Automatic Generation Method, Device and Equipment for Dangerous Scenarios in Vehicle Function Testing

Abstract

The present application discloses a method, device, and equipment for automatically generating dangerous scenarios in vehicle function testing. By controlling the vehicle to run in a random traffic environment, a collision event is generated between the vehicle and a random collision target in the random traffic environment; collision state data of the vehicle and the corresponding collision target in each collision event is obtained; when the current state data of the vehicle matches the collision state data of the vehicle in the collision event during vehicle function testing, the collision target in the collision event is controlled to move according to the corresponding collision state data to generate a dangerous scenario. It is realized that dangerous scenarios can be automatically generated on the existing continuous test road, with high adaptability to the road structure. The behavior of the vehicle to be tested has been considered during the scenario generation process, and the probability of generating high-risk dangerous scenarios is high. There is no need for a relatively complex real-time algorithm, which basically does not affect the system real-time performance and is easy to implement.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle function simulation testing, and in particular to a method, device and equipment for automatically generating dangerous scenarios in vehicle function testing. Background Art

[0002] When conducting simulation tests on vehicles, simulation scenarios are the basis for functional verification and safety testing of intelligent connected vehicles. Compared with testing methods such as open roads and closed field tests, the use of simulation to conduct corner and dangerous scene tests has the unique advantages of being efficient, easy to implement, repeatable, low-cost and safe.

[0003] The simulation scenarios are mainly divided into two types: fragmentary and continuous. Among them, the fragmentary scenario is mainly defined and generated according to the vehicle's function to be tested, and is used for special function testing of the assisted driving system, such as the AEB pedestrian collision avoidance function test scenario; the continuous scenario is mainly used for high-level automatic driving system testing, placing the vehicle to be tested in a continuous scenario to test the vehicle's comprehensive intelligent driving ability to comply with traffic regulations, ensure safety and comfort during the process of continuous and long-term driving from the initial position to the destination.

[0004] At present, the definition of corner scenes and dangerous scenes in simulation scenarios is mainly based on fragmentary scenes obtained by three methods: real vehicle accident data, expert experience, and theoretical analysis. The real vehicle accident data restoration scheme reproduces in the simulation software based on the accident database. The scenes obtained by this scheme are fragmentary and difficult to combine with high-level autonomous driving continuous test scenarios. For example, the real vehicle data scene is a curve, and the continuous simulation scene built does not have a road structure that is relatively straight with the actual curve structure. In the expert experience scheme, such scenes are generally classified based on some typical scenes accumulated from experience. These scenes are to be used in the built continuous test roads. The specific values ​​of each parameter in the experience scene need to be adapted to the road structure. The workload is large, time-consuming, and the scenes that may be adapted cannot form dangerous scenes because the behavior of the test piece is not considered. The theoretical analysis scheme requires real-time dynamic adjustment of the behavior of traffic participants to form a relative state with the test vehicle with a collision risk. Because this scheme needs to predict the behavior based on the real-time state of the test vehicle, it requires a large amount of calculation and real-time computing resources, and has extremely high requirements for the robustness of the behavior budget algorithm, which is difficult to implement. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device and equipment for automatically generating dangerous scenarios in vehicle function testing, aiming to solve the technical problem of difficulty in generating dangerous scenarios in vehicle function testing.

[0006] In a first aspect, the present application provides a method for automatically generating dangerous scenarios in vehicle function testing, the method comprising the following steps:

[0007] Control the vehicle to run in a random traffic environment, so that the vehicle generates a collision event with a random collision target in the random traffic environment;

[0008] Obtain the collision state data of the vehicle and the corresponding collision target in each collision event;

[0009] When performing a vehicle function test, when the current state data of the vehicle matches the collision state data of the vehicle in the collision event, control the collision target in the collision event to move according to the corresponding collision state data to generate a dangerous scenario.

[0010] In some embodiments, the obtaining the collision state data of the vehicle and the corresponding collision target in each collision event includes:

[0011] Obtain the coordinates and speed of the vehicle in each collision event, and obtain the coordinates, speed and heading angle of the corresponding collision target.

[0012] In some embodiments, the obtaining the coordinates and speed of the vehicle in each collision event, and obtaining the coordinates, speed and heading angle of the corresponding collision target further includes:

[0013] Obtain the coordinates and speed of the vehicle at a first preset moment before the collision in each collision event, and obtain the coordinates, speed and heading angle of the corresponding collision target at the first preset moment before the collision, the second preset moment after the collision and the moment of the collision.

[0014] In some embodiments, when the current state data of the vehicle matches the collision state data of the vehicle in the collision event, controlling the collision target in the collision event to move according to the corresponding collision state data to generate a dangerous scenario includes:

[0015] When the deviation between the current coordinates and speed of the vehicle and the coordinates and speed of the vehicle at the first preset moment before the collision in the collision event is less than a preset deviation threshold, control the collision target in the collision event to move according to the corresponding collision state data to generate a dangerous scenario.

[0016] In some embodiments, controlling the collision target in the collision event to move according to the corresponding collision state data to generate a dangerous scenario further includes:

[0017] Control the collision target in the collision event to move according to the corresponding coordinates, speed and heading angle at the first preset moment before the collision, the second preset moment after the collision and the moment of the collision to generate the dangerous scenario.

[0018] In some embodiments, obtaining the respective collision state data of the vehicle and the corresponding collision target in each collision event further includes:

[0019] After the vehicle finishes running in the random traffic environment, determine the types of various collision events generated by the vehicle during this run and the quantity of each type.

[0020] Judge whether the types of collision events and the quantity of each type meet the generation requirements of the dangerous scenario.

[0021] If so, store the collision events.

[0022] Otherwise, control the vehicle to run again in the random traffic environment until the types of collision events generated and the quantity of each type meet the generation requirements of the dangerous scenario.

[0023] In some embodiments, before controlling the vehicle to run in the random traffic environment, it further includes:

[0024] Generate the random traffic environment according to the configured range of the traffic environment, the types and states of traffic participants in the traffic environment, and the traffic flow density in the traffic environment.

[0025] Wherein, the types of the traffic participants include at least one type of vehicle, cyclists, and pedestrians, and the states of the traffic participants include the moving positions and moving manners of the traffic participants.

[0026] In some embodiments, controlling the vehicle to run in the random traffic environment includes:

[0027] Disable the collision avoidance function of the vehicle.

[0028] Control the vehicle to run in the random traffic environment according to a preset target trajectory.

[0029] In a second aspect, the present application further provides an automatic generation device for dangerous scenarios in vehicle function testing. The device includes:

[0030] A first control module, which is used to control the vehicle to run in a random traffic environment so that the vehicle generates collision events with random collision targets in the random traffic environment.

[0031] An acquisition module, which is used to acquire the collision state data of the vehicle and the corresponding collision targets in each collision event.

[0032] A second control module, which is used to control the collision target in the collision event to move according to the corresponding collision state data to generate a dangerous scenario when the current state data of the vehicle matches the collision state data of the vehicle in the collision event during vehicle function testing.

[0033] In a third aspect, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored on the memory and executable by the processor. When the computer program is executed by the processor, the steps of the method for automatically generating a dangerous scenario in the vehicle function test as described above are implemented.

[0034] The present application provides a method, a device, and a device for automatically generating a dangerous scenario in a vehicle function test. By controlling the vehicle to run in a random traffic environment, a collision event is generated between the vehicle and a random collision target in the random traffic environment; collision state data of the vehicle and the corresponding collision target in each collision event is obtained; when the current state data of the vehicle matches the collision state data of the vehicle in the collision event during the vehicle function test, the collision target in the collision event is controlled to move according to the corresponding collision state data to generate a dangerous scenario. It is possible to automatically generate a dangerous scenario on an existing continuous test road, with high adaptability to the road structure. During the scenario generation process, the behavior of the vehicle to be tested has been considered, and the probability of generating a high-risk dangerous scenario is high. There is no need for a relatively complex real-time algorithm, which basically does not affect the system real-time performance and is easy to implement. Description of the Drawings

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is a schematic flowchart of a method for automatically generating a dangerous scenario in a vehicle function test provided by an embodiment of the present application;

[0037] Figure 2 It is a diagram of a status data record table for collision events;

[0038] Figure 3 It is a schematic block diagram of a device for automatically generating a dangerous scenario in a vehicle function test provided by an embodiment of the present application;

[0039] Figure 4 It is a schematic block diagram of the structure of a computer device related to an embodiment of the present application.

[0040] The realization, functional features, and advantages of the purpose of the present application will be further described in conjunction with the embodiments with reference to the drawings. Detailed Embodiments

[0041] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0042] The flowchart shown in the accompanying drawings is only an example, and does not necessarily include all contents and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0043] The embodiments of the present application provide a method, device, and equipment for automatically generating dangerous scenarios in vehicle function testing. Among them, the method for automatically generating dangerous scenarios in vehicle function testing can be applied to a computer device, and the computer device can be an electronic device such as a laptop computer or a desktop computer.

[0044] Next, some embodiments of the present application will be described in detail in conjunction with the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0045] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for automatically generating dangerous scenarios in vehicle function testing provided by the embodiments of the present application.

[0046] As Figure 1 shown, the method includes steps S1 to S3.

[0047] Step S1: Control the vehicle to run in a random traffic environment so that the vehicle generates a collision event with a random collision target in the random traffic environment.

[0048] It should be noted that generating a random traffic environment is also included before controlling the vehicle to run in the random traffic environment.

[0049] Specifically, generating a random traffic environment includes: generating the random traffic environment according to the configured range of the traffic environment, the types and states of traffic participants in the traffic environment, and the traffic flow density in the traffic environment; wherein, the types of traffic participants include at least one type of vehicle, cyclist, and pedestrian, and the states of traffic participants include the movement positions and movement modes of the traffic participants.

[0050] Exemplarily, when generating a random traffic environment, it includes configuring the range of the random traffic environment, the random traffic flow density in the configured random traffic environment, and the types of vehicles in the random traffic flow. Among them, the range of the random traffic environment is the environmental area or road length. The types of vehicles in the random traffic flow can include various types of vehicles such as sedans, trucks, buses, etc. The random traffic flow density is the number of vehicles within the preset range of the random traffic environment. The random traffic environment also includes cyclists and pedestrians, etc. When configuring, it also includes configuring the positions and movement manners of traffic participants such as the pedestrian class and the cyclist class in the scene.

[0051] Furthermore, controlling the vehicle to run in the random traffic environment so that the vehicle generates a collision event with a random collision target in the random traffic environment includes: disabling the collision avoidance function of the vehicle and controlling the vehicle to run in the random traffic environment according to a preset target trajectory.

[0052] It should be noted that the random collision target is a vehicle, a cyclist, or a pedestrian, etc. configured in the random traffic environment. Intelligent connected vehicles generally have a collision avoidance function, that is, when the vehicle is too close to other objects and a collision may occur, the vehicle will brake or adjust its direction to avoid the collision. In this embodiment, it is necessary to obtain a collision event between the vehicle and a random collision target in the random traffic environment. Therefore, it is necessary to disable the collision avoidance function of the vehicle so that the vehicle travels through the entire random traffic environment according to the target trajectory to generate a collision event.

[0053] Step S2: Obtain the collision state data of the vehicle and the corresponding collision target in each collision event.

[0054] Specifically, obtain the coordinates and speed of the vehicle in each collision event, and obtain the coordinates, speed, and heading angle of the corresponding collision target.

[0055] Preferably, obtain the coordinates and speed of the vehicle at the first preset moment before the collision in each collision event, and obtain the coordinates, speed, and heading angle of the corresponding collision target at the first preset moment before the collision, the second preset moment after the collision, and at the time of the collision.

[0056] Exemplarily, after the collision event occurs, obtain the coordinates and speed of the vehicle T1 seconds before the collision, and at the same time obtain the coordinates, speed, and heading angle of the collision target that collides with the vehicle T1 seconds before the collision, the coordinates, speed, and heading angle at the time of the collision, and the coordinates, speed, and heading angle T2 seconds after the collision. Among them, the coordinates of the vehicle include the X-direction (lateral) coordinate, the Y (longitudinal) -direction coordinate, and the Z (vertical) -direction coordinate of the vehicle; the coordinates of the collision target include the X-direction (lateral) coordinate, the Y (longitudinal) -direction coordinate, and the Z (vertical) -direction coordinate of the collision target. At the same time, record the type of the collision target.

[0057] Further, obtaining the collision state data of the vehicle and the corresponding collision targets in each collision event further includes: after the vehicle finishes running in the random traffic environment, determining the types of each collision event generated by the vehicle during this run and the quantity of each type; judging whether the types of the collision events and the quantity of each type meet the generation requirements of the dangerous scenario; if so, storing the collision events; otherwise, controlling the vehicle to run again in the random traffic environment until the types of the generated collision events and the quantity of each type meet the generation requirements of the dangerous scenario.

[0058] Exemplarily, the types of the collision time include the types of traffic participants that collide with the vehicle and the way of collision, such as head-on collision, side collision, etc. For example, the dangerous scenario to be generated includes 5 side collision events with cars and 1 head-on collision event with pedestrians. If after the vehicle finishes running in the random traffic environment, there are 5 or more side collision events with cars generated and no head-on collision event with pedestrians; or if there are less than 5 side collision events with cars generated and 1 or more head-on collision events with pedestrians generated, it is considered that the generation requirements of the dangerous scenario are not met. If the collision data does not meet the generation requirements of the dangerous scenario, the data of the random traffic environment and the collision events will be initialized, and the vehicle will be controlled to run in the random environment again to generate collision events until the types and the quantity of the types of the collision events both meet the generation requirements of the dangerous scenario.

[0059] Further, after the types and the quantity of the generated collision events both meet the generation requirements of the dangerous scenario, the state data of the collision events can be stored according to the record table as Figure 2 shown to form a dangerous event sequence.

[0060] Step S3, when conducting vehicle function testing, when the current state data of the vehicle matches the collision state data of the vehicle in the collision event, controlling the collision target in this collision event to move according to the corresponding collision state data to generate a dangerous scenario.

[0061] Specifically, when the deviation between the current coordinates and speed of the vehicle and the coordinates and speed of the vehicle in the collision event at the first preset moment before the collision is less than the preset deviation threshold, controlling the collision target in this collision event to move according to the corresponding collision state data to generate a dangerous scenario.

[0062] It should be noted that controlling the collision target in this collision event to move according to the corresponding collision state data to generate a dangerous scenario specifically includes: controlling the collision target in this collision event to move according to the coordinates, speed, and heading angle corresponding to the first preset moment before the collision, the moment of collision, and the second preset moment after the collision to generate the dangerous scenario.

[0063] Exemplarily, start the autonomous driving vehicle or system to be tested according to the normal test procedure for testing. Observe in real time whether the deviation between the coordinates and speed of the autonomous driving vehicle to be tested and the coordinates and speed at the first preset moment before the vehicle collision recorded in the dangerous event sequence is less than the preset deviation threshold. When the deviation is less than the preset deviation threshold, trigger the coordinates and speed corresponding to the first preset moment before the root collision of the relevant collision target corresponding to the dangerous event, the moment of collision, and the second preset moment after the collision to move, so as to generate a dangerous interaction behavior.

[0064] It should be understood that in this embodiment, first, by shielding the collision avoidance function of the vehicle, a relatively large number of collision events are generated in a pre-running manner, and then the key data within a period of time before and after the collision event point is recorded; then, start the test of the autonomous driving vehicle / system to be tested according to the normal test procedure. At this time, the collision avoidance function can be normally turned on. Observe in real time whether the coordinates and speed of the autonomous driving vehicle to be tested are close to the coordinates and speed in the collision events that have occurred. When they are close, immediately trigger the corresponding collision target to perform a dangerous interaction behavior and generate a dangerous scenario to test whether the vehicle with the collision avoidance function turned on can avoid the collision target, so as to realize the simulation test of the vehicle.

[0065] The beneficial effect of the method for automatically generating a dangerous scenario in vehicle function testing provided by the embodiment of the present application is that a dangerous scenario is automatically generated on the existing continuous test road, and the adaptability to the road structure is high. The behavior of the vehicle to be tested has been considered during the scenario generation process, and the probability of generating a high-risk dangerous scenario is high. There is no need for a relatively complex real-time algorithm, which basically does not affect the real-time performance of the system and is easy to implement.

[0066] Please refer to Figure 3 , Figure 3 which is a schematic block diagram of an apparatus for automatically generating a dangerous scenario in vehicle function testing provided by the embodiment of the present application.

[0067] As Figure 3 shown, the apparatus includes:

[0068] A first control module, which is used to control the vehicle to run in a random traffic environment, so that the vehicle generates a collision event with a random collision target in the random traffic environment;

[0069] An acquisition module, which is used to acquire the collision state data of the vehicle and the corresponding collision target in each collision event;

[0070] A second control module, which is used to control the collision target in the collision event to move according to the corresponding collision state data to generate a dangerous scenario when the current state data of the vehicle matches the collision state data of the vehicle in the collision event during the vehicle function test.

[0071] Wherein, the obtaining module is further configured to obtain the coordinates and speed of the vehicle in each collision event, and obtain the coordinates, speed and heading angle of the corresponding collision target.

[0072] Wherein, the obtaining module is further configured to obtain the coordinates and speed of the vehicle at a first preset moment before the collision in each collision event, and obtain the coordinates, speed and heading angle of the corresponding collision target at the first preset moment before the collision, the second preset moment after the collision and the moment of the collision.

[0073] Wherein, the second control module is further configured to:

[0074] When the deviation between the current coordinates and speed of the vehicle and the coordinates and speed of the vehicle at the first preset moment before the collision in the collision event is less than a preset deviation threshold, control the collision target in the collision event to move according to the corresponding collision state data to generate a dangerous scenario.

[0075] Wherein, the second control module is further configured to:

[0076] Control the collision target in the collision event to move according to the coordinates, speed and heading angle corresponding to the first preset moment before the collision, the second preset moment after the collision and the moment of the collision to generate the dangerous scenario.

[0077] Wherein, the obtaining module is further configured to:

[0078] After the vehicle finishes running in the random traffic environment, determine the types of each collision event generated by the vehicle during this run and the quantity of each type;

[0079] Judge whether the types of the collision events and the quantity of each type meet the generation requirements of the dangerous scenario;

[0080] If so, store the collision event;

[0081] Otherwise, control the vehicle to run again in the random traffic environment until the types of the generated collision events and the quantity of each type meet the generation requirements of the dangerous scenario.

[0082] Wherein, the device is further configured to:

[0083] Generate the random traffic environment according to the configured range of the traffic environment, the types and states of traffic participants in the traffic environment, and the traffic flow density in the traffic environment;

[0084] Wherein, the types of the traffic participants include at least one type of vehicle, cyclist and pedestrian, and the states of the traffic participants include the moving positions and moving modes of the traffic participants.

[0085] Wherein, the first control module is further configured to:

[0086] Disable the collision avoidance function of the vehicle;

[0087] Control the vehicle to run in the random traffic environment according to a preset target trajectory.

[0088] It should be noted that those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described device and each module and unit can refer to the corresponding processes in the foregoing embodiments, and will not be elaborated herein.

[0089] The device provided in the above embodiment can be implemented in the form of a computer program, and the computer program can run on a computer device as shown in Figure 4 shown.

[0090] Please refer to Figure 4 , Figure 4 , which is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application. The computer device can be a terminal such as a notebook computer.

[0091] As shown in Figure 4 , the computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the memory can include a non-volatile storage medium and an internal memory.

[0092] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute an automatic generation method for a dangerous scenario in any vehicle function test.

[0093] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0094] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute an automatic generation method for a dangerous scenario in any vehicle function test.

[0095] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 4 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0096] It should be understood that the processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0097] It should be noted that in this text, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article, or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or system including that element.

[0098] The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments. The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An automatic generation method for dangerous scenarios in vehicle function testing, characterized in that, Including: Controlling a vehicle to run in a random traffic environment so that the vehicle generates a collision event with a random collision target in the random traffic environment; Obtaining collision state data of the vehicle and the corresponding collision target in each collision event; When conducting a vehicle function test, when the current state data of the vehicle matches the collision state data of the vehicle in a collision event, controlling the collision target in this collision event to move according to the corresponding collision state data to generate a dangerous scenario; Among them, the obtaining of the collision state data of the vehicle and the corresponding collision target in each collision event includes: Obtaining the coordinates and speed of the vehicle in each collision event, and obtaining the coordinates, speed and heading angle of the corresponding collision target; Among them, the obtaining of the coordinates and speed of the vehicle in each collision event, and obtaining the coordinates, speed and heading angle of the corresponding collision target further includes: Obtaining the coordinates and speed of the vehicle at a first preset moment before the collision in each collision event, and obtaining the coordinates, speed and heading angle of the corresponding collision target at the first preset moment before the collision, the second preset moment after the collision and at the time of the collision; Among them, controlling the collision target in this collision event to move according to the corresponding collision state data to generate a dangerous scenario further includes: Controlling the collision target in this collision event to move according to the coordinates, speed and heading angle corresponding to the first preset moment before the collision, at the time of the collision and the second preset moment after the collision to generate the dangerous scenario.

2. The automatic generation method for dangerous scenarios in vehicle function testing according to claim 1, characterized in that, When the current state data of the vehicle matches the collision state data of the vehicle in a collision event, controlling the collision target in this collision event to move according to the corresponding collision state data to generate a dangerous scenario includes: When the deviation between the current coordinates and speed of the vehicle and the coordinates and speed of the vehicle at the first preset moment before the collision in the collision event is less than a preset deviation threshold, controlling the collision target in this collision event to move according to the corresponding collision state data to generate a dangerous scenario.

3. The automatic generation method for dangerous scenarios in vehicle function testing according to claim 1, characterized in that, The obtaining of the respective collision state data of the vehicle and the corresponding collision target in each collision event further includes: After the vehicle finishes running in the random traffic environment, determining the types of each collision event generated by the vehicle during this run and the quantity of each type; Judging whether the types of the collision events and the quantity of each type meet the generation requirements of the dangerous scenario; If so, storing the collision events; Otherwise, controlling the vehicle to run again in the random traffic environment until the types of the generated collision events and the quantity of each type meet the generation requirements of the dangerous scenario.

4. The automatic generation method for dangerous scenarios in vehicle function testing according to claim 1, characterized in that, Before controlling the vehicle to run in the random traffic environment, it further includes: Generating the random traffic environment according to the configured range of the traffic environment, the types and states of traffic participants in the traffic environment, and the traffic flow density in the traffic environment; Among them, the types of the traffic participants include at least one type of vehicle, cyclist and pedestrian, and the states of the traffic participants include the movement positions and movement modes of the traffic participants.

5. The automatic generation method for dangerous scenarios in vehicle function testing according to claim 1, characterized in that, Controlling the vehicle to run in the random traffic environment includes: Blocking the collision avoidance function of the vehicle; Control the vehicle to run in the random traffic environment according to a preset target trajectory.

6. An automatic generation device for dangerous scenarios in vehicle function testing, characterized in that, Comprising: A first control module for controlling the vehicle to run in a random traffic environment so that the vehicle generates a collision event with a random collision target in the random traffic environment; An acquisition module for acquiring the collision state data of the vehicle and the corresponding collision target in each collision event; A second control module for, when performing a vehicle function test, controlling the collision target in the collision event to move according to the corresponding collision state data when the current state data of the vehicle matches the collision state data of the vehicle in the collision event, so as to generate a dangerous scenario; Wherein, the acquisition module is further configured to: Acquire the coordinates and speed of the vehicle in each collision event, and acquire the coordinates, speed and heading angle of the corresponding collision target; Wherein, the acquisition module is further configured to: Acquire the coordinates and speed of the vehicle at a first preset moment before the collision in each collision event, and acquire the coordinates, speed and heading angle of the corresponding collision target at the first preset moment before the collision, the second preset moment after the collision, and the moment of collision; Wherein, the second control module is further configured to: Control the collision target in the collision event to move according to the corresponding coordinates, speed and heading angle at the first preset moment before the collision, the second preset moment after the collision, and the moment of collision, so as to generate the dangerous scenario.

7. A computer device, characterized in that, The computer device includes a processor, a memory, and a computer program stored on the memory and executable by the processor. When the computer program is executed by the processor, the steps of the method for automatically generating a dangerous scenario in a vehicle function test as described in any one of claims 1 to 5 are implemented.

Images