; and a second control unit, configured to automatically In the driving simulation scene, any scene object is controlled to move according to the target trajectory indicated by the trajectory information and the speed indicated by the target speed information.

In some embodiments, the state information includes at least one of position information, velocity information, acceleration information, and shape information.

In some embodiments, the scene objects include dynamic scene objects and static scene objects, the dynamic scene objects include obstacles and traffic indicating devices, and the static scene objects include lane lines and features.

In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved are all in compliance with relevant laws and regulations, and do not violate public order and good customs.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

FIG. 7 shows a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 7 , the device 700 includes a computing unit 701 that can be executed according to a computer program stored in a read only memory (ROM) 702 or loaded into a random access memory (RAM) 703 from a storage unit 708 Various appropriate actions and handling. In the RAM 703, various programs and data necessary for the operation of the device 700 can also be stored. The computing unit 701 , the ROM 702 , and the RAM 703 are connected to each other through a bus 704 . An input/output (I/O) interface 705 is also connected to bus 704 .

Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706, such as a keyboard, mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc. ; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 709 allows the device 700 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Computing unit 701 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of computing units 701 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 executes the various methods and processes described above, such as the control method of the automatic driving simulation scene. For example, in some embodiments, the method of controlling an autonomous driving simulation scenario may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708 . In some embodiments, part or all of the computer program may be loaded and/or installed on device 700 via ROM 702 and/or communication unit 709 . When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the control method of the automatic driving simulation scenario described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the control method of the automated driving simulation scenario by any other suitable means (eg, by means of firmware).

Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), complex programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) display or an LCD (liquid crystal display)) for displaying information to the user ; and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, no limitation is imposed herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure should be included within the protection scope of the present disclosure.

Claims (21)

1. A control method for an automatic driving simulation scenario, comprising: acquiring a state information set of multiple scene objects, wherein the state information set includes a plurality of state information, the state information corresponds to a switching condition, and the switching condition corresponds to a switching action; generating an automatic driving simulation scene according to the state information set of the plurality of scene objects; and In response to determining that any scene object in the plurality of scene objects satisfies the switching condition, control the any scene object to perform the switching action corresponding to the switching condition, so that the any scene object is in the switch to a target state in the automatic driving simulation scenario, wherein the target state is indicated by the state information corresponding to the switching condition. 2. The method of claim 1, wherein the state information set comprises at least one of initial state information, control state information, specific state information, and end state information; The initial state information is used to indicate the initial state of the scene object in the automatic driving simulation scene; The control state information is used to indicate the control state of the scene object related to the simulation test target in the automatic driving simulation scene; The specific state information is used to indicate the specific state of the scene object in the automatic driving simulation scene; The end state information is used to indicate the end state of the scene object in the automatic driving simulation scene. 3. The method according to claim 1, wherein the acquiring the state information sets of the plurality of scene objects comprises: Acquire state information of the vehicle to be tested and a set of state information of the multiple scene objects. 4. The method according to claim 3, wherein the generating an automatic driving simulation scene according to the state information sets of the plurality of scene objects comprises: generating an initial automatic driving simulation scene according to the state information set of the plurality of scene objects; and The automatic driving simulation scene is generated according to the state information of the vehicle to be tested and the initial automatic driving simulation scene. 5. The method of claim 3, further comprising: According to the state information of the vehicle to be tested and the state information of a plurality of the scene objects, it is determined whether the scene objects satisfy the switching condition. 6. The method according to claim 1, wherein the controlling any one of the scene objects to perform the switching action corresponding to the switching condition comprises: determining target trajectory information of any of the scene objects according to the state information corresponding to the switching condition; and In the automatic driving simulation scene, any scene object is controlled to move according to the target trajectory indicated by the target trajectory information. 7. The method according to claim 1, wherein the controlling the any scene object to perform the switching action corresponding to the switching condition comprises: determining target trajectory information and target speed information of any one of the scene objects according to the state information corresponding to the switching condition; and In the automatic driving simulation scene, any scene object is controlled to move according to the target trajectory indicated by the trajectory information and the speed indicated by the target speed information. 8. The method of claim 1, wherein the state information includes at least one of position information, velocity information, acceleration information, and shape information. 9. The method of claim 1, wherein the scene objects include dynamic scene objects including obstacles and traffic indicating devices and static scene objects, the static scene objects including lane lines and features. 10. A control device for an automatic driving simulation scene, comprising: an acquisition module, configured to acquire a state information set of a plurality of scene objects, wherein the state information set includes a plurality of state information, the state information corresponds to a switching condition, and the switching condition corresponds to a switching action; a generation module, configured to generate an automatic driving simulation scene according to the state information set of the plurality of scene objects; and A control module, configured to, in response to determining that any scene object among the plurality of scene objects satisfies the switching condition, control the any scene object to perform the switching action corresponding to the switching condition, so that any one of the scene objects satisfies the switching condition. A scene object switches to a target state in the automatic driving simulation scene, wherein the target state is indicated by the state information corresponding to the switching condition. 11. The apparatus of claim 10, wherein the state information set includes at least one of initial state information, control state information, specific state information, and end state information; The initial state information is used to indicate the initial state of the scene object in the automatic driving simulation scene; The control state information is used to indicate the control state of the scene object related to the simulation test target in the automatic driving simulation scene; The specific state information is used to indicate the specific state of the scene object in the automatic driving simulation scene; The end state information is used to indicate the end state of the scene object in the automatic driving simulation scene. 12. The apparatus of claim 10, wherein the obtaining module comprises: An acquiring unit, configured to acquire state information of the vehicle to be tested and state information sets of the plurality of scene objects. 13. The apparatus of claim 12, wherein the generating module comprises: a first generating unit, configured to generate an initial automatic driving simulation scene according to the state information set of the plurality of scene objects; and A second generating unit, configured to generate the automatic driving simulation scene according to the state information of the vehicle to be tested and the initial automatic driving simulation scene. 14. The apparatus of claim 12, further comprising: A determination module, configured to determine whether the scene object satisfies the switching condition according to the state information of the vehicle to be tested and the state information of a plurality of the scene objects. 15. The apparatus of claim 10, wherein the control module comprises: a first determining unit, configured to determine target trajectory information of any scene object according to the state information corresponding to the switching condition; and A first control unit, configured to control any scene object to move according to the target trajectory indicated by the target trajectory information in the automatic driving simulation scene. 16. The apparatus of claim 10, wherein the control module comprises: a second determining unit, configured to determine target trajectory information and target speed information of any scene object according to the state information corresponding to the switching condition; and The second control unit is configured to, in the automatic driving simulation scene, control any of the scene objects to move according to the target trajectory indicated by the trajectory information and the speed indicated by the target speed information. 17. The apparatus of claim 10, wherein the state information includes at least one of position information, velocity information, acceleration information, and shape information. 18. The apparatus of claim 10, wherein the scene objects include dynamic scene objects and static scene objects, the dynamic scene objects include obstacles and traffic indicating devices, and the static scene objects include lane lines and features. 19. An electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any one of claims 1 to 9 Methods. 20. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1 to 9. 21. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 9.

Images