Autonomous driving simulation test method and system based on functional design document

Abstract

This invention relates to the field of autonomous driving technology, providing a method and system for autonomous driving simulation testing based on functional design documents. The method includes: sending a simulation test form to the cloud and receiving an intermediate simulation test scenario file returned from the cloud; the simulation test form is obtained by sequentially parsing and classifying requirement management information; the requirement management information is extracted from the functional design document; the intermediate simulation test scenario file is obtained by running a form processing tool based on the Django web framework, using the simulation test form as input; the form processing tool is deployed in the cloud; a simulation test scenario is generated based on the intermediate simulation test scenario file, and autonomous driving simulation testing is performed based on the simulation test scenario. The simulation test scenario obtained by this invention can comprehensively cover the requirement management information in the functional design document, better meet testing requirements, and eliminates the step of secondary selection of scenario sets based on requirements in existing scenario construction methods.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to an autonomous driving simulation testing method and system based on functional design documents. Background Technology

[0002] Before commercial application, autonomous or assisted driving systems require extensive testing. However, the complexity of test scenarios and the safety of personnel pose significant challenges to autonomous driving testing. Therefore, scenario-based simulation testing is essential for autonomous driving testing. Simulation testing primarily involves constructing various complex scenarios, including dangerous and difficult-to-reproduce scenarios, to achieve closed-loop simulation testing of autonomous driving perception, decision-making, planning, and control algorithms, thus addressing the issues of scenario complexity and personnel safety.

[0003] Currently, most autonomous driving test scenario definition methods still follow those of ADAS (Advanced Driving Assistance System), which focuses on defining scenarios that emphasize changes in driving behavior. This approach suffers from poor scenario matching with requirements and requires additional secondary screening before testing can be performed.

[0004] Therefore, how to provide a simulation test scenario generation method that better meets the testing needs for autonomous driving simulation testing has become a technical problem that the industry urgently needs to solve. Summary of the Invention

[0005] This invention provides an autonomous driving simulation testing method and system based on functional design documents, which solves the shortcomings of existing technologies such as poor matching between scenarios and requirements and the need for additional secondary screening before testing can be performed, and realizes the generation and testing of simulation test scenarios that are more in line with testing requirements.

[0006] This invention provides an autonomous driving simulation testing method based on functional design documents, comprising:

[0007] The simulation test form is sent to the cloud, and the intermediate simulation test scenario file is received from the cloud. The simulation test form is obtained by parsing and classifying the requirement management information in sequence. The requirement management information is extracted from the functional design document. The intermediate simulation test scenario file is obtained by running a form processing tool based on the Django Web framework with the simulation test form as input. The form processing tool is deployed in the cloud.

[0008] A simulation test scenario is generated based on the intermediate file of the simulation test scenario, and an autonomous driving simulation test is performed based on the simulation test scenario.

[0009] According to the present invention, an autonomous driving simulation testing method based on a functional design document is provided, wherein the simulation test form includes a test case table; the test cases in the test case table correspond one-to-one with the categorized requirement management information.

[0010] According to the present invention, an autonomous driving simulation testing method based on functional design documents is provided, wherein the test cases include test pass conditions, initial state of the master vehicle, motion target of the master vehicle, initial state of the interactive vehicle, motion target of the interactive vehicle, and corresponding requirement management information.

[0011] According to the present invention, an autonomous driving simulation testing method based on a functional design document is provided, wherein the simulation testing form further includes a functional definition table; the functional definition table includes categorized requirement management information and test cases corresponding one-to-one with the requirement management information.

[0012] According to the present invention, an autonomous driving simulation testing method based on a functional design document is provided, wherein the step of performing autonomous driving simulation testing based on the simulation test scenario includes:

[0013] If the simulation test scenario is determined to cover all the requirement management information in the function definition table, then an autonomous driving simulation test will be performed based on the simulation test scenario.

[0014] According to the present invention, an autonomous driving simulation testing method based on a functional design document is provided. The simulation test form further includes a simulation parameter table, which includes the parameter space of the test cases, the execution sequence of the master vehicle's actions, the execution sequence of the interactive vehicle's actions, road geometry variables, light intensity variables, and weather variables.

[0015] According to the present invention, an autonomous driving simulation testing method based on a functional design document is provided, wherein the master vehicle motion execution sequence includes master vehicle actions executed sequentially, and the master vehicle actions executed sequentially are capable of completing the master vehicle motion target; the interactive vehicle motion execution sequence includes interactive actions executed sequentially, and the interactive actions executed sequentially are capable of completing the interactive motion target.

[0016] According to the present invention, an autonomous driving simulation test method based on a functional design document is provided, wherein the parameter space of discrete parameters includes at least one discrete value of the parameter; and the parameter space of continuous parameters includes the parameter value range and step size.

[0017] According to the present invention, an autonomous driving simulation test method based on a functional design document is provided, wherein the simulation test form further includes a signal table; the signal table includes signal names and signal values ​​required to execute the test cases.

[0018] According to the autonomous driving simulation testing method based on functional design documents provided by the present invention, after the step of sending the simulation test form to the cloud, the method further includes:

[0019] Receive the simulation test scenario statistics returned by the cloud.

[0020] According to the present invention, an autonomous driving simulation testing method based on a functional design document further includes, after the step of performing autonomous driving simulation testing based on the simulation test scenario:

[0021] A test report is generated based on the statistical information of the simulation test scenario and the results of the autonomous driving simulation test.

[0022] This invention also provides an autonomous driving simulation testing system based on functional design documents, comprising:

[0023] The form processing module is used to send the simulation test form to the cloud and receive the simulation test scenario intermediate file returned by the cloud. The simulation test form is obtained by parsing and classifying the requirement management information in sequence. The requirement management information is extracted from the functional design document. The simulation test scenario intermediate file is obtained by running a form processing tool based on the Django Web framework with the simulation test form as input. The form processing tool is deployed in the cloud.

[0024] The simulation test module is used to generate a simulation test scenario based on the intermediate file of the simulation test scenario, and to perform autonomous driving simulation test based on the simulation test scenario; the simulation test scenario can cover the requirement management information.

[0025] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the autonomous driving simulation test method based on the functional design document described above.

[0026] 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 the autonomous driving simulation test method based on the functional design document as described above.

[0027] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the autonomous driving simulation test method based on functional design documents as described above.

[0028] The autonomous driving simulation testing method and system based on functional design documents provided by this invention obtains a simulation test form by parsing and classifying the requirement management information extracted from the functional design document, and further generates a simulation test scenario based on the simulation test form. This makes the final simulation test scenario fully cover the requirement management information in the functional design document, better meet the test requirements, and eliminate the step of secondary screening of scenario sets for requirements in existing scenario construction methods.

[0029] Meanwhile, since simulation testing requires a certain degree of facilitation, the analysis of simulation test scenarios is quite complex. By using cloud-deployed form processing tools to perform complex information processing, the efficiency of scenario generation can be improved while reducing the demand for local computing resources.

[0030] Furthermore, form processing tools based on the Django web framework can provide form processing services to users with different needs, and users do not need to pre-install an environment; they can enable cloud-based parsing functions by directly accessing a web link. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0032] Figure 1 This is one of the flowcharts of the autonomous driving simulation testing method based on functional design documents provided by the present invention;

[0033] Figure 2 This is the second flowchart of the autonomous driving simulation testing method based on functional design documents provided by the present invention;

[0034] Figure 3 This is a schematic diagram of the cloud-based parsing logic provided in an embodiment of the present invention;

[0035] Figure 4 This is a schematic diagram of the structure of the autonomous driving simulation test system based on functional design documents provided by the present invention;

[0036] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0037] Figure label:

[0038] 1: Form processing module;

[0039] 2: Simulation testing module;

[0040] 510: Processor;

[0041] 520: Communication interface;

[0042] 530: Memory;

[0043] 540: Communication bus. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0045] The following is combined with Figures 1-3 This invention describes an autonomous driving simulation testing method based on functional design documents.

[0046] like Figure 1 As shown, this embodiment of the invention provides an autonomous driving simulation testing method based on a functional design document, including:

[0047] Step 102: Send the simulation test form to the cloud and receive the intermediate simulation test scenario file returned by the cloud; the simulation test form is obtained by parsing and classifying the requirement management information in sequence; the requirement management information is extracted from the functional design document; the intermediate simulation test scenario file is obtained by running a form processing tool based on the Django Web framework with the simulation test form as input; the form processing tool is deployed in the cloud;

[0048] Step 104: Generate a simulation test scenario based on the intermediate file of the simulation test scenario, and perform an autonomous driving simulation test based on the simulation test scenario.

[0049] Figure 3 The cloud parsing logic of this embodiment is shown. That is, the execution main program of this embodiment includes three parts: a form generation program deployed locally, a form processing program (form processing tool) deployed in the cloud, and a simulation program (simulation tool) deployed locally.

[0050] The various parts of the executing program transmit data via a network.

[0051] It is worth noting that "local" is a concept relative to the cloud and should not be construed as a limitation on this embodiment. The form generation program and the simulation program deployed locally may be deployed on multiple local devices located in different geographical locations.

[0052] In step 102, the generation of intermediate files for simulation test scenarios (i.e., cases) is implemented based on the Django web framework; therefore, it can be understood that the form processing tool deployed in the cloud, in a preferred implementation, is a service provided by the developer, and the generation of simulation test forms and the execution of simulation tests can be performed by different users according to their actual needs.

[0053] The advantages of this implementation method are:

[0054] The developers deploy the algorithm in the cloud, and the parsing is completed there. Users do not need to pre-install any environment; they can enable the cloud-based parsing function by directly accessing a web link. The form processing tool supports both single-function and multi-function parsing.

[0055] The beneficial effects of this embodiment are as follows:

[0056] By parsing and classifying the requirement management information extracted from the functional design document, a simulation test form is obtained. Furthermore, a simulation test scenario is generated based on the simulation test form, so that the final simulation test scenario can fully cover the requirement management information in the functional design document, better meet the test requirements, and save the step of secondary screening of scenario sets for requirements in the existing scenario construction method.

[0057] Meanwhile, since simulation testing requires a certain degree of facilitation, the analysis of simulation test scenarios is quite complex. By using cloud-deployed form processing tools to perform complex information processing, the efficiency of scenario generation can be improved while reducing the demand for local computing resources.

[0058] Furthermore, form processing tools based on the Django web framework can provide form processing services to users with different needs, and users do not need to pre-install an environment; they can enable cloud-based parsing functions by directly accessing a web link.

[0059] According to the above embodiments, in this embodiment:

[0060] The steps for performing autonomous driving simulation testing based on the simulation test scenario include:

[0061] If the simulation test scenario is determined to cover all the requirement management information in the function definition table, then an autonomous driving simulation test will be performed based on the simulation test scenario.

[0062] After the step of sending the simulation test form to the cloud, the method further includes:

[0063] Receive the simulation test scenario statistics returned by the cloud.

[0064] After the step of performing autonomous driving simulation testing based on the simulation test scenario, the method further includes:

[0065] A test report is generated based on the statistical information of the simulation test scenario and the results of the autonomous driving simulation test.

[0066] like Figure 2 As shown, the complete process of this embodiment combined with the previous embodiment is as follows.

[0067] Step 1022: Send the simulation test form to the cloud and receive the intermediate simulation test scenario file returned by the cloud.

[0068] Step 1024: Receive the intermediate file of the simulation test scenario returned from the cloud;

[0069] Step 1026: Receive the simulation test scenario statistics returned by the cloud;

[0070] Step 1042: Generate a simulation test scenario based on the intermediate file of the simulation test scenario;

[0071] Step 1044: If the simulation test scenario is determined to cover all the demand management information in the demand management information table, then an autonomous driving simulation test is performed based on the simulation test scenario.

[0072] Step 106: Generate a test report based on the statistical information of the simulation test scenario and the results of the autonomous driving simulation test.

[0073] It is worth noting that the simulation test scenario statistics information can also be used by users to extract the number of logical scenarios in the scenario library, and to count the number of scenarios for different testing methods, such as the number of scenarios that can be achieved through automated simulation and the number of scenarios that need to be simulated manually.

[0074] The beneficial effects of this embodiment are as follows:

[0075] By using the simulation test scenario statistics returned from the cloud, obtained from the intermediate files of the simulation test scenario, and the results of the autonomous driving simulation test, test reports can be generated more efficiently.

[0076] Furthermore, the confirmation process in step 1044 further ensures that the simulation test scenario covers all requirement management information.

[0077] According to any of the above embodiments, in this embodiment:

[0078] The simulation test form includes a test case table, case_lib; the test cases in the test case table correspond one-to-one with the categorized requirements management information (RM).

[0079] The test cases include test pass conditions, initial state of the master vehicle, motion target of the master vehicle, initial state of the interactive vehicle, motion target of the interactive vehicle, and corresponding requirement management information.

[0080] The interactive vehicle mentioned here refers to the target vehicle (TV) in the ISO standard for autonomous driving.

[0081] In a preferred implementation, case_lib is the main body of the scenario definition section, which clarifies the test scenarios that each function needs to cover, the test execution, the pass conditions, and the correspondence with the functional requirements. Among them, the test scenarios are expressed in two ways: logical scenarios and parameter scenarios. The former focuses on a simple summary of the scenario, while the latter focuses on abstracting the parameters in the scenario.

[0082] `case_lib` is a collection of logical scenarios (i.e., test cases). `case_lib` is the cornerstone of parameter specification; the scenario parameterization of the simulation will be expanded and instantiated based on the descriptions in `case_lib`.

[0083] The simulation test form also includes a function definition table fd_lib; the function definition table includes categorized requirement management information and test cases that correspond one-to-one with the requirement management information.

[0084] In a preferred implementation, fd_lib is the system definition for the function (i.e., RM) and serves as one of the bases for scenario design. It includes the function definition number, function definition description, and associated scenario number. The purpose is to clarify the requirements and ensure that the test scenarios fully cover those requirements.

[0085] fd_lib expands the hundreds of functional design documents (FD) into functional design requirements (RMs). Each logical scenario corresponds to one RM requirement, and the product is tested later to see if it meets the development requirements.

[0086] The simulation test form also includes a simulation parameter table para_sim_lib, which includes the parameter space of the test cases, the main vehicle action execution sequence, the interactive vehicle action execution sequence, road geometry variables, light intensity variables, and weather variables.

[0087] The master vehicle motion execution sequence includes master vehicle actions executed sequentially, and the master vehicle actions executed sequentially can complete the master vehicle motion target; the interactive vehicle motion execution sequence includes interactive actions executed sequentially, and the interactive actions executed sequentially can complete the interactive motion target.

[0088] The parameter space of a discrete parameter includes at least one discrete value of the parameter; the parameter space of a continuous parameter includes the range of parameter values ​​and the step size.

[0089] In a preferred embodiment, `para_sim_lib` is used to define the parameters required for the simulation. To automate the subsequent import of parameters and generation of the simulation scenario, the scenario needs to be decomposed into several specific variables, and the parameters are concatenated using certain rules to generate the scenario. Simulation testing requirements differ from real-vehicle testing; it does not require high flexibility but demands comprehensive coverage. Therefore, the generation rules for `para_sim_lib` include:

[0090] Rule 1: Starting from the simulation tool VTD, including a complete set of 208 simulation parameters to meet the definition requirements of different functions and scenarios;

[0091] Rule 2: Based on the VTD process for building virtual scenes, define the initial state Init for the three objects: the main vehicle hv, the target vehicle tv1, and the target vehicle tv2. Action 1 describes action1, action 2 describes action2, action 3 describes action3, and action 4 describes action4.

[0092] Rule 3: The initial state (init) defines information such as vehicle type, initial speed, lane, vehicle orientation, and location. The action description (action) defines the action type, target speed, acceleration change, lane change direction, and lane change duration.

[0093] Rule 4: In addition to simulation parameter information, add road geometry variable roadGeo, light intensity variable illumination, and weather variable weather.

[0094] The introduction of rule 4 can effectively link the design runtime domain (ODD) and the simulation scenario.

[0095] Rule 5: Variable structure: "variable; unit; variable value or range; variable step size".

[0096] Rule 5 introduces expansion step information, which allows variables to be expanded in an iterative manner.

[0097] Therefore, it can be understood that through para_sim_lib, logical scenarios can combine ODD elements and parameter values ​​such as daytime, nighttime, no load, full load, straight road, and curve to form specific test cases for simulation.

[0098] The simulation test form also includes a signal table, signal_lib; the signal table includes the signal names and signal values ​​required to execute the test cases.

[0099] In a preferred embodiment, signal_lib is used to define test scenarios for signal types, listing the required signal names and signal values ​​for different scenarios, and then combining the action order in para_sim_lib to achieve sequential triggering of signals.

[0100] The following describes the autonomous driving simulation test system based on functional design documents provided by the present invention. The autonomous driving simulation test system based on functional design documents described below can be referred to in correspondence with the autonomous driving simulation test method based on functional design documents described above.

[0101] like Figure 4 As shown, this embodiment of the invention provides an autonomous driving simulation testing system based on a functional design document, comprising:

[0102] Form processing module 1 is used to send the simulation test form to the cloud and receive the simulation test scenario intermediate file returned by the cloud. The simulation test form is obtained by parsing and classifying the requirement management information in sequence. The requirement management information is extracted from the functional design document. The simulation test scenario intermediate file is obtained by running a form processing tool based on the Django Web framework with the simulation test form as input. The form processing tool is deployed in the cloud.

[0103] The simulation test module 2 is used to generate a simulation test scenario based on the intermediate file of the simulation test scenario, and to perform autonomous driving simulation test based on the simulation test scenario; the simulation test scenario can cover the requirement management information.

[0104] The simulation test form includes a test case table; the test cases in the test case table correspond one-to-one with the categorized requirements management information.

[0105] The test cases include test pass conditions, initial state of the master vehicle, motion target of the master vehicle, initial state of the interactive vehicle, motion target of the interactive vehicle, and corresponding requirement management information.

[0106] The simulation test form also includes a function definition table; the function definition table includes categorized requirement management information and test cases that correspond one-to-one with the requirement management information.

[0107] The simulation test form also includes a simulation parameter table, which includes the parameter space of the test cases, the main vehicle action execution sequence, the interactive vehicle action execution sequence, road geometry variables, light intensity variables, and weather variables.

[0108] The master vehicle motion execution sequence includes master vehicle actions executed sequentially, and the master vehicle actions executed sequentially can complete the master vehicle motion target; the interactive vehicle motion execution sequence includes interactive actions executed sequentially, and the interactive actions executed sequentially can complete the interactive motion target.

[0109] The parameter space of a discrete parameter includes at least one discrete value of the parameter; the parameter space of a continuous parameter includes the range of parameter values ​​and the step size.

[0110] The simulation test form also includes a signal table; the signal table includes the signal names and signal values ​​required to execute the test cases.

[0111] Furthermore, the simulation test module 2 includes:

[0112] The confirmation submodule is used to determine if the simulation test scenario covers all the requirement management information in the function definition table, and then to perform autonomous driving simulation testing based on the simulation test scenario.

[0113] The autonomous driving simulation testing system based on functional design documents also includes:

[0114] The statistics module is used to receive the simulation test scenario statistics returned by the cloud.

[0115] The test report module generates a test report based on the statistical information of the simulation test scenario and the results of the autonomous driving simulation test.

[0116] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, communications interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute an autonomous driving simulation test method based on a functional design document. This method includes: sending a simulation test form to the cloud and receiving an intermediate simulation test scenario file returned by the cloud; the simulation test form is obtained by sequentially parsing and classifying requirement management information; the requirement management information is extracted from the functional design document; the intermediate simulation test scenario file is obtained by running a form processing tool based on the Django web framework, using the simulation test form as input; the form processing tool is deployed in the cloud; a simulation test scenario is generated based on the intermediate simulation test scenario file, and an autonomous driving simulation test is executed based on the simulation test scenario.

[0117] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a 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, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] On the other hand, the present invention also provides a computer program product, which includes a computer program that 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 simulation testing method based on the functional design document provided by the above methods. The method includes: sending a simulation test form to the cloud and receiving a simulation test scenario intermediate file returned by the cloud; the simulation test form is obtained by sequentially parsing and classifying requirement management information; the requirement management information is extracted from the functional design document; the simulation test scenario intermediate file is obtained by running a form processing tool based on the Django Web framework with the simulation test form as input; the form processing tool is deployed in the cloud; generating a simulation test scenario based on the simulation test scenario intermediate file, and performing autonomous driving simulation testing based on the simulation test scenario.

[0119] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements an autonomous driving simulation testing method based on a functional design document provided by the above methods. This method includes: sending a simulation test form to a cloud, and receiving an intermediate simulation test scenario file returned by the cloud; the simulation test form is obtained by sequentially parsing and classifying requirement management information; the requirement management information is extracted from a functional design document; the intermediate simulation test scenario file is obtained by running a form processing tool based on the Django Web framework, using the simulation test form as input; the form processing tool is deployed in the cloud; generating a simulation test scenario based on the intermediate simulation test scenario file, and performing an autonomous driving simulation test based on the simulation test scenario.

[0120] The device embodiments described above are merely illustrative. 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 network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments 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, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An autonomous driving simulation testing method based on functional design documents, characterized in that, include: Send the simulation test form to the cloud and receive the intermediate file of the simulation test scenario returned by the cloud. The simulation test form is obtained by sequentially parsing and classifying the requirement management information; The requirement management information is extracted from the functional design document; the intermediate file of the simulation test scenario is obtained by running a form processing tool based on the Django Web framework, with the simulation test form as input. The form processing tool is deployed in the cloud; the simulation test form includes a test case table; the test cases in the test case table correspond one-to-one with the categorized requirement management information; A simulation test scenario is generated based on the intermediate file of the simulation test scenario, and an autonomous driving simulation test is performed based on the simulation test scenario; The simulation test form also includes a simulation parameter table, which includes the parameter space of the test cases, the main vehicle action execution sequence, the interactive vehicle action execution sequence, road geometry variables, light intensity variables, and weather variables. The simulation parameter table is used to define the parameters required for the simulation, decompose the scene into several specific variables, and realize the concatenation of parameters and the automatic import of parameters by establishing preset rules, and generate simulation scenes. The preset rules include: Rule 1: Starting from the simulation tool VTD, including a complete set of 208 simulation parameters to meet the definition requirements of different functions and scenarios; Rule 2: Based on the VTD virtual scene construction process, for the three objects, the main vehicle hv, the target vehicle tv1, and the target vehicle tv2, define the initial state Init, action 1 describes action1, action 2 describes action2, action 3 describes action3, and action 4 describes action4 respectively. Rule 3: The initial state (init) defines the vehicle type, initial speed, lane, vehicle orientation, and location information; the action description (action) defines the action type, target speed, acceleration change, lane change direction, and lane change duration. Rule 4: In addition to simulation parameter information, add road geometry variable roadGeo, light intensity variable illumination, and weather variable weather; The introduction of rule 4 connects the design runtime domain (ODD) and the simulation scenario; Rule 5: The variable structure is "variable; unit; variable value or range; variable step size".

2. The autonomous driving simulation testing method based on functional design documents according to claim 1, characterized in that, The test cases include test pass conditions, initial state of the master vehicle, motion target of the master vehicle, initial state of the interactive vehicle, motion target of the interactive vehicle, and corresponding requirement management information.

3. The autonomous driving simulation testing method based on functional design documents according to claim 1, characterized in that, The simulation test form also includes a function definition table; the function definition table includes categorized requirement management information and test cases that correspond one-to-one with the requirement management information.

4. The autonomous driving simulation testing method based on functional design documents according to claim 3, characterized in that, The steps for performing autonomous driving simulation testing based on the simulation test scenario include: If the simulation test scenario is determined to cover all the requirement management information in the function definition table, then an autonomous driving simulation test will be performed based on the simulation test scenario.

5. The autonomous driving simulation testing method based on functional design documents according to claim 2, characterized in that, The master vehicle action execution sequence includes master vehicle actions executed sequentially, and the master vehicle actions executed sequentially can complete the master vehicle motion target; the interactive vehicle action execution sequence includes interactive actions executed sequentially, and the interactive actions executed sequentially can complete the interactive vehicle motion target.

6. The autonomous driving simulation testing method based on functional design documents according to claim 1, characterized in that, The parameter space of a discrete parameter includes at least one discrete value of the parameter; the parameter space of a continuous parameter includes the range of parameter values ​​and the step size.

7. The autonomous driving simulation testing method based on functional design documents according to claim 1, characterized in that, The simulation test form also includes a signal table; the signal table includes the signal names and signal values ​​required to execute the test cases.

8. The autonomous driving simulation testing method based on functional design documents according to claim 1, characterized in that, After the step of sending the simulation test form to the cloud, the method further includes: Receive the simulation test scenario statistics returned by the cloud.

9. The autonomous driving simulation testing method based on functional design documents according to claim 8, characterized in that, After the step of performing autonomous driving simulation testing based on the simulation test scenario, the method further includes: A test report is generated based on the statistical information of the simulation test scenario and the results of the autonomous driving simulation test.

10. An autonomous driving simulation testing system based on functional design documents, characterized in that, include: The form processing module is used to send the simulation test form to the cloud and receive the intermediate simulation test scenario file returned by the cloud. The simulation test form is obtained by sequentially parsing and classifying the requirement management information; The requirement management information is extracted from the functional design document; the intermediate file of the simulation test scenario is obtained by running a form processing tool based on the Django Web framework, with the simulation test form as input. The form processing tool is deployed in the cloud; the simulation test form includes a test case table; the test cases in the test case table correspond one-to-one with the categorized requirement management information; The simulation testing module is used to generate a simulation testing scenario based on the intermediate file of the simulation testing scenario, and to perform autonomous driving simulation testing based on the simulation testing scenario; the simulation testing scenario can cover the requirement management information; The simulation test form also includes a simulation parameter table, which includes the parameter space of the test cases, the execution sequence of the main vehicle's actions, the execution sequence of the interactive vehicle's actions, road geometry variables, light intensity variables, and weather variables. The simulation parameter table is used to define the parameters required for the simulation, decompose the scene into several specific variables, and establish preset rules to achieve parameter concatenation and automated parameter import, and generate a simulation scene. The preset rules include: Rule 1: Starting from the simulation tool VTD, it includes a complete set of 208 simulation parameters to meet the definition requirements of different functions and scenarios; Rule 2: Based on the VTD's virtual scene construction process, for the three objects—main vehicle hv, target vehicle tv1, and target vehicle tv2—initial states Ini are defined respectively. t, Action 1 describes action1, Action 2 describes action2, Action 3 describes action3, Action 4 describes action4; Rule 3: The initial state init defines the vehicle type, initial speed, lane, vehicle orientation, and location information; the action description in action defines the action type, target speed, acceleration change, lane change direction, and lane change duration; Rule 4: In addition to simulation parameter information, additional road geometry variables roadGeo, illumination variables illumination, and weather variables weather are added; the introduction of rule 4 can connect the design runtime domain ODD and the simulation scenario; Rule 5: The variable structure is "variable; unit; variable value or range; variable step size".

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the autonomous driving simulation test method based on the functional design document as described in any one of claims 1 to 9.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the autonomous driving simulation test method based on the functional design document as described in any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the autonomous driving simulation test method based on the functional design document as described in any one of claims 1 to 9.

Images