Autonomous vehicle simulation testing method, device, equipment and readable storage medium

Abstract

A kind of automatic driving vehicle simulation test method, device and equipment and readable storage medium, automatic driving vehicle simulation test method includes: in simulation scene, when detecting the absolute value of the difference between the remaining time length of the automatic driving vehicle to reach the preset collision point and the remaining time length of the vulnerable traffic participant to reach the preset collision point is less than the preset error time length, control vulnerable traffic participant to slow down and stop;If it is detected that the automatic driving vehicle slows down and stops, the subsequent state of the automatic driving vehicle is monitored;If it is monitored that the automatic driving vehicle starts, the vulnerable traffic participant is also controlled to start;If it is monitored that the automatic driving vehicle keeps stopping, the vulnerable traffic participant is also controlled to keep stopping.The present application is simulated by the game psychology and behavior action of vulnerable traffic participant in simulation scene, and the performance of automatic driving vehicle and vulnerable traffic participant under game can be more accurately evaluated.

Description

Technical Field

[0001] This application relates to the field of vehicle simulation testing technology, and in particular to an autonomous vehicle simulation testing method, apparatus, equipment, and readable storage medium. Background Technology

[0002] Currently, simulation tests for autonomous driving typically assume that vulnerable road users, such as pedestrians, bicycles, and electric vehicles, are traveling at a constant speed. However, this does not reflect real-world scenarios. In reality, there is a game between vulnerable road users and vehicles, and this game can lead to traffic accidents. Therefore, current simulation tests for scenarios involving the game between autonomous vehicles and vulnerable road users are inaccurate. Summary of the Invention

[0003] This application provides a method, apparatus, device, and readable storage medium for simulating autonomous vehicle testing, aiming to solve the technical problem of inaccurate simulation testing in scenarios involving autonomous vehicles and vulnerable traffic participants.

[0004] In a first aspect, embodiments of this application provide an autonomous vehicle simulation testing method, the autonomous vehicle simulation testing method comprising:

[0005] In the simulation scenario, when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable road user to reach the preset collision point is less than the preset error time, the vulnerable road user is controlled to decelerate and stop.

[0006] If the autonomous vehicle is detected to slow down and stop, then monitor the subsequent state of the autonomous vehicle.

[0007] If an autonomous vehicle is detected to be activated, then controls for vulnerable road users will also be activated.

[0008] If the autonomous vehicle is detected to remain stationary, then vulnerable road users should also be controlled to remain stationary.

[0009] Optionally, in the simulation scenario, when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable road user to reach the preset collision point is less than a preset error time, controlling the vulnerable road user to decelerate and stop includes:

[0010] In the simulation scenario, an autonomous vehicle is set to travel towards a preset collision point at a preset initial speed. When the remaining time for the autonomous vehicle to travel to the preset collision point at a preset initial speed is detected as a preset time, the vulnerable traffic participant is controlled to start moving towards the preset collision point from the initial position. The preset time is the time for the vulnerable traffic participant to move from the initial position to the preset collision point.

[0011] When the vulnerable road user moves to the preset judgment position, calculate the first remaining time for the autonomous vehicle to reach the preset collision point at a preset initial speed and the second remaining time for the vulnerable road user to reach the preset collision point.

[0012] If the absolute value of the difference between the first remaining time and the second remaining time is less than the preset error time, then the vulnerable traffic participants will be controlled to slow down and stop to the preset pause position.

[0013] Optionally, the process of a vulnerable road user moving from the initial position to the preset collision point includes acceleration, constant speed and deceleration phases, with the preset judgment position located during the constant speed phase of the vulnerable road user.

[0014] Optionally, controlling a vulnerable traffic participant to move from an initial position toward a preset collision point includes:

[0015] The system controls vulnerable road users to begin climbing over a barrier from an initial position located outside the barrier and proceed toward a preset collision point. The preset duration includes the time required to climb over the barrier, and the outside of the barrier refers to the outer side of the barrier relative to the autonomous vehicle.

[0016] Optionally, the preset judgment position is the position of the railing.

[0017] Optionally, the autonomous vehicle simulation testing method further includes:

[0018] Record the distance between the autonomous vehicle and vulnerable road users during the simulation test, as well as whether the vehicle collides with vulnerable road users, in order to evaluate the simulation test results of the autonomous vehicle.

[0019] Optionally, after controlling the vulnerable road user to decelerate and stop when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable road user to reach the preset collision point is less than a preset error time, the following steps are taken:

[0020] If the autonomous vehicle is detected to have failed to slow down and stop, the system will control vulnerable road users to continue moving toward the pre-set collision point.

[0021] Secondly, embodiments of this application provide an autonomous vehicle simulation testing device, the autonomous vehicle simulation testing device comprising:

[0022] The deceleration and stop module is used to control the vulnerable traffic participant to decelerate and stop when the absolute value of the difference between the remaining time of the autonomous vehicle to reach the preset collision point and the remaining time of the vulnerable traffic participant to reach the preset collision point is less than a preset error time in a simulation scenario.

[0023] The status monitoring module is used to monitor the subsequent status of the autonomous vehicle if it is detected that the autonomous vehicle has slowed down and stopped.

[0024] The activation module is used to control vulnerable road users to also activate if the activation of an autonomous vehicle is detected.

[0025] The stop-and-hold module is used to control vulnerable road users to also remain stationary if the autonomous vehicle is detected to remain stationary.

[0026] Thirdly, this application provides an autonomous vehicle simulation test device, which includes a processor, a memory, and an autonomous vehicle simulation test program stored in the memory and executable by the processor. When the autonomous vehicle simulation test program is executed by the processor, it implements the steps of the autonomous vehicle simulation test method described above.

[0027] Fourthly, embodiments of this application provide a readable storage medium storing an autonomous vehicle simulation test program, wherein when the autonomous vehicle simulation test program is executed by a processor, it implements the steps of the autonomous vehicle simulation test method as described above.

[0028] The beneficial effects of the technical solutions provided in this application include:

[0029] In this embodiment of the application, under the simulation scenario, when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable traffic participant to reach the preset collision point is less than a preset error time, the vulnerable traffic participant is controlled to decelerate and stop; if the autonomous vehicle is detected to decelerate and stop, the subsequent state of the autonomous vehicle is monitored; if the autonomous vehicle is detected to start, the vulnerable traffic participant is controlled to start as well; if the autonomous vehicle is detected to remain stopped, the vulnerable traffic participant is controlled to remain stopped as well. This application's embodiments demonstrate that, in a simulation scenario, an autonomous vehicle equipped with an autonomous or assisted driving system controls the vehicle autonomously using its algorithm. Simulation tests are conducted to observe and evaluate the performance of the autonomous vehicle in a game scenario involving vulnerable road users. When the simulation system detects an impending collision between a vulnerable road user and the autonomous vehicle, it controls the vulnerable road user to decelerate and stop. If the autonomous vehicle decelerates and stops, the system monitors its subsequent behavior and controls the vulnerable road user to perform corresponding actions based on this behavior. This realistically simulates the psychological and behavioral actions of vulnerable road users. Compared to current autonomous driving simulation tests that simply set vulnerable road users to uniform motion, this application, by realistically simulating the psychological and behavioral actions of vulnerable road users, can provide a more accurate evaluation of the performance of the autonomous vehicle in a game scenario involving vulnerable road users. Attached Figure Description

[0030] Figure 1 This is a flowchart illustrating an embodiment of the autonomous vehicle simulation testing method of this application;

[0031] Figure 2 For this application Figure 1 A detailed flowchart of step S10;

[0032] Figure 3 This is a schematic diagram of a simulation scenario for an embodiment of the autonomous vehicle simulation testing method of this application;

[0033] Figure 4 This is a functional module diagram of an embodiment of the autonomous vehicle simulation testing device of this application;

[0034] Figure 5 This is a schematic diagram of the hardware structure of the autonomous vehicle simulation test equipment involved in the embodiments of this application. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0037] In a first aspect, embodiments of this application provide a method for simulating and testing autonomous vehicles.

[0038] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the autonomous vehicle simulation testing method of this application, as shown below. Figure 1 As shown, the simulation testing method for autonomous vehicles includes:

[0039] Step S10: In the simulation scenario, when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable traffic participant to reach the preset collision point is less than the preset error time, the vulnerable traffic participant is controlled to decelerate and stop.

[0040] In this embodiment, the simulation is applied to test autonomous vehicles equipped with autonomous or assisted driving systems, particularly observing their performance in a game scenario involving vulnerable road users. The autonomous vehicle is controlled autonomously by its onboard autonomous or assisted driving system algorithm; the simulation system does not intervene. Instead, it controls the vulnerable road users based on the detected state and behavior of the autonomous vehicle. By realistically simulating the psychology and behavior of vulnerable road users in the game scenario, the simulation system more accurately evaluates the behavior of both the autonomous vehicle and the vulnerable road users. Specifically, when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable road user to reach the preset collision point is less than a preset error time, i.e., when the simulation system determines that a collision is imminent by detecting the remaining time for both the autonomous vehicle and the vulnerable road user to reach the preset collision point, it controls the vulnerable road user to decelerate and stop. Vulnerable road users include, for example, pedestrians, bicycles, and electric vehicles.

[0041] Step S20: If the autonomous vehicle is detected to decelerate and stop, then monitor the subsequent state of the autonomous vehicle.

[0042] In this embodiment, after the simulation system detects a possible collision in step S10, it controls the vulnerable traffic participant to slow down and stop. At this time, the behavior state of the autonomous vehicle is observed. If the autonomous vehicle slows down and stops, the subsequent state of the autonomous vehicle is monitored so as to control the vulnerable traffic participant to perform the corresponding behavior according to the behavior state of the autonomous vehicle. Thus, from the perspective of the vulnerable traffic participant, the scenario of traffic game between the vulnerable traffic participant and the autonomous vehicle is simulated.

[0043] In step S30, if the autonomous vehicle is detected to be activated, the control of vulnerable traffic participants is also activated.

[0044] In this embodiment, taking a pedestrian as an example of a vulnerable traffic participant, it is understood that in real traffic game scenarios, it often happens that when a pedestrian sees a vehicle start, the pedestrian will also start. Therefore, if the start of an autonomous vehicle is detected, the vulnerable traffic participant is controlled to start as well. Compared with the current simulation test of autonomous driving, which simply sets the vulnerable traffic participant to uniform motion, this application can make a more accurate evaluation of the performance of the autonomous vehicle in the game between the autonomous vehicle and the vulnerable traffic participant by realistically simulating the psychology and behavior of the vulnerable traffic participant.

[0045] In step S40, if it is detected that the autonomous vehicle remains stationary, then the vulnerable road users are also controlled to remain stationary.

[0046] In this embodiment, it is also understood that in real traffic game scenarios, it often happens that when pedestrians see a vehicle remaining stationary, they will also remain stationary. Therefore, if the autonomous vehicle is detected to remain stationary, the vulnerable traffic participant is also controlled to remain stationary. Compared to current autonomous driving simulation tests that simply set the vulnerable traffic participant to uniform motion, this application realistically simulates the psychology and behavior of the vulnerable traffic participant, thereby enabling a more accurate evaluation of the performance of the autonomous vehicle in the game between the autonomous vehicle and the vulnerable traffic participant. It should be noted that after the autonomous vehicle remains stationary for a certain period of time, the vulnerable traffic participant can be controlled to continue moving towards the preset collision point to observe the subsequent behavior of the autonomous vehicle.

[0047] In this embodiment, the simulation is applied to test autonomous vehicles equipped with autonomous or assisted driving systems. Specifically, the simulation observes the performance of autonomous vehicles in a game-theoretic scenario involving vulnerable road users. The autonomous vehicle is controlled autonomously by its onboard autonomous or assisted driving system algorithm; the simulation system does not intervene. Instead, the simulation system controls the vulnerable road user based on the detected state and behavior of the autonomous vehicle. By realistically simulating the psychology and behavior of the vulnerable road user in the game-theoretic scenario, the simulation system more accurately evaluates the autonomous vehicle's performance. When the simulation system detects the remaining time for both the autonomous vehicle and the vulnerable road user to reach a preset collision point and determines that a collision is imminent, it controls the vulnerable road user to decelerate and stop. The behavior of the autonomous vehicle is then observed. If the autonomous vehicle decelerates and stops, its subsequent state is monitored to control the vulnerable road user's corresponding actions based on the autonomous vehicle's behavior. This simulation, from the perspective of the vulnerable road user, simulates a traffic game scenario between the vulnerable road user and the autonomous vehicle. Taking pedestrians as a vulnerable road user as an example, it is understandable that in real traffic game scenarios, it often happens that when pedestrians and vehicles perceive a collision risk, they will stop simultaneously, and when pedestrians or vehicles see the other is stationary, they will start simultaneously. Therefore, in order to realistically simulate this traffic game scenario, if the autonomous vehicle is detected to start, the vulnerable road user is also controlled to start; if the autonomous vehicle is detected to remain stationary, the vulnerable road user is also controlled to remain stationary. Thus, compared to the current simulation tests of autonomous driving that simply set the vulnerable road user to uniform motion, this application can make a more accurate evaluation of the performance of autonomous vehicles in the game between autonomous vehicles and vulnerable road users by realistically simulating the psychology and behavior of vulnerable road users.

[0048] Furthermore, in one embodiment, reference is made to Figure 2 , Figure 2 For this application Figure 1 A detailed flowchart of step S10 is shown below. Figure 2 As shown, step S10 includes:

[0049] Step S101: In the simulation scenario, the autonomous vehicle is set to travel towards the preset collision point at a preset initial speed. When the remaining time for the autonomous vehicle to travel at the preset initial speed to the preset collision point is detected to be a preset time, the vulnerable traffic participant is controlled to travel towards the preset collision point from the initial position. The preset time is the time for the vulnerable traffic participant to travel from the initial position to the preset collision point.

[0050] Step S102: When the vulnerable traffic participant travels to the preset judgment position, calculate the first remaining time for the autonomous vehicle to travel at a preset initial speed at a constant speed to reach the preset collision point and the second remaining time for the vulnerable traffic participant to reach the preset collision point.

[0051] Step S103: If the absolute value of the difference between the first remaining time and the second remaining time is less than the preset error time, then control the vulnerable traffic participants to decelerate and stop to the preset pause position.

[0052] In this embodiment, refer to Figure 3 , Figure 3 This is a schematic diagram of a simulation scenario for an embodiment of the autonomous vehicle simulation testing method of this application, as shown below. Figure 3 As shown, in the simulation scenario, which is a traffic intersection with a zebra crossing, an autonomous vehicle is set to travel towards a preset collision point at a preset initial speed. The preset initial speed can be set according to the specific testing requirements of the autonomous vehicle. After the simulation system sets a preset initial speed for the autonomous vehicle, no control intervention is performed on the autonomous vehicle during the subsequent simulation test. The autonomous vehicle is controlled by its onboard autonomous driving or assisted driving system algorithm to travel towards the preset collision point. When the simulation system detects that the remaining time for the autonomous vehicle to travel at a constant speed to the preset collision point is a preset time, it controls the vulnerable traffic participant to start traveling towards the preset collision point from the initial position. The time for the vulnerable traffic participant to travel from the initial position to the preset collision point is the preset time. Therefore, it can be seen that when the vulnerable traffic participant starts running from the initial position, both the vulnerable traffic participant and the autonomous vehicle arrive at the preset collision point after the same preset time. When a vulnerable road user moves to a preset judgment position, the system calculates the first remaining time for the autonomous vehicle to reach the preset collision point at a preset initial speed and the second remaining time for the vulnerable road user to reach the preset collision point. If the absolute value of the difference between the first remaining time and the second remaining time is less than the preset error time, it indicates that a collision is about to occur between the vulnerable road user and the autonomous vehicle. The system then controls the vulnerable road user to decelerate and stop at a preset pause position.

[0053] Furthermore, in one embodiment, the process of a vulnerable traffic participant moving from an initial position to a preset collision point includes acceleration, constant speed, and deceleration phases, with the preset judgment position located during the constant speed phase of the vulnerable traffic participant.

[0054] In this embodiment, the process of a vulnerable traffic participant moving from the initial position to the preset collision point includes acceleration, constant speed and deceleration stages. As mentioned above, vulnerable traffic participants include pedestrians, bicycles and electric vehicles. Different acceleration, constant speed and deceleration can be set according to different vulnerable traffic participants to realistically simulate real-world scenarios. When the vulnerable traffic participant moves at a constant speed to the preset judgment position, it is detected and judged whether a collision is about to occur between the vulnerable traffic participant and the autonomous vehicle.

[0055] Furthermore, in one embodiment, controlling a vulnerable traffic participant to move from an initial position toward a predetermined collision point includes:

[0056] The system controls vulnerable road users to begin climbing over a barrier from an initial position located outside the barrier and proceed toward a preset collision point. The preset duration includes the time required to climb over the barrier, and the outside of the barrier refers to the outer side of the barrier relative to the autonomous vehicle.

[0057] In this embodiment, it differs from Figure 3 In a traffic intersection scenario with a zebra crossing, a scenario simulating a vulnerable road user climbing over a barrier is presented. The vulnerable road user initially positions themselves outside the barrier. It's important to note that when the vulnerable road user is outside the barrier, the autonomous vehicle's algorithm should not stop the vehicle. Only when the vulnerable road user initially positions themselves inside the barrier should the algorithm stop the vehicle if collision conditions are met. If the autonomous vehicle stops when the vulnerable road user is initially outside the barrier, it indicates that the algorithm is inadequate. In this scenario, both the vulnerable road user and the autonomous vehicle reach the preset collision point after the same preset time, which includes the time it takes for the vulnerable road user to climb over the barrier.

[0058] Furthermore, in one embodiment, the preset judgment position is the position of the railing.

[0059] In this embodiment, the scenario of vulnerable road users climbing over railings is usually quite dangerous. Therefore, the preset judgment position can be the railing position, that is, the collision risk is detected and judged when the vulnerable road user climbs over the railing. It is easy to understand that the corresponding scenario is that the collision risk is detected and judged when the vulnerable road user moves to the preset judgment position after climbing over the railing.

[0060] Furthermore, in one embodiment, the autonomous vehicle simulation testing method further includes:

[0061] Record the distance between the autonomous vehicle and vulnerable road users during the simulation test, as well as whether the vehicle collides with vulnerable road users, in order to evaluate the simulation test results of the autonomous vehicle.

[0062] In this embodiment, compared to the current simulation test of autonomous driving which simply sets vulnerable traffic participants to uniform motion, this application simulates the psychology and behavior of vulnerable traffic participants in a realistic way, and records the distance between the autonomous vehicle and the vulnerable traffic participants and whether the autonomous vehicle collides with the vulnerable traffic participants during the simulation test, so as to accurately evaluate the performance of the autonomous vehicle in the game between the autonomous vehicle and the vulnerable traffic participants.

[0063] Further, in one embodiment, the process after step S10 includes:

[0064] If the autonomous vehicle is detected to have failed to slow down and stop, the system will control vulnerable road users to continue moving toward the pre-set collision point.

[0065] In this embodiment, after the simulation system detects a collision risk and controls the vulnerable road user to slow down and stop, if it detects that the autonomous vehicle has not slowed down and stopped, it controls the vulnerable road user to continue moving towards the preset collision point in order to observe the emergency avoidance capability of the autonomous vehicle.

[0066] Secondly, embodiments of this application also provide an autonomous vehicle simulation testing device.

[0067] In one embodiment, reference is made to Figure 4 , Figure 4 This is a functional block diagram of an embodiment of the autonomous vehicle simulation testing device of this application, as shown below. Figure 4 As shown, the autonomous vehicle simulation test device includes:

[0068] The deceleration and stop module 10 is used to control the vulnerable traffic participant to decelerate and stop when the absolute value of the difference between the remaining time of the autonomous vehicle to reach the preset collision point and the remaining time of the vulnerable traffic participant to reach the preset collision point is less than the preset error time in a simulation scenario.

[0069] The status monitoring module 20 is used to monitor the subsequent status of the autonomous vehicle if it is detected that the autonomous vehicle is slowing down and stopping.

[0070] The activation module 30 is used to control vulnerable traffic participants to also activate if the activation of the autonomous vehicle is detected.

[0071] The stop-and-hold module 40 is used to control vulnerable road users to also remain stopped if the autonomous vehicle is detected to remain stopped.

[0072] Furthermore, in one embodiment, the deceleration and stop module 10 is used for:

[0073] In the simulation scenario, an autonomous vehicle is set to travel towards a preset collision point at a preset initial speed. When the remaining time for the autonomous vehicle to travel to the preset collision point at a preset initial speed is detected as a preset time, the vulnerable traffic participant is controlled to start moving towards the preset collision point from the initial position. The preset time is the time for the vulnerable traffic participant to move from the initial position to the preset collision point.

[0074] When the vulnerable road user moves to the preset judgment position, calculate the first remaining time for the autonomous vehicle to reach the preset collision point at a preset initial speed and the second remaining time for the vulnerable road user to reach the preset collision point.

[0075] If the absolute value of the difference between the first remaining time and the second remaining time is less than the preset error time, then the vulnerable traffic participants will be controlled to slow down and stop to the preset pause position.

[0076] Furthermore, in one embodiment, the process of a vulnerable traffic participant moving from an initial position to a preset collision point includes acceleration, constant speed, and deceleration phases, with the preset judgment position located during the constant speed phase of the vulnerable traffic participant.

[0077] Furthermore, in one embodiment, the autonomous vehicle simulation testing device further includes a barrier-climbing module, used for:

[0078] The system controls vulnerable road users to begin climbing over a barrier from an initial position located outside the barrier and proceed toward a preset collision point. The preset duration includes the time required to climb over the barrier, and the outside of the barrier refers to the outer side of the barrier relative to the autonomous vehicle.

[0079] Furthermore, in one embodiment, the preset judgment position is the position of the railing.

[0080] Furthermore, in one embodiment, the autonomous vehicle simulation testing apparatus further includes a recording and evaluation module, used for:

[0081] Record the distance between the autonomous vehicle and vulnerable road users during the simulation test, as well as whether the vehicle collides with vulnerable road users, in order to evaluate the simulation test results of the autonomous vehicle.

[0082] Furthermore, in one embodiment, the autonomous vehicle simulation testing apparatus further includes a continuing-journey module, used for:

[0083] If the autonomous vehicle is detected to have failed to slow down and stop, the system will control vulnerable road users to continue moving toward the pre-set collision point.

[0084] The functions of each module in the above-mentioned autonomous vehicle simulation test device correspond to the steps in the above-mentioned autonomous vehicle simulation test method embodiment, and their functions and implementation processes will not be described in detail here.

[0085] Thirdly, embodiments of this application provide an autonomous vehicle simulation testing device.

[0086] Reference Figure 5 , Figure 5 This is a schematic diagram of the hardware structure of the autonomous vehicle simulation testing equipment involved in the embodiments of this application. In this embodiment, the autonomous vehicle simulation testing equipment may include a processor, a memory, a communication interface, and a communication bus.

[0087] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0088] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the autonomous vehicle simulation test equipment, as well as interfaces used for interconnecting the autonomous vehicle simulation test equipment with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0089] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0090] The processor can be a general-purpose processor, which can call the autonomous vehicle simulation test program stored in the memory and execute the autonomous vehicle simulation test method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the autonomous vehicle simulation test program is called can be referred to in the various embodiments of the autonomous vehicle simulation test method of this application, and will not be repeated here.

[0091] Those skilled in the art will understand that Figure 5 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0092] Fourthly, embodiments of this application also provide a readable storage medium.

[0093] The present application has an autonomous vehicle simulation test program stored on a readable storage medium, wherein when the autonomous vehicle simulation test program is executed by a processor, it implements the steps of the autonomous vehicle simulation test method described above.

[0094] The method implemented when the autonomous vehicle simulation test program is executed can be referred to in various embodiments of the autonomous vehicle simulation test method of this application, and will not be repeated here.

[0095] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0096] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0097] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0098] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0099] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0100] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0101] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A simulation testing method for autonomous vehicles, characterized in that, The autonomous vehicle simulation testing method includes: In the simulation scenario, when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable road user to reach the preset collision point is less than the preset error time, the vulnerable road user is controlled to decelerate and stop. If the autonomous vehicle is detected to slow down and stop, then monitor the subsequent state of the autonomous vehicle. If an autonomous vehicle is detected to be activated, then controls for vulnerable road users will also be activated. If the autonomous vehicle is detected to remain stationary, then vulnerable road users should also be controlled to remain stationary. In the simulation scenario, when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable road user to reach the preset collision point is less than a preset error time, controlling the vulnerable road user to decelerate and stop includes: In the simulation scenario, an autonomous vehicle is set to travel towards a preset collision point at a preset initial speed. When the remaining time for the autonomous vehicle to travel to the preset collision point at a preset initial speed is detected as a preset time, the vulnerable traffic participant is controlled to start moving towards the preset collision point from the initial position. The preset time is the time for the vulnerable traffic participant to move from the initial position to the preset collision point. When the vulnerable road user moves to the preset judgment position, calculate the first remaining time for the autonomous vehicle to reach the preset collision point at a preset initial speed and the second remaining time for the vulnerable road user to reach the preset collision point. If the absolute value of the difference between the first remaining time and the second remaining time is less than the preset error time, then the vulnerable traffic participants will be controlled to slow down and stop to the preset pause position.

2. The autonomous vehicle simulation testing method as described in claim 1, characterized in that, The process of a vulnerable road user moving from the initial position to the preset collision point includes acceleration, constant speed and deceleration phases, with the preset judgment position located during the constant speed phase of the vulnerable road user.

3. The autonomous vehicle simulation testing method as described in claim 1, characterized in that, The method of controlling vulnerable road users to move from an initial position toward a preset collision point includes: The system controls vulnerable road users to begin climbing over a barrier from an initial position located outside the barrier and proceed toward a preset collision point. The preset duration includes the time required to climb over the barrier, and the outside of the barrier refers to the outer side of the barrier relative to the autonomous vehicle.

4. The autonomous vehicle simulation testing method as described in claim 3, characterized in that, The preset judgment position is the position of the railing.

5. The autonomous vehicle simulation testing method as described in claim 1, characterized in that, The autonomous vehicle simulation testing method also includes: Record the distance between the autonomous vehicle and vulnerable road users during the simulation test, as well as whether the vehicle collides with vulnerable road users, in order to evaluate the simulation test results of the autonomous vehicle.

6. The autonomous vehicle simulation testing method as described in claim 1, characterized in that, After controlling the vulnerable road user to decelerate and stop when the absolute value of the difference between the remaining time for the autonomous vehicle to reach the preset collision point and the remaining time for the vulnerable road user to reach the preset collision point is less than a preset error time, the process includes: If the autonomous vehicle is detected to have failed to slow down and stop, the system will control vulnerable road users to continue moving toward the pre-set collision point.

7. An autonomous vehicle simulation testing device, characterized in that, The autonomous vehicle simulation testing device includes: The deceleration and stop module is used to control the vulnerable traffic participant to decelerate and stop when the absolute value of the difference between the remaining time of the autonomous vehicle to reach the preset collision point and the remaining time of the vulnerable traffic participant to reach the preset collision point is less than a preset error time in a simulation scenario. The status monitoring module is used to monitor the subsequent status of the autonomous vehicle if it is detected that the autonomous vehicle has slowed down and stopped. The activation module is used to control vulnerable road users to also activate if the activation of an autonomous vehicle is detected. The stop-and-hold module is used to control vulnerable road users to also remain stationary if the autonomous vehicle is detected to remain stationary. The deceleration and stopping module is also used for: In the simulation scenario, an autonomous vehicle is set to travel towards a preset collision point at a preset initial speed. When the remaining time for the autonomous vehicle to travel to the preset collision point at a preset initial speed is detected as a preset time, the vulnerable traffic participant is controlled to start moving towards the preset collision point from the initial position. The preset time is the time for the vulnerable traffic participant to move from the initial position to the preset collision point. When the vulnerable road user moves to the preset judgment position, calculate the first remaining time for the autonomous vehicle to reach the preset collision point at a preset initial speed and the second remaining time for the vulnerable road user to reach the preset collision point. If the absolute value of the difference between the first remaining time and the second remaining time is less than the preset error time, then the vulnerable traffic participants will be controlled to slow down and stop to the preset pause position.

8. An autonomous vehicle simulation testing device, characterized in that, The autonomous vehicle simulation test equipment includes a processor, a memory, and an autonomous vehicle simulation test program stored in the memory and executable by the processor, wherein when the autonomous vehicle simulation test program is executed by the processor, it implements the steps of the autonomous vehicle simulation test method as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that, The readable storage medium stores an autonomous vehicle simulation test program, wherein when the autonomous vehicle simulation test program is executed by a processor, it implements the steps of the autonomous vehicle simulation test method as described in any one of claims 1 to 6.

Images