Method and system for generating autonomous driving real vehicle test scenarios

Abstract

The present invention relates to the field of autonomous driving technology, and provides a method and system for generating an autonomous driving real vehicle test scene. The method includes: determining a set of focus units in an autonomous driving system deployed on a real vehicle according to the real vehicle test requirements; screening behavioral elements and environmental elements according to the set of focus units to obtain effective behavioral elements and effective environmental elements; combining effective behavioral elements and effective environmental elements under set scene constraints to obtain a real vehicle test scene; behavioral elements are constituent elements of the test scene, including type information and motion information of traffic participants; environmental elements are constituent elements of the test scene, including road information or weather information. The present invention enables the final real vehicle test scene to gather elements that have an impact on the focus units, thereby providing a good foundation for the efficiency of subsequent real vehicle tests.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and system for generating an autonomous driving real vehicle test scenario. Background Art

[0002] Autonomous driving, also known as unmanned driving, computer driving or wheeled mobile robot, is a cutting-edge technology that relies on computers and artificial intelligence technology to complete complete, safe and effective driving without human control.

[0003] However, autonomous driving also faces many challenges, such as bad weather, complex traffic conditions, etc., so its performance in some scenarios may not match that of human drivers. To solve this problem, more testing and iterative updates of the autonomous driving model are needed to improve its processing capabilities in complex scenarios.

[0004] Real vehicle testing is an effective means to improve the processing capabilities of autonomous driving in complex scenarios. However, real vehicle testing has the disadvantage of high testing costs because it involves factors such as vehicle scheduling and road / weather environment matching.

[0005] The existing autonomous driving real-car test scenario generation is usually designed with reference to the scene set generation method of simulation testing. Although this type of test scenario set is rich in content and has a large number of scenes, it is limited by the cost of real-car testing and cannot match the real-car testing needs well, resulting in low efficiency of real-car testing.

[0006] Therefore, how to provide a more targeted and efficient autonomous driving vehicle testing method has become a technical problem that needs to be urgently solved in the industry. Summary of the invention

[0007] The present invention provides a method and system for generating an autonomous driving real vehicle test scenario, so as to solve the defect of poor matching between the test scenario and the real vehicle test requirements in the prior art, and realize more targeted and efficient autonomous driving real vehicle testing.

[0008] The present invention provides a method for generating an automatic driving real vehicle test scene, comprising:

[0009] According to the actual vehicle test requirements, determining a set of focus units in the automatic driving system deployed on the actual vehicle;

[0010] According to the set of attention units, the behavior elements and the environment elements are respectively screened to obtain effective behavior elements and effective environment elements;

[0011] Under the set scenario constraints, the effective behavior elements and the effective environment elements are combined to obtain a real vehicle test scenario;

[0012] The behavior elements are components of the test scene, including type information and movement information of traffic participants; the environment elements are components of the test scene, including road information or weather information.

[0013] According to a method for generating a test scenario for an autonomous driving vehicle provided by the present invention, the step of screening the behavior elements according to the set of focus units to obtain valid behavior elements comprises:

[0014] Determine the behavior attributes corresponding one-to-one to the set of behavior elements;

[0015] Determining that there is an intersection between the interaction unit set in the behavior attribute and the focus unit set, outputting the behavior element set corresponding to the behavior attribute as a valid behavior element;

[0016] The interaction unit is a component unit of the automatic driving system.

[0017] According to a method for generating a test scene for an autonomous driving vehicle provided by the present invention, the step of screening environmental elements according to the set of focus units to obtain effective environmental elements comprises:

[0018] Acquire environmental attributes corresponding to the environmental elements one by one;

[0019] Determining that there is an intersection between the interactive unit set in the environmental attribute and the focus unit set, outputting the environmental element corresponding to the environmental attribute as a valid environmental element;

[0020] The interaction unit is a component unit of the automatic driving system.

[0021] According to a method for generating an autonomous driving real vehicle test scenario provided by the present invention, the step of combining the effective behavior elements and the effective environment elements under the set scenario constraints to obtain the real vehicle test scenario includes:

[0022] Select at least one valid environment element to form an environment part of a real vehicle test scene that satisfies the set scene constraints together with the supplementary environment element, and use the valid behavior element as the behavior part of the real vehicle test scene;

[0023] A real vehicle test scenario is obtained according to the real vehicle test scenario environment part and the real vehicle test scenario behavior part.

[0024] According to a method for generating a real-car test scenario for autonomous driving provided by the present invention, the scenario constraint includes an environmental part constraint; the environmental part constraint means that the environmental part of the real-car test scenario is composed of an environmental element of a load type, an environmental element of a road attribute type, an environmental element of a road curvature type, an environmental element of a weather type, and an environmental element of a lighting type;

[0025] The supplementary environmental elements refer to environmental elements whose load type is full load, environmental elements whose road attribute type is expressway, environmental elements whose road curvature type is straight road, environmental elements whose weather type is sunny day or environmental elements whose illumination type is daytime.

[0026] According to a method for generating an autonomous driving real vehicle test scenario provided by the present invention, the step of obtaining the real vehicle test scenario according to the real vehicle test scenario environment part and the real vehicle test scenario behavior part comprises:

[0027] Traversing and combining the real vehicle test scenario environment part and the vehicle test scenario behavior part to obtain a plurality of unassigned real vehicle test scenarios;

[0028] Parameter extension and assignment are performed on the unassigned real vehicle test scenarios at set intervals to obtain a real vehicle test scenario set.

[0029] The present invention also provides an automatic driving real vehicle test scene generation system, comprising:

[0030] A focus module, used to determine a focus unit set in the autonomous driving system deployed on the actual vehicle according to the actual vehicle test requirements;

[0031] A valid module, used to screen the behavior elements and the environment elements according to the focus unit set to obtain valid behavior elements and valid environment elements;

[0032] A generation module, used to combine the effective behavior elements and the effective environment elements under the set scenario constraints to obtain a real vehicle test scenario;

[0033] The behavior elements are components of the test scene, including type information and movement information of traffic participants; the environment elements are components of the test scene, including road information or weather information.

[0034] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-described methods for generating a real-vehicle test scenario for an autonomous driving vehicle are implemented.

[0035] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described methods for generating a real-vehicle test scenario for an autonomous driving vehicle.

[0036] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned methods for generating a real-vehicle test scenario for autonomous driving.

[0037] The method and system for generating an actual vehicle test scenario for autonomous driving provided by the present invention determine a focus unit based on actual vehicle test requirements, and screen the behavioral elements and environmental elements that constitute the test scenario based on the focus unit to obtain effective behavioral elements and effective environmental elements that can effectively influence the focus unit, so that the final actual vehicle test scenario brings together elements that have an impact on the focus unit, thereby providing a good foundation for the efficiency of subsequent actual vehicle tests. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 It is a flowchart of the method for generating a real vehicle test scenario for autonomous driving provided by the present invention;

[0040] Figure 2 is a schematic diagram of a scene generation process provided by an embodiment of the present invention;

[0041] Figure 3 It is a structural schematic diagram of the automatic driving real vehicle test scenario generation system provided by the present invention;

[0042] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention.

[0043] Reference numerals:

[0044] 1: Focus module; 2: Valid module; 3: Generate module;

[0045] 410: processor; 420: communication interface; 430: memory;

[0046] 440: Communication bus. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Combine the following Figure 1-Figure 2The present invention describes the method for generating a real-vehicle test scenario for autonomous driving.

[0049] like Figure 1 As shown, an embodiment of the present invention provides a method for generating a real-vehicle test scenario for an autonomous driving vehicle, comprising:

[0050] Step 102, determining a set of focus units in the autonomous driving system deployed on the actual vehicle according to the actual vehicle test requirements;

[0051] Step 104, filtering the behavior elements and the environment elements according to the focus unit set to obtain valid behavior elements and valid environment elements;

[0052] Step 106, under the set scenario constraints, combining the valid behavior elements and the valid environment elements to obtain a real vehicle test scenario;

[0053] The behavior elements are components of the test scene, including type information and movement information of traffic participants; the environment elements are components of the test scene, including road information or weather information.

[0054] In this embodiment, the behavior element is a scene dynamic behavior constituent element related to the dynamic driving behavior DDT, wherein the type of traffic participants may be cars, trucks, etc., and the motion information of traffic participants may be position, speed, direction, acceleration, etc.

[0055] The environmental elements are scene static environment constituent elements related to an operating design domain (ODD).

[0056] It is worth noting that not all ODDs belong to environmental elements. The environmental elements in this embodiment mainly consider road information (such as tunnels, straight roads, curve curvature, slope curvature, etc.) and weather information (such as daytime, sunny days, no street lights, turning on car lights, etc.).

[0057] In a preferred embodiment, the autonomous driving system includes a perception unit (perception), a control unit (planning & control, PNC) and a positioning unit (loclization); in some other embodiments, the perception unit (perception), the control unit (planning & control) and the positioning unit (loclization) can be further subdivided into more specific functional units.

[0058] The beneficial effects of this embodiment are:

[0059] The focus unit is determined based on the actual vehicle test requirements, and the behavioral elements and environmental elements that constitute the test scenario are screened based on the focus unit to obtain effective behavioral elements and effective environmental elements that can effectively influence the focus unit. As a result, the final actual vehicle test scenario brings together the elements that have an impact on the focus unit, thereby providing a good foundation for the efficiency of subsequent actual vehicle testing.

[0060] like Figure 2 As shown, according to the above embodiment, in this embodiment:

[0061] The step of respectively screening the behavior elements and the environment elements according to the focus unit set to obtain valid behavior elements and valid environment elements comprises:

[0062] Step 1041, determining the behavior attributes corresponding to the behavior element set one by one;

[0063] Step 1042, determining that there is an intersection between the interaction unit set in the behavior attribute and the focus unit set, then outputting the behavior element set corresponding to the behavior attribute as a valid behavior element;

[0064] The interaction unit is a component unit of the automatic driving system.

[0065] Step 1043, obtaining environmental attributes corresponding to the environmental elements one by one;

[0066] Step 1044, determining that there is an intersection between the interactive unit set in the environmental attribute and the focus unit set, then outputting the environmental element corresponding to the environmental attribute as a valid environmental element;

[0067] The interaction unit is a component unit of the automatic driving system.

[0068] In a preferred embodiment, in steps 1042 and 1044, the focus unit set is a subset of the interaction unit set.

[0069] The step of combining the effective behavior elements and the effective environment elements under the set scenario constraints to obtain a real vehicle test scenario includes:

[0070] Step 1061, selecting at least one valid environment element to form an actual vehicle test scene environment part that meets the set scene constraints with the supplementary environment element, and using the valid behavior element as the actual vehicle test scene behavior part;

[0071] Step 1062, obtaining a real vehicle test scenario according to the real vehicle test scenario environment part and the real vehicle test scenario behavior part.

[0072] The step of obtaining the real vehicle test scenario according to the real vehicle test scenario environment part and the real vehicle test scenario behavior part comprises:

[0073] Step 10621, traverse and combine the real vehicle test scenario environment part and the vehicle test scenario behavior part to obtain multiple unassigned real vehicle test scenarios;

[0074] Step 10622, performing parameter expansion and assignment on the unassigned real vehicle test scenarios at set intervals to obtain a real vehicle test scenario set.

[0075] The scene constraint includes an environmental part constraint; the environmental part constraint means that the real vehicle test scene environmental part is composed of a load type environmental element, a road attribute type environmental element, a road curvature type environmental element, a weather type environmental element, and a lighting type environmental element;

[0076] The supplementary environmental elements refer to environmental elements whose load type is full load, environmental elements whose road attribute type is expressway, environmental elements whose road curvature type is straight road, environmental elements whose weather type is sunny day or environmental elements whose illumination type is daytime.

[0077] In a preferred embodiment, the execution result of step 1041 is as follows:

[0078]

[0079] In the table, Y means that the behavior element set can affect the unit, and a null value means that the behavior element set cannot affect the unit;

[0080] Assuming that the PNC unit is the only element in the set of units of interest, the result of executing step 1042 is:

[0081] The set of behavior elements numbered 1-8 is a valid behavior element.

[0082] The execution result of step 1043 is as follows:

[0083]

[0084] In the table, Y means that the environmental element can affect the unit, and a null value means that the environmental element cannot affect the unit;

[0085] Assuming that the PNC unit is the only element in the focus unit set, the execution result of step 1044 is:

[0086] Environmental elements such as no load, curves, slopes, and rainy days are effective environmental elements.

[0087] By executing step 1061, it can be obtained that the set of behavioral elements numbered 1-8 is 8 possibilities for the behavioral part of the actual vehicle test scenario; any combination of the four environmental elements of no-load, curve, ramp, and rainy day is 15 possibilities for the environmental part of the actual vehicle test scenario (4 single environmental elements, 6 dual environmental elements, 4 triple environmental elements, and 1 quadruple environmental element).

[0088] Execute step 10621 to arrange and combine the 8 possible real vehicle test scenario behavior parts and the 15 possible real vehicle test scenario environment parts to obtain 120 unassigned real vehicle test scenarios.

[0089] Execute step 10622 to assign values ​​to 120 unassigned real vehicle test scenarios according to the set parameter distribution (for example, fill in speed, light brightness, etc.).

[0090] It is worth noting that the behavioral elements, environmental elements and units of the autonomous driving system are not limited to the contents listed in the above table. The above table is only for illustrative purposes and does not constitute a limitation on the scope of protection of the present invention.

[0091] In addition, the assignment process of step 10622 also has assignment constraints; the assignment constraints are obtained based on the execution logic of the behavior element. For example, for the behavior element in which the target vehicle overtakes the host vehicle from the rear side and cuts in and slows down, its execution logic is:

[0092] The main vehicle is traveling at the speed limit k_hv_speed. The target vehicle is approaching the main vehicle from behind at a speed k_tv_speed01 in the adjacent lane k_side of the main vehicle. When the target vehicle exceeds the main vehicle k_dis, the target vehicle cuts in front of the main vehicle and decelerates from k_tv_acc to k_tv_speed02.

[0093] In order to complete the above execution logic, there must be restrictions on the speed, acceleration, and relative position of the target vehicle and the main vehicle, so that the target vehicle can successfully overtake the main vehicle, cut in, and retrieve. This restriction is an assignment constraint.

[0094] The beneficial effects of this embodiment are:

[0095] By using the intermediate variable of the impact of the test focus unit in the autonomous driving system, the behavioral elements and environmental elements in the test scenario construction are effectively linked, making the construction of the real vehicle scenario more targeted, improving the efficiency of the real vehicle test, and reducing the overall cost of the real vehicle test.

[0096] The following is a description of the autonomous driving real vehicle test scenario generation device provided by the present invention. The autonomous driving real vehicle test scenario generation device described below and the autonomous driving real vehicle test scenario generation method described above can be referenced to each other.

[0097] like Figure 3 As shown, an embodiment of the present invention further provides an automatic driving real vehicle test scenario generation system, comprising:

[0098] A focus module 1 is used to determine a focus unit set in the automatic driving system deployed on the actual vehicle according to the actual vehicle test requirements;

[0099] Validation module 2, used to screen the behavior elements and the environment elements according to the focus unit set to obtain valid behavior elements and valid environment elements;

[0100] A generation module 3 is used to combine the effective behavior elements and the effective environment elements under the set scenario constraints to obtain a real vehicle test scenario;

[0101] The behavior elements are components of the test scene, including type information and movement information of traffic participants; the environment elements are components of the test scene, including road information or weather information.

[0102] Furthermore, the effective module 2 includes:

[0103] A behavior attribute submodule, used to determine the behavior attributes corresponding one-to-one to the behavior element set;

[0104] The effective behavior submodule is used to determine that there is an intersection between the interaction unit set in the behavior attribute and the focus unit set, and then output the behavior element set corresponding to the behavior attribute as a valid behavior element;

[0105] An environmental attribute submodule, used to obtain environmental attributes corresponding to the environmental elements one by one;

[0106] The effective environment submodule is used to determine that there is an intersection between the interactive unit set in the environmental attribute and the focus unit set, and then output the environmental element corresponding to the environmental attribute as a valid environmental element;

[0107] The interaction unit is a component unit of the automatic driving system.

[0108] The generating module 3 comprises:

[0109] The first generation submodule is used to select at least one valid environment element to form a real vehicle test scene environment part that meets the set scene constraints with the supplementary environment element, and use the valid behavior element as the real vehicle test scene behavior part;

[0110] The second generation submodule is used to obtain the real vehicle test scenario according to the real vehicle test scenario environment part and the real vehicle test scenario behavior part.

[0111] The second generation submodule includes:

[0112] A traversal submodule, used for traversing and combining the real vehicle test scenario environment part and the vehicle test scenario behavior part to obtain a plurality of unassigned real vehicle test scenarios;

[0113] The assignment submodule is used to perform parameter expansion assignment on the unassigned real vehicle test scenarios at set intervals to obtain a real vehicle test scenario set.

[0114] The beneficial effects of this embodiment are:

[0115] The focus unit is determined based on the actual vehicle test requirements, and the behavioral elements and environmental elements that constitute the test scenario are screened based on the focus unit to obtain effective behavioral elements and effective environmental elements that can effectively influence the focus unit. As a result, the final actual vehicle test scenario brings together the elements that have an impact on the focus unit, thereby providing a good foundation for the efficiency of subsequent actual vehicle testing.

[0116] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the method for generating a test scene for an autonomous driving vehicle, the method comprising: determining a set of attention units in the autonomous driving system deployed on the vehicle according to the requirements of the vehicle test; filtering the behavior elements and the environment elements according to the set of attention units respectively to obtain valid behavior elements and valid environment elements; combining the valid behavior elements and the valid environment elements under the set scene constraints to obtain a vehicle test scene; the behavior elements are components of the test scene, including the type information and movement information of the traffic participants; the environment elements are components of the test scene, including road information or weather information.

[0117] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0118] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the autonomous driving real vehicle test scenario generation method provided by the above-mentioned methods, the method including: according to the actual vehicle test requirements, determining a set of focus units in the autonomous driving system deployed on the actual vehicle; according to the set of focus units, respectively screening behavior elements and environmental elements to obtain valid behavior elements and valid environmental elements; under the set scenario constraints, combining the valid behavior elements and valid environmental elements to obtain a real vehicle test scene; the behavior elements are constituent elements of the test scene, including type information and motion information of traffic participants; the environmental elements are constituent elements of the test scene, including road information or weather information.

[0119] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the autonomous driving real vehicle test scenario generation method provided by the above-mentioned methods, the method comprising: determining a set of focus units in the autonomous driving system deployed on the real vehicle according to the real vehicle test requirements; screening behavior elements and environmental elements according to the set of focus units to obtain valid behavior elements and valid environmental elements; under the set scenario constraints, combining the valid behavior elements and valid environmental elements to obtain a real vehicle test scenario; the behavior elements are constituent elements of the test scenario, including type information and motion information of traffic participants; the environmental elements are constituent elements of the test scenario, including road information or weather information.

[0120] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a test scenario for an autonomous driving vehicle, characterized in that: include: According to the actual vehicle test requirements, determining a set of focus units in the automatic driving system deployed on the actual vehicle; According to the set of attention units, the behavior elements and the environment elements are respectively screened to obtain effective behavior elements and effective environment elements; Under the set scenario constraints, the effective behavior elements and the effective environment elements are combined to obtain a real vehicle test scenario; The behavior element is a component element of the test scenario, including type information and movement information of the traffic participant; The environmental elements are components of the test scene, including road information or weather information.

2. The method for generating a real-car test scenario for autonomous driving according to claim 1, characterized in that: The step of screening the behavior elements according to the focus unit set to obtain valid behavior elements comprises: Determine the behavior attributes corresponding one-to-one to the set of behavior elements; Determining that there is an intersection between the interaction unit set in the behavior attribute and the focus unit set, outputting the behavior element set corresponding to the behavior attribute as a valid behavior element; The interaction unit is a component unit of the automatic driving system.

3. The method for generating a test scenario for an autonomous driving vehicle according to claim 1, characterized in that: The step of screening the environmental elements according to the focus unit set to obtain the valid environmental elements comprises: Acquire environmental attributes corresponding to the environmental elements one by one; Determining that there is an intersection between the interactive unit set in the environmental attribute and the focus unit set, outputting the environmental element corresponding to the environmental attribute as a valid environmental element; The interaction unit is a component unit of the automatic driving system.

4. The method for generating a real-car test scenario for autonomous driving according to claim 2, characterized in that: The step of combining the effective behavior elements and the effective environment elements under the set scenario constraints to obtain a real vehicle test scenario includes: Select at least one valid environment element to form an environment part of a real vehicle test scene that satisfies the set scene constraints together with the supplementary environment element, and use the valid behavior element as the behavior part of the real vehicle test scene; A real vehicle test scenario is obtained according to the real vehicle test scenario environment part and the real vehicle test scenario behavior part.

5. The method for generating a real-car test scenario for autonomous driving according to claim 4, characterized in that: The scene constraint includes an environmental part constraint; the environmental part constraint means that the real vehicle test scene environmental part is composed of a load type environmental element, a road attribute type environmental element, a road curvature type environmental element, a weather type environmental element, and a lighting type environmental element; The supplementary environmental elements refer to environmental elements whose load type is full load, environmental elements whose road attribute type is expressway, environmental elements whose road curvature type is straight road, environmental elements whose weather type is sunny day or environmental elements whose illumination type is daytime.

6. The method for generating a test scenario for an autonomous driving vehicle according to claim 4, characterized in that: The step of obtaining the real vehicle test scenario according to the real vehicle test scenario environment part and the real vehicle test scenario behavior part comprises: Traversing and combining the real vehicle test scenario environment part and the vehicle test scenario behavior part to obtain a plurality of unassigned real vehicle test scenarios; Parameter extension and assignment are performed on the unassigned real vehicle test scenarios at set intervals to obtain a real vehicle test scenario set.

7. A system for generating automatic driving real vehicle test scenarios, characterized in that: include: A focus module, used to determine a focus unit set in the autonomous driving system deployed on the actual vehicle according to the actual vehicle test requirements; A valid module, used to screen the behavior elements and the environment elements according to the focus unit set to obtain valid behavior elements and valid environment elements; A generation module, used to combine the effective behavior elements and the effective environment elements under the set scenario constraints to obtain a real vehicle test scenario; The behavior element is a component element of the test scenario, including type information and movement information of the traffic participant; The environmental elements are components of the test scene, including road information or weather information.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for generating an autonomous driving real vehicle test scenario as described in any one of claims 1 to 6 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for generating an autonomous driving real vehicle test scenario as described in any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for generating an autonomous driving real vehicle test scenario as described in any one of claims 1 to 6 are implemented.

Images