Vehicle fault simulation test system, method, device, computer program product

Abstract

The application discloses a kind of vehicle fault simulation test system, method, device, computer program product, it is related to vehicle function test technical field.Therein, the system includes: simulation software, for constructing the initial simulation test scene of vehicle to be measured;Fault injection board card, for adding fault information in at least part of scene data of initial simulation test scene, obtain target simulation test scene;Control equipment, for controlling the front-view camera of vehicle to be measured to present target simulation test scene, to carry out test to the automatic driving function to be measured of vehicle to be measured under target simulation test scene, obtain test data, wherein, test data is used to determine the function safety level of automatic driving function to be measured;Analysis equipment, for carrying out function safety analysis to test data, obtain function safety level.The application solves the technical problem that the test result accuracy of vehicle function scene test method used in prior art is low.

Description

Technical Field

[0001] This invention relates to the field of vehicle function testing technology, and more specifically, to a vehicle fault simulation testing system, method, apparatus, and computer program product. Background Technology

[0002] With the continuous development of automotive intelligence, autonomous driving technology has become a trend in the automotive industry, and the development of autonomous driving functions is gradually becoming more diversified, complex, and intelligent. However, current autonomous driving systems are vulnerable and still cannot achieve absolutely safe driving capabilities in all weather conditions and all scenarios. Therefore, how to deal with potential safety hazards during autonomous driving has become a major challenge on the road to the widespread application of autonomous driving technology.

[0003] Currently, in the development of intelligent driving vehicle systems, the main methods for verifying the safety of autonomous vehicles are simulation testing and real-vehicle testing during the development process. Simulation testing, due to its diverse testing scenarios and low cost, has become the mainstream method for testing autonomous driving functions. To improve the safety of advanced autonomous driving functions, faults can be artificially introduced during autonomous driving scenario simulations to verify the robustness of the autonomous driving system in specific scenarios, thereby verifying whether the current development results meet the designed functional safety specifications.

[0004] As a sensor in autonomous driving systems that enables functions such as automatic emergency braking, advanced cruise control, intelligent speed limit recognition, and lane keeping assist, the forward-facing camera inputs scene information to various controllers for perception, decision-making, and control. Therefore, fault handling of the perceived signals (such as camera breakage, obstruction, dust accumulation, or exposure to strong light) can simulate video fault injection scenarios during testing. Currently, testing for forward-facing camera fault injection scenarios mainly utilizes real-vehicle testing and hardware-in-the-loop testing (HIL). However, real-vehicle testing is costly, risky, and inefficient, and cannot be used for large-scale fault injection scenario testing. Hardware-in-the-loop testing uses simulated vehicle actuators, cannot reflect real vehicle performance during testing, and is more suitable for testing vehicle logic scenarios than for functional scenarios like camera fault injection.

[0005] As can be seen from the above analysis, there is currently no effective solution to the problem of low accuracy of test results in the vehicle functional scenario testing methods used in the above-mentioned existing technologies. Summary of the Invention

[0006] This invention provides a vehicle fault simulation testing system, method, apparatus, and computer program product to at least solve the technical problem of low accuracy of test results in existing vehicle functional scenario testing methods.

[0007] According to one aspect of the present invention, a vehicle fault simulation testing system is provided, comprising:

[0008] Simulation software is used to construct an initial simulation test scenario for the vehicle under test; a fault injection board is used to add fault information to at least a portion of the scenario data in the initial simulation test scenario to obtain a target simulation test scenario; a control device is used to control the forward-facing camera of the vehicle under test to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data, wherein the test data is used to determine the functional safety level of the autonomous driving function under test; and an analysis device is used to perform functional safety analysis on the test data to obtain the functional safety level.

[0009] According to another aspect of the present invention, a vehicle fault simulation test method is provided, comprising:

[0010] Construct an initial simulation test scenario for the vehicle under test; add fault information to at least a portion of the scenario data in the initial simulation test scenario to obtain a target simulation test scenario; control the forward-facing camera of the vehicle under test to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data, wherein the test data is used to determine the functional safety level of the autonomous driving function under test; perform functional safety analysis on the test data to obtain the functional safety level.

[0011] Optionally, the initial simulation test scenario includes at least a vehicle model, a sensor model, and an environment model. Constructing the initial simulation test scenario for the vehicle under test includes: collecting initial vehicle data and initial environment data of the vehicle under test, wherein the initial vehicle data includes at least: initial vehicle position, sensor position, and vehicle body data; establishing a scene coordinate system based on the initial vehicle position; and constructing a vehicle model based on the vehicle body data, a sensor model based on the sensor position, and an environment model based on the initial environment data within the scene coordinate system.

[0012] Optionally, adding fault information to at least a portion of the scenario data in the initial simulation test scenario to obtain the target simulation test scenario includes: determining the autonomous driving function to be tested for the vehicle under test; adding fault information to at least a portion of the scenario data based on the autonomous driving function to be tested to obtain the target simulation test scenario corresponding to the autonomous driving function to be tested, wherein the fault information is determined by the test requirements of the autonomous driving function to be tested.

[0013] Optionally, the test data includes at least multiple types of response data of the autonomous driving function under test. The autonomous driving function of the vehicle under test is tested in the target simulation test scenario, and the test data obtained includes: acquiring the scene perception data of the vehicle under test for the target simulation test scenario; making plans and decisions based on the scene perception data to generate control commands for the autonomous driving function under test; executing the control commands to control the vehicle under test to activate the autonomous driving function under test; and collecting multiple types of response data through multiple sensors during the operation of the autonomous driving function under test.

[0014] Optionally, performing functional safety analysis on the test data to obtain the functional safety level includes: scoring any type of response data according to a preset scoring table corresponding to any type of response data to obtain multiple score values; performing a weighted summation of the multiple score values ​​to obtain a target score value; and determining the functional safety level corresponding to the target score value based on a functional safety level mapping table.

[0015] Optionally, the above vehicle fault simulation test method further includes: generating target prompt information based on test data in response to the functional safety level being lower than a preset level limit; and providing functional safety prompts based on the target prompt information.

[0016] Optionally, the response data includes at least the pose data of the vehicle under test, and the above vehicle fault simulation test method further includes: updating the initial simulation test scenario using the pose data.

[0017] According to another aspect of the present invention, a vehicle fault simulation testing apparatus is also provided, comprising:

[0018] The system comprises the following modules: a construction module for building an initial simulation test scenario for the vehicle under test; a processing module for handling faults in the initial simulation test scenario to obtain a target simulation test scenario; a testing module for controlling the forward-facing camera of the vehicle under test to present the target simulation test scenario, thereby testing the autonomous driving function of the vehicle under test in the target simulation test scenario and obtaining test data, which is used to determine the functional safety level of the autonomous driving function under test; and an analysis module for performing functional safety analysis on the test data to obtain the functional safety level.

[0019] Optionally, the initial simulation test scenario includes at least a vehicle model, a sensor model, and an environment model. The aforementioned construction module is also used to: collect initial vehicle data and initial environment data of the vehicle under test, wherein the initial vehicle data includes at least: initial vehicle position, sensor position, and vehicle body data; establish a scene coordinate system based on the initial vehicle position; and in the scene coordinate system, construct a vehicle model based on the vehicle body data, construct a sensor model based on the sensor position, and construct an environment model based on the initial environment data.

[0020] Optionally, the above processing module is further configured to: determine the autonomous driving function to be tested of the vehicle under test; and add fault information to at least some scenario data according to the autonomous driving function to be tested to obtain a target simulation test scenario corresponding to the autonomous driving function to be tested, wherein the fault information is determined by the test requirements of the autonomous driving function to be tested.

[0021] Optionally, the test data includes at least multiple types of response data of the autonomous driving function under test. The aforementioned test module is also used to: acquire scene perception data of the vehicle under test for the target simulation test scenario; perform planning and decision-making based on the scene perception data to generate control commands for the autonomous driving function under test; execute the control commands to control the vehicle under test to activate the autonomous driving function under test; and collect multiple types of response data through multiple sensors during the operation of the autonomous driving function under test.

[0022] Optionally, the analysis module is further configured to: score any type of response data according to a preset scoring table corresponding to any type of response data, and obtain multiple scoring values; perform a weighted summation of the multiple scoring values ​​to obtain a target scoring value; and determine the functional safety level corresponding to the target scoring value based on a functional safety level mapping table.

[0023] Optionally, the vehicle fault simulation testing device further includes: a prompting module, used to generate target prompting information based on test data in response to a functional safety level being lower than a preset level limit; and to provide functional safety prompts based on the target prompting information.

[0024] Optionally, the response data includes at least the pose data of the vehicle under test, and the vehicle fault simulation test device further includes an update module for updating the initial simulation test scenario using the pose data.

[0025] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the vehicle fault simulation test method of any of the foregoing.

[0026] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform any of the aforementioned vehicle fault simulation test methods.

[0027] According to another aspect of the present invention, a vehicle is also provided, including an on-board memory and an on-board processor, wherein the on-board memory stores a computer program, and the on-board processor is configured to run the computer program to execute the vehicle fault simulation test method described in any of the foregoing embodiments.

[0028] In this embodiment of the invention, an initial simulation test scenario for the vehicle under test is first constructed. Fault information is added to at least a portion of the scenario data in the initial simulation test scenario to obtain a target simulation test scenario. The forward-facing camera of the vehicle under test is controlled to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test. Functional safety analysis is performed on the test data to obtain the functional safety level. By using a fault injection board to process the fault in the initial simulation test scenario constructed by the simulation software, the target simulation test scenario corresponding to the autonomous driving function under test is obtained. Then, the target simulation test scenario is injected into the forward-facing camera of the vehicle under test in the form of video. The target simulation test scenario is used to simulate the fault scenario when the vehicle is driving in real time to test the autonomous driving function of the vehicle. This achieves the purpose of testing vehicle functional scenarios through video fault injection, thereby improving the accuracy of vehicle functional scenario test results and solving the technical problem of low accuracy of test results in the existing vehicle functional scenario test methods. Attached Figure Description

[0029] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0030] Figure 1 This is a hardware structure block diagram of a vehicle terminal for a vehicle fault simulation testing method according to an embodiment of the present invention.

[0031] Figure 2 This is a schematic diagram of a vehicle fault simulation test system according to an embodiment of the present invention;

[0032] Figure 3 This is a flowchart of a vehicle fault simulation test method according to an embodiment of the present invention;

[0033] Figure 4 This is a schematic diagram of an optional vehicle fault simulation test scenario according to an embodiment of the present invention;

[0034] Figure 5 This is a schematic diagram of another optional vehicle fault simulation test scenario according to an embodiment of the present invention;

[0035] Figure 6 This is a schematic diagram of another optional vehicle fault simulation test scenario according to an embodiment of the present invention;

[0036] Figure 7 This is a structural block diagram of a vehicle fault simulation testing device according to an embodiment of the present invention. Detailed Implementation

[0037] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] According to an embodiment of the present invention, a method embodiment for vehicle fault simulation testing is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0040] Figure 1 This is a hardware structure block diagram of a vehicle terminal for a vehicle fault simulation testing method according to an embodiment of the present invention, such as... Figure 1As shown, a vehicle terminal (or mobile device) may include one or more processors 102 (processor 102 may include, but is not limited to, processing devices such as microprocessors (MCUs) or field-programmable gate arrays (FPGAs),) a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display device 110, an input / output device 108 (i.e., I / O devices), a Universal Serial Bus (USB) port (which may be included as one of the ports of a computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure), and / or a camera (not shown in the figure). Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the vehicle terminal described above. For example, the vehicle terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0041] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits may be embodied, in whole or in part, as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be integrated, in whole or in part, into any other component within the vehicle terminal (or mobile device).

[0042] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the vehicle fault simulation test method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned vehicle fault simulation test method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the vehicle terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0043] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the vehicle terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0044] Under the above operating environment, the embodiments of the present invention provide as follows: Figure 2 The vehicle fault simulation test system shown is as follows: Figure 2 As shown, the system includes:

[0045] Simulation software 201 is used to construct an initial simulation test scenario for the vehicle under test; fault injection board 202 is used to add fault information to at least a portion of the scenario data in the initial simulation test scenario to obtain a target simulation test scenario; control equipment including controller 203, host computer 204, vehicle actuator 205, etc., is used to control the forward-facing camera of the vehicle under test to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data, wherein the test data is used to determine the functional safety level of the autonomous driving function under test; analysis equipment (not shown in the figure) is used to perform functional safety analysis on the test data to obtain the functional safety level.

[0046] Based on the aforementioned vehicle fault simulation testing system, embodiments of the present invention also provide, for example... Figure 3 The vehicle fault simulation test method shown is as follows: Figure 3 As shown, the method includes the following implementation steps:

[0047] Step S301: Construct the initial simulation test scenario for the vehicle under test;

[0048] Step S302: Add fault information to at least a portion of the scenario data of the initial simulation test scenario to obtain the target simulation test scenario;

[0049] Step S303: Control the forward-facing camera of the vehicle under test to present the target simulation test scene, so as to test the autonomous driving function of the vehicle under test in the target simulation test scene and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test.

[0050] Step S304: Perform functional safety analysis on the test data to obtain the functional safety level.

[0051] like Figure 2As shown, the vehicle simulation software 201 first constructs an initial simulation test scenario for the vehicle under test. Then, the simulation software 201 provides this initial simulation test scenario to the fault injection board 202 in the form of a simulated video stream. The fault injection board 202 adds fault information to the scene data in the initial simulation test scenario based on the currently tested autonomous driving function (i.e., the autonomous driving function under test), thereby simulating the fault test scenario required by the autonomous driving function under test using the target simulated fault scenario. Further, the fault injection board 202 provides the target simulated test scenario to the forward-looking camera 206. It should be noted that the fault injection board 202 can provide the forward-looking camera 206 with scene perception data transformed from the target simulated test scenario. The forward-looking camera 206 can provide this scene perception data to the vehicle under test for perception, presenting the target simulated test scenario to the vehicle under test, thereby testing the autonomous driving function under test and analyzing the functional safety of the autonomous driving function under test.

[0052] In this embodiment of the invention, an initial simulation test scenario for the vehicle under test is first constructed. Fault information is added to at least a portion of the scenario data in the initial simulation test scenario to obtain a target simulation test scenario. The forward-facing camera of the vehicle under test is controlled to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test. Functional safety analysis is performed on the test data to obtain the functional safety level. By using a fault injection board to process the fault in the initial simulation test scenario constructed by the simulation software, the target simulation test scenario corresponding to the autonomous driving function under test is obtained. Then, the target simulation test scenario is injected into the forward-facing camera of the vehicle under test in the form of video. The target simulation test scenario is used to simulate the fault scenario when the vehicle is driving in real time to test the autonomous driving function of the vehicle. This achieves the purpose of testing vehicle functional scenarios through video fault injection, thereby improving the accuracy of vehicle functional scenario test results and solving the technical problem of low accuracy of test results in the existing vehicle functional scenario test methods.

[0053] The methods described in the embodiments of the present invention will be further described below.

[0054] In an optional embodiment, in step S301, the initial simulation test scenario includes at least a vehicle model, a sensor model, and an environment model. Constructing the initial simulation test scenario for the vehicle under test includes:

[0055] Step S311: Collect initial vehicle data and initial environmental data of the vehicle under test. The initial vehicle data includes at least the initial vehicle position, sensor position and vehicle body data.

[0056] Step S312: Establish a scene coordinate system based on the initial vehicle position;

[0057] Step S313: In the scene coordinate system, construct a vehicle model based on the vehicle body data, construct a sensor model based on the sensor positions, and construct an environment model based on the initial environment data.

[0058] As an optional implementation, the ground projection point of the rear axle midpoint of the vehicle can be determined based on the initial vehicle position. A scene coordinate system is established using this ground projection point as the origin. A vehicle model is constructed based on the vehicle's dimensions and other body data. Corresponding sensor models are constructed based on the coordinates of each sensor relative to this ground projection point (i.e., sensor positions). An environmental model is also constructed based on initial environmental data such as roads, traffic signs, light intensity, pedestrians, and obstacles surrounding the vehicle, thus creating the initial simulation test scene. Furthermore, as before... Figure 2 As shown, the data management software can be debugged in the host computer 204 to configure the input / output channels of the controller 203, record data and communicate with the host. At the same time, the position of the vehicle under test can be calibrated using the global positioning system conversion model and the world geodetic coordinate system can be converted to the Cartesian coordinate system.

[0059] In an optional embodiment, step S302, performing fault handling on the initial simulation test scenario to obtain the target simulation test scenario includes:

[0060] Step S321: Determine the autonomous driving function to be tested for the vehicle under test;

[0061] Step S322: Based on the autonomous driving function under test, add fault information to at least some of the scenario data to obtain the target simulation test scenario corresponding to the autonomous driving function under test, wherein the fault information is determined by the test requirements of the autonomous driving function under test.

[0062] The autonomous driving functions of the vehicle under test may include, but are not limited to: automatic emergency braking, automatic cruise control, intelligent speed limit recognition, and lane keeping assist.

[0063] As an optional implementation, assuming the autonomous driving function under test is an automatic emergency braking function, the fault test scenario (i.e., the target simulation test scenario) corresponding to the automatic emergency braking function may include, but is not limited to: a broken front-view camera, an obstructed front-view camera, or dust accumulation on the front-view camera (e.g., ...). Figure 4 As shown), when exposed to strong light (such as...) Figure 5 As shown), "ghost peek" (such as...) Figure 6 (As shown).

[0064] As another optional implementation method, when the autonomous driving function under test is the automatic emergency braking function and the target simulation test scenario is the "ghosting" scenario, the fault injection board can adjust the relative position of the vehicle under test and the pedestrian in the initial simulation test scenario, so that when the vehicle under test has a certain speed, the pedestrian suddenly enters from the blind spot in front of the vehicle under test.

[0065] In an optional embodiment, in step S303, the test data includes at least multiple types of response data of the autonomous driving function under test. The autonomous driving function of the vehicle under test is tested in a target simulation test scenario, and the test data obtained includes:

[0066] Step S331: Obtain scene perception data of the vehicle under test for the target simulation test scenario;

[0067] Step S332: Based on scene perception data, plan and make decisions to generate control commands for the autonomous driving function under test;

[0068] Step S333: Execute control commands to control the vehicle under test to activate the autonomous driving function under test;

[0069] Step S334: During the operation of the autonomous driving function under test, multiple types of response data are collected through multiple sensors.

[0070] Still as Figure 2 As shown, after the target simulation test scenario is constructed, it is injected into the vehicle under test through the forward-looking camera 206 to conduct an in-loop test on the vehicle under test. The autonomous driving function perception sensors of the vehicle under test (such as vision sensors, distance sensors, and radar sensors) can perceive the target simulation test scenario and send the obtained scenario perception data to the controller 203. The controller 203 performs planning and decision-making based on the scenario perception data, determines the autonomous driving function to be activated, and generates the control command corresponding to the autonomous driving function to be activated. Furthermore, the vehicle actuator 205 executes the control command to realize the functional response of the vehicle under test to the target simulation test scenario.

[0071] Still as Figure 2 As shown, further, during the functional response process, on the one hand, the driver of the vehicle under test completes driving control according to the current driving state of the vehicle under test; on the other hand, the autonomous driving system of the vehicle under test activates the autonomous driving function corresponding to the control command, so that the autonomous driving system directly controls the motion state of the vehicle under test and changes the vehicle's position and posture data.

[0072] It should be noted that the controller 203 can record data throughout the entire testing process of the autonomous driving function under test, especially before and after the response of the autonomous driving function under test, to record the data changes of the vehicle under test, thereby obtaining test data.

[0073] The aforementioned sensors may include, but are not limited to: braking system sensors, distance sensors, and inertial sensors. Among them, the braking system sensors can be used to collect the changes in the position of the brake pedal and the changes in braking pressure of the vehicle under test before and after the autonomous driving function under test is activated. The distance sensors can be used to collect the distance between the vehicle under test and obstacles, pedestrians, etc. in front of it before and after the autonomous driving function under test is activated. The inertial sensors can be used to collect the changes in acceleration and direction of the vehicle under test before and after the autonomous driving function under test is activated.

[0074] In an optional embodiment, in step S304, functional safety analysis is performed on the test data to obtain the functional safety level, including:

[0075] Step S341: Based on the preset scoring table corresponding to any type of response data, score any type of response data to obtain multiple score values;

[0076] Step S342: Perform a weighted summation of multiple rating values ​​to obtain the target rating value;

[0077] Step S343: Determine the functional safety level corresponding to the target score value based on the functional safety level mapping table.

[0078] As an optional implementation, when the autonomous driving function under test is the automatic emergency braking function and the target simulation test scenario is a "ghost pedestrian" scenario, the collected multi-type response data can include the braking time and braking distance of the vehicle under test. The braking time refers to the time required for the vehicle under test to come to a complete stop from the start of braking, and the braking distance refers to the distance traveled by the vehicle under test from the start of braking to a complete stop. Furthermore, the Automotive Safety Integrity Level (ASIL) of the automatic emergency braking function can be evaluated based on these multi-type responses. For example, multiple time intervals can be pre-divided and the braking time score value corresponding to each time interval can be determined, and multiple distance intervals can be pre-divided and the braking distance score value corresponding to each distance interval can be determined. Then, the braking time score value and the braking distance score value are weighted and summed to obtain the target score value of the automatic emergency braking function. Finally, the target score value is mapped to the corresponding functional safety level.

[0079] It should be noted that the ASIL levels, from lowest to highest, are: A, B, C, and D.

[0080] In an optional embodiment, the above-described vehicle fault simulation test method further includes:

[0081] Step S305: In response to the functional safety level being lower than the preset level limit, generate target prompt information based on test data;

[0082] Step S306: Provide functional safety prompts based on the target prompt information.

[0083] As an optional implementation, when the test determines that the current functional safety level of the autonomous driving function under test is low (e.g., below level B), in order to ensure the driving safety of the vehicle under test, a target prompt message containing the functional safety level can be generated based on the test data to prompt the vehicle user that there is an autonomous driving function that affects driving safety.

[0084] In an optional embodiment, the response data includes at least the pose data of the vehicle under test, and the above-described vehicle fault simulation test method further includes:

[0085] Step S307: Update the initial simulation test scene using pose data.

[0086] The aforementioned pose data may include, but is not limited to: position data (the current position coordinates of the vehicle under test), attitude data (the current orientation and angle of the vehicle under test), velocity data (the linear velocity and angular velocity of the vehicle under test), acceleration data (linear acceleration and angular acceleration), and path data (the path that the vehicle under test has already traversed, the path it is currently on, and the path it will traverse).

[0087] In this embodiment of the invention, an initial simulation test scenario for the vehicle under test is first constructed. Fault information is added to at least a portion of the scenario data in the initial simulation test scenario to obtain a target simulation test scenario. The forward-facing camera of the vehicle under test is controlled to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test. Functional safety analysis is performed on the test data to obtain the functional safety level. By using a fault injection board to process the fault in the initial simulation test scenario constructed by the simulation software, the target simulation test scenario corresponding to the autonomous driving function under test is obtained. Then, the target simulation test scenario is injected into the forward-facing camera of the vehicle under test in the form of video. The target simulation test scenario is used to simulate the fault scenario when the vehicle is driving in real time to test the autonomous driving function of the vehicle. This achieves the purpose of testing vehicle functional scenarios through video fault injection, thereby improving the accuracy of vehicle functional scenario test results and solving the technical problem of low accuracy of test results in the existing vehicle functional scenario test methods.

[0088] In this embodiment, a vehicle fault simulation testing device is also provided. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, a "module" is a combination of software and / or hardware that can perform a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0089] Figure 7 This is a structural block diagram of a vehicle fault simulation testing device according to an embodiment of the present invention, such as... Figure 7 As shown, the device includes:

[0090] Module 701 is used to build the initial simulation test scenario for the vehicle under test;

[0091] Processing module 702 is used to perform fault processing on the initial simulation test scenario to obtain the target simulation test scenario;

[0092] Test module 703 is used to control the forward-facing camera of the vehicle under test to present a target simulation test scene, so as to test the autonomous driving function of the vehicle under test in the target simulation test scene and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test.

[0093] Analysis module 704 is used to perform functional safety analysis on test data to obtain the functional safety level.

[0094] Optionally, the initial simulation test scenario includes at least a vehicle model, a sensor model, and an environment model. The aforementioned construction module 701 is also used to: collect initial vehicle data and initial environment data of the vehicle under test, wherein the initial vehicle data includes at least: initial vehicle position, sensor position, and vehicle body data; establish a scene coordinate system based on the initial vehicle position; and in the scene coordinate system, construct a vehicle model based on the vehicle body data, construct a sensor model based on the sensor position, and construct an environment model based on the initial environment data.

[0095] Optionally, the processing module 702 is further configured to: determine the autonomous driving function to be tested of the vehicle under test; and add fault information to at least some scenario data according to the autonomous driving function to be tested to obtain a target simulation test scenario corresponding to the autonomous driving function to be tested, wherein the fault information is determined by the test requirements of the autonomous driving function to be tested.

[0096] Optionally, the test data includes at least multiple types of response data of the autonomous driving function under test. The test module 703 is also used to: acquire scene perception data of the vehicle under test for the target simulation test scenario; make plans and decisions based on the scene perception data to generate control commands for the autonomous driving function under test; execute the control commands to control the vehicle under test to activate the autonomous driving function under test; and collect multiple types of response data through multiple sensors during the operation of the autonomous driving function under test.

[0097] Optionally, the analysis module 704 is further configured to: score any type of response data according to a preset scoring table corresponding to any type of response data to obtain multiple score values; perform a weighted summation of the multiple score values ​​to obtain a target score value; and determine the functional safety level corresponding to the target score value based on a functional safety level mapping table.

[0098] Optionally, the above-mentioned vehicle fault simulation test device further includes: a prompting module 705 (not shown in the figure), used to generate target prompting information based on test data in response to the functional safety level being lower than the preset level limit; and to provide functional safety prompting based on the target prompting information.

[0099] Optionally, the response data includes at least the pose data of the vehicle under test. The vehicle fault simulation test device also includes an update module 706 (not shown in the figure), which is used to update the initial simulation test scene using the pose data.

[0100] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0101] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the vehicle fault simulation test method of any of the foregoing.

[0102] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform any of the aforementioned vehicle fault simulation test methods.

[0103] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0104] Step S1: Construct the initial simulation test scenario for the vehicle under test;

[0105] Step S2: Add fault information to at least a portion of the scenario data of the initial simulation test scenario to obtain the target simulation test scenario;

[0106] Step S3: Control the forward-facing camera of the vehicle under test to present the target simulation test scene, so as to test the autonomous driving function of the vehicle under test in the target simulation test scene and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test.

[0107] Step S4: Perform functional safety analysis on the test data to obtain the functional safety level.

[0108] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0109] According to another aspect of the present invention, a vehicle is also provided, including an on-board memory and an on-board processor, wherein the on-board memory stores a computer program, and the on-board processor is configured to run the computer program to execute the vehicle fault simulation test method described in any of the foregoing embodiments.

[0110] Optionally, in this embodiment, the on-board processor can be configured to perform the following steps via a computer program:

[0111] Step S1: Construct the initial simulation test scenario for the vehicle under test;

[0112] Step S2: Add fault information to at least a portion of the scenario data of the initial simulation test scenario to obtain the target simulation test scenario;

[0113] Step S3: Control the forward-facing camera of the vehicle under test to present the target simulation test scene, so as to test the autonomous driving function of the vehicle under test in the target simulation test scene and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test.

[0114] Step S4: Perform functional safety analysis on the test data to obtain the functional safety level.

[0115] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and their optional implementations, which will not be repeated here.

[0116] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0117] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0118] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection can be through some interfaces; the indirect coupling or communication connection of units or modules can be electrical or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0121] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0122] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A vehicle fault simulation testing system, characterized in that, include: Simulation software is used to construct an initial simulation test scenario for the vehicle under test, wherein the initial simulation test scenario includes at least a vehicle model, a sensor model, and an environment model; The simulation software is also used to collect initial vehicle data and initial environment data of the vehicle under test, wherein the initial vehicle data includes at least: initial vehicle position and vehicle body data; determine the ground projection point of the rear axle midpoint of the vehicle based on the initial vehicle position, and establish a scene coordinate system with the ground projection point as the origin; in the scene coordinate system, construct the vehicle model based on the vehicle body data, construct the sensor model based on the sensor positions, and construct the environment model based on the initial environment data, wherein the sensor positions are the coordinates of each of the multiple sensors of the vehicle under test relative to the ground projection point; A fault injection board is used to add fault information to at least a portion of the scenario data in the initial simulation test scenario to obtain the target simulation test scenario. A control device is used to control the forward-facing camera of the vehicle under test to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test, and the test data includes at least the multi-type response data of the autonomous driving function under test. An analysis device is used to perform functional safety analysis on the test data to obtain the functional safety level; The response data includes at least the pose data of the vehicle under test. The vehicle fault simulation test system is also used to update the initial simulation test scenario using the pose data.

2. A vehicle fault simulation test method, characterized in that, include: Construct an initial simulation test scenario for the vehicle under test, wherein the initial simulation test scenario includes at least a vehicle model, a sensor model, and an environment model; The initial simulation test scenario for the vehicle under test includes: collecting initial vehicle data and initial environment data of the vehicle under test, wherein the initial vehicle data includes at least: initial vehicle position and vehicle body data; determining the ground projection point of the midpoint of the rear axle of the vehicle based on the initial vehicle position, and establishing a scene coordinate system with the ground projection point as the origin; in the scene coordinate system, constructing the vehicle model based on the vehicle body data, constructing the sensor model based on the sensor positions, and constructing the environment model based on the initial environment data, wherein the sensor positions are the coordinates of each of the multiple sensors of the vehicle under test relative to the ground projection point; Fault information is added to at least a portion of the scenario data in the initial simulation test scenario to obtain the target simulation test scenario; The forward-facing camera of the vehicle under test is controlled to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test, and the test data includes at least the multi-type response data of the autonomous driving function under test. Perform functional safety analysis on the test data to obtain the functional safety level; The response data includes at least the pose data of the vehicle under test, and the vehicle fault simulation test method further includes: updating the initial simulation test scenario using the pose data.

3. The vehicle fault simulation test method according to claim 2, characterized in that, Adding fault information to at least a portion of the scenario data in the initial simulation test scenario to obtain the target simulation test scenario includes: Determine the autonomous driving function to be tested for the vehicle under test; Based on the autonomous driving function under test, the fault information is added to at least a portion of the scene data to obtain the target simulation test scene corresponding to the autonomous driving function under test, wherein the fault information is determined by the test requirements of the autonomous driving function under test.

4. The vehicle fault simulation test method according to claim 2, characterized in that, The test data obtained by testing the autonomous driving function of the vehicle under test in the target simulation test scenario includes: Acquire scene perception data of the vehicle under test for the target simulation test scenario; Based on the scene perception data, planning and decision-making are performed to generate control commands for the autonomous driving function under test; Execute the control command to control the vehicle under test to activate the autonomous driving function under test; During the operation of the autonomous driving function under test, the various types of response data are collected by multiple sensors.

5. The vehicle fault simulation test method according to claim 4, characterized in that, Functional safety analysis is performed on the test data to obtain the functional safety level, which includes: Based on a preset scoring table corresponding to any type of response data, the response data of any type is scored to obtain multiple score values; The target score is obtained by weighted summation of the multiple score values. The functional safety level corresponding to the target score is determined based on the functional safety level mapping table.

6. The vehicle fault simulation test method according to claim 5, characterized in that, The vehicle fault simulation test method also includes: In response to the functional safety level being lower than a preset level limit, a target prompt message is generated based on the test data; Functional safety prompts are provided based on the target prompt information.

7. A vehicle fault simulation testing device, characterized in that, include: A construction module is used to construct an initial simulation test scenario for the vehicle under test, wherein the initial simulation test scenario includes at least a vehicle model, a sensor model, and an environment model; The construction module is further configured to collect initial vehicle data and initial environmental data of the vehicle under test, wherein the initial vehicle data includes at least: initial vehicle position and vehicle body data; determine the ground projection point of the rear axle midpoint of the vehicle based on the initial vehicle position, and establish a scene coordinate system with the ground projection point as the origin; in the scene coordinate system, construct the vehicle model based on the vehicle body data, construct the sensor model based on the sensor positions, and construct the environment model based on the initial environmental data, wherein the sensor positions are the coordinates of each of the multiple sensors of the vehicle under test relative to the ground projection point; The processing module is used to perform fault processing on the initial simulation test scenario to obtain the target simulation test scenario; The testing module is used to control the forward-facing camera of the vehicle under test to present the target simulation test scenario, so as to test the autonomous driving function of the vehicle under test under the target simulation test scenario and obtain test data. The test data is used to determine the functional safety level of the autonomous driving function under test, and the test data includes at least the multi-type response data of the autonomous driving function under test. The analysis module is used to perform functional safety analysis on the test data to obtain the functional safety level; The response data includes at least the pose data of the vehicle under test, and the device is further configured to update the initial simulation test scenario using the pose data.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle fault simulation test method according to any one of claims 2 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the vehicle fault simulation test method of any one of claims 2 to 6.

10. A vehicle, characterized in that, It includes an on-board memory and an on-board processor, wherein the on-board memory stores a computer program, and the on-board processor is configured to run the computer program to execute the vehicle fault simulation test method of any one of claims 2 to 6.

Images