Autonomous Driving Real Vehicle Testing Method and System Based on Functional Design Document

Abstract

The present invention relates to the field of autonomous driving technology, and provides an autonomous driving in-vehicle test method and system based on a functional design document. The method includes: constructing a logical scenario and parameter pairs, and adding at least one of the parameter pairs to the logical scenario; the parameter pairs include a corresponding execution variable and a road geometry variable; instantiating the parameter space of the logical scenario to obtain a set of in-vehicle test scenarios, and performing an autonomous driving in-vehicle test based on the set of in-vehicle test scenarios. The present invention sets a second execution variable according to the test execution result, so that the second execution variable set is a proper subset of the first execution variable set, effectively reducing the complexity of scenario definition. Based on this, the autonomous driving in-vehicle test can eliminate unnecessary repeated tests and achieve higher test efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and in particular, to a method and system for real vehicle testing of autonomous driving based on a functional design document. Background Art

[0002] Before commercial application, autonomous driving or assisted driving needs to undergo a large number of tests. However, the complexity of test scenarios and the safety of personnel pose great challenges to autonomous driving testing. Therefore, simulation testing based on a scenario library is the only way for autonomous driving testing. Simulation testing mainly realizes the closed-loop simulation testing of algorithms such as autonomous driving perception, decision-making and planning, and control by constructing various complex scenarios including dangerous and difficult-to-reproduce scenarios, solving the problems of scenario complexity and personnel safety.

[0003] Currently, most of the scenario definition methods for autonomous driving testing still follow the definition method in ADAS (Advanced Driving Assistance System), adopting a scenario definition that focuses on driving behavior changes. Each test case describes a single scenario, and the main body of the test cases for a type of scenario is the same, only the parameters are replaced.

[0004] There are tens of thousands of test scenarios that autonomous driving needs to solve. The above traditional scenario definition method has the following problems.

[0005] 1. Defining scenarios in units of test cases requires an overly large number of independent definitions;

[0006] 2. The expression of the same main body with different parameters under the same type of scenario is too repetitive.

[0007] Therefore, how to provide a more efficient and general method and system for real vehicle testing of autonomous driving has become a technical problem that urgently needs to be solved in the industry. Summary of the Invention

[0008] The present invention provides a method and system for real vehicle testing of autonomous driving based on a functional design document, to solve the defects of complex scenario definition and repetitive expression in the prior art, and realize more efficient and general real vehicle testing of autonomous driving.

[0009] The present invention provides a method for real vehicle testing of autonomous driving based on a functional design document, including:

[0010] Constructing a logical scenario and parameter pairs, and adding at least one of the parameter pairs to the logical scenario;

[0011] Instantiating the parameter space of the logical scenario to obtain a set of real vehicle test scenarios, and performing real vehicle testing of autonomous driving based on the set of real vehicle test scenarios;

[0012] The logical scenarios correspond one-to-one with the requirements management information; the requirements management information is extracted from the functional design document;

[0013] The parameter pairs include an execution variable and a road geometry variable that correspond one-to-one; the execution variable refers to the execution action parameters of the autonomous driving test vehicle; the road geometry variable refers to the road parameters of the autonomous driving in-vehicle test;

[0014] At least one parameter pair added to the logical scenario includes a first execution variable set and a second execution variable set; the execution variables in the first execution variable set all correspond one-to-one to a first road geometry variable; the execution variables in the second execution variable set all correspond one-to-one to a second road geometry variable; the second execution variable set is a proper subset of the first execution variable set, and the difference between the test execution results of the execution variables in the second execution variable set under the first road geometry variable and under the second road geometry variable satisfies a set first condition.

[0015] According to an autonomous driving in-vehicle test method based on a functional design document provided by the present invention, the step of instantiating the parameter space of the logical scenario to obtain a set of in-vehicle test scenarios includes:

[0016] Based on the first design operating domain element, instantiate the parameter space of the logical scenario to obtain a first scenario set;

[0017] Based on the second design operating domain element, instantiate the parameter space of the logical scenario to obtain a second scenario set, and use the union of the first scenario set and the second scenario set as the set of in-vehicle test scenarios;

[0018] The second scenario set is a proper subset of the first scenario set, and the difference between the test results of the in-vehicle test scenarios in the second scenario set combined with the first design operating domain element and the test results combined with the second design operating domain element satisfies a set second condition.

[0019] According to an autonomous driving in-vehicle test method based on a functional design document provided by the present invention, the first design operating domain element is the test vehicle type; the second design operating domain element is a test vehicle type different from the first design operating domain element.

[0020] According to an autonomous driving in-vehicle test method based on a functional design document provided by the present invention, the execution variable includes an execution variable name and an execution variable value; the road geometry variable includes a road geometry variable name and a road geometry variable value.

[0021] A method for real vehicle testing of autonomous driving based on a functional design document provided by the present invention, wherein the values of the execution variables are composed of discrete values of the execution variables; the values of the road geometric variables are composed of discrete values of the road geometric variables.

[0022] A method for real vehicle testing of autonomous driving based on a functional design document provided by the present invention, wherein the first road geometric variable is a straight road; the second road geometric variable is a curve or a ramp.

[0023] A method for real vehicle testing of autonomous driving based on a functional design document provided by the present invention, wherein the requirement management information is obtained by sequentially parsing and classifying after being extracted from the functional design document.

[0024] The present invention also provides a real vehicle testing system for autonomous driving based on a functional design document, comprising:

[0025] A construction module for constructing a logical scenario and parameter pairs, and adding at least one of the parameter pairs to the logical scenario;

[0026] An instance testing module for instantiating the parameter space of the logical scenario to obtain a set of real vehicle testing scenarios, and performing real vehicle testing of autonomous driving based on the set of real vehicle testing scenarios;

[0027] The logical scenario corresponds one-to-one with the requirement management information; the requirement management information is extracted from the functional design document;

[0028] The parameter pairs include a corresponding execution variable and a road geometric variable; the execution variable refers to the execution action parameter of the autonomous driving test vehicle; the road geometric variable refers to the road parameter of the real vehicle testing of autonomous driving;

[0029] At least one parameter pair added to the logical scenario includes a first execution variable set and a second execution variable set; the execution variables in the first execution variable set all correspond one-to-one to the first road geometric variable; the execution variables in the second execution variable set all correspond one-to-one to the second road geometric variable; the second execution variable set is a proper subset of the first execution variable set, and the difference between the test execution results of the execution variables in the second execution variable set under the first road geometric variable and under the second road geometric variable satisfies a set first condition.

[0030] A real vehicle testing system for autonomous driving based on a functional design document provided by the present invention, wherein the instance testing module includes:

[0031] A first scenario sub-module for instantiating the parameter space of the logical scenario based on the first design operation domain element to obtain a first scenario set;

[0032] The second scenario sub-module is used to instantiate the parameter space of the logic scenario based on the second design operation domain element to obtain a second scenario set, and use the union of the first scenario set and the second scenario set as the real vehicle test scenario set;

[0033] The second scenario set is a proper subset of the first scenario set, and the difference between the test results of the real vehicle test scenarios in the second scenario set combined with the first design operation domain element and the test results combined with the second design operation domain element satisfies a set second condition.

[0034] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned any one of the autonomous driving real vehicle test methods based on the functional design document are implemented.

[0035] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned any one of the autonomous driving real vehicle test methods based on the functional design document are implemented.

[0036] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the above-mentioned any one of the autonomous driving real vehicle test methods based on the functional design document are implemented.

[0037] The autonomous driving real vehicle test method and system based on the functional design document provided by the present invention set the second execution variable according to the test execution result, making the second execution variable set a proper subset of the first execution variable set, effectively reducing the complexity of scenario definition. Based on this, the autonomous driving real vehicle test can eliminate unnecessary repeated tests and achieve higher test efficiency. 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 will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 is one of the flow charts of the autonomous driving real vehicle test method based on the functional design document provided by the present invention;

[0040] Figure 2 is the second flow chart of the autonomous driving real vehicle test method based on the functional design document provided by the present invention;

[0041] Figure 3 It is a schematic diagram of the process for establishing a scenario library provided by an embodiment of the present invention;

[0042] Figure 4 It is a schematic diagram of the structure of an on-road autonomous driving test system based on a functional design document provided by the present invention;

[0043] Figure 5 It is a schematic diagram of the structure of an electronic device provided by the present invention.

[0044] Reference numerals:

[0045] 1: Construction module;

[0046] 2: Instance test module;

[0047] 510: Processor;

[0048] 520: Communication interface;

[0049] 530: Memory;

[0050] 540: Communication bus. Detailed implementation manners

[0051] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0052] The following combines Figures 1 - 3 to describe the on-road autonomous driving test method based on a functional design document of the present invention.

[0053] As Figure 1 shown, an embodiment of the present invention provides an on-road autonomous driving test method based on a functional design document, including:

[0054] Step 102, constructing logical scenarios and parameter pairs, and adding at least one of the parameter pairs to the logical scenarios;

[0055] Step 104, instantiating the parameter space of the logical scenarios to obtain a set of on-road test scenarios, and performing on-road autonomous driving tests based on the set of on-road test scenarios;

[0056] The logical scenarios correspond one-to-one with requirement management information; the requirement management information is extracted from a functional design document;

[0057] The parameter pairs include an execution variable and a road geometry variable that correspond one-to-one; the execution variable refers to the execution action parameter of the autonomous driving test vehicle; the road geometry variable refers to the road parameter of the real vehicle test of autonomous driving.

[0058] At least one parameter pair added to the logical scenario includes a first execution variable set and a second execution variable set; the execution variables in the first execution variable set all correspond one-to-one to a first road geometry variable; the execution variables in the second execution variable set all correspond one-to-one to a second road geometry variable; the second execution variable set is a proper subset of the first execution variable set, and the difference between the test execution results of the execution variables in the second execution variable set under the first road geometry variable and under the second road geometry variable satisfies a set first condition.

[0059] The execution subject of this embodiment is an autonomous driving real vehicle test program based on a functional design document.

[0060] In this embodiment, since the test execution results of some execution variables under the logical scenario based on the first road geometry variable are not much different from the test execution results under the logical scenario based on the second road geometry variable, reliable test results can be obtained by testing these execution variables with little difference only for the first road geometry variable or only for the second road geometry variable.

[0061] Traditional scenario definition methods do not consider this factor, but traverse all possible parameter combinations to obtain a scenario library with a huge number of scenarios. Although some of these scenarios can be selected for testing through screening in the subsequent actual test process, this solution not only increases the preparation steps of the actual test, but also may have the problem that the selected scenarios cannot comprehensively and reliably cover the test requirements.

[0062] In this embodiment, at the beginning of constructing the logical scenario in step 102, a logical scenario corresponding one-to-one to the requirements management information is defined. It should be noted that the logical scenario is a general scenario that does not include specific parameter values. In other words, the logical scenario corresponding to the requirements management information can generate multiple specific test scenarios (i.e., real vehicle test scenarios including specific parameter values, such as vehicle initial position, speed, acceleration, road curvature, weather visibility, etc.) through the instantiation of the parameter space.

[0063] The requirements management information (RM) is extracted from the functional design document (FD) document. That is, the initial input and constraints of the real vehicle test scenario set finally executed in this embodiment are the FD document, which ensures that the logical scenario / specific test scenario can meet the upstream requirements from the source.

[0064] In a preferred embodiment, the requirement management information is obtained by extracting from the functional design document and then parsing and classifying it in sequence.

[0065] In addition, since this embodiment introduces parameter pairs and defines the second set of execution variables and the first set of execution variables, unnecessary and duplicate specific scenarios are excluded during the process of generating multiple specific test scenarios from the logical scenario, and a more flexible and efficient set of on-road vehicle test scenarios is obtained.

[0066] Considering that the cost of on-road vehicle testing for autonomous driving is higher than that of simulation testing, adopting the more flexible and efficient set of on-road vehicle test scenarios of this embodiment can reduce the number of test scenarios and the testing cost on the basis of ensuring the reliability of the on-road vehicle test results.

[0067] The beneficial effects of this embodiment are as follows:

[0068] Set the second execution variable according to the test execution result, making the second set of execution variables a proper subset of the first set of execution variables, effectively reducing the complexity of scenario definition. Based on this, the on-road vehicle testing for autonomous driving can avoid unnecessary repeated testing and achieve higher testing efficiency.

[0069] According to the above embodiments, in this embodiment:

[0070] As Figure 2 shown, the steps of instantiating the parameter space of the logical scenario to obtain the set of on-road vehicle test scenarios include:

[0071] Step 1042, instantiate the parameter space of the logical scenario based on the first design operation domain element to obtain a first scenario set;

[0072] Step 1044, instantiate the parameter space of the logical scenario based on the second design operation domain element to obtain a second scenario set, and use the union of the first scenario set and the second scenario set as the set of on-road vehicle test scenarios;

[0073] The second scenario set is a proper subset of the first scenario set, and the difference between the test results of the on-road vehicle test scenarios in the second scenario set combined with the first design operation domain element and the test results combined with the second design operation domain element satisfies a set second condition.

[0074] Step 1046, perform on-road vehicle testing for autonomous driving based on the set of on-road vehicle test scenarios;

[0075] Based on the adjustment of the test ratio for road geometric variables in the above embodiment, this embodiment further adjusts the test ratio of the on-road vehicle test scenarios for a specific Operational Design Domain (ODD).

[0076] For the adjustment scheme of the test ratio, on the one hand, as described in this embodiment and the above embodiment, it can be adjusted through the difference in test results to obtain a more efficient set of on-road vehicle test scenarios; on the other hand, it can be based on the FD document and RM to obtain a more targeted set of on-road vehicle test scenarios.

[0077] The beneficial effects of this embodiment are as follows:

[0078] Through the adjustment of the test ratio, a more efficient and / or more targeted set of on-road vehicle test scenarios is obtained, thereby improving the efficiency and pertinence of the on-road vehicle test for autonomous driving.

[0079] According to any of the above embodiments, in this embodiment:

[0080] The first operational design domain element is the test vehicle type; the second operational design domain element is a test vehicle type different from the first operational design domain element.

[0081] For example, a specific scenario has been carefully tested under the target odd of a sedan, and only some targeted tests will be conducted under the target odd of a truck.

[0082] The first road geometric variable is a straight road; the second road geometric variable is a curve or a slope.

[0083] For example, a specific scenario has been carefully tested under the road geometric variable (roadGeo) of a straight road, and only some targeted tests will be conducted on a curve or a slope.

[0084] In a preferred implementation manner, the result output in step 102, that is, the logical scenario and the parameter pair are in the form of a form; the form generation part (such as the construction module) of the program can execute step 102 to obtain an on-road vehicle parameter form including the logical scenario and the parameter pair; the instantiation part of the program can execute the step of instantiating the parameter space of the logical scenario to obtain a set of on-road vehicle test scenarios; the test part of the program can execute the step of performing an on-road vehicle test for autonomous driving based on the set of on-road vehicle test scenarios.

[0085] In the on-road vehicle parameter form including the logical scenario and the parameter pair:

[0086] The execution variable includes an execution variable name and an execution variable value; the road geometric variable includes a road geometric variable name and a road geometric variable value.

[0087] The values of the execution variables consist of discrete values of the execution variables; the values of the road geometry variables consist of discrete values of the road geometry variables.

[0088] Furthermore, the real vehicle parameter form can be obtained based on the logical scenario table, that is, a logical scenario table is constructed according to the RM, and the parameter pairs are added to the appropriate positions in the logical scenario table to obtain the real vehicle parameter form.

[0089] Even further, the execution subjects of steps 102 and 104, that is, the form generation part, the instantiation part, and the test part of the program, can be deployed on different device ends. For example, in the scenario where the computing power of the local device is limited, the instantiation part of the program can be deployed in the cloud, the form generation part of the program can be deployed on the local computer, and the test part of the program can be deployed on the test vehicle, and data transmission between the various parts of the program is realized through network communication.

[0090] In a preferred embodiment, the real vehicle test scenario generation steps and the simulation scenario generation steps of this embodiment or the above embodiments can be integrated based on the following process to implement a test scenario generation scheme that can communicate with each other.

[0091] S1. Scenario definition stage.

[0092] After obtaining the RM by parsing the FD document, the logical scenario definition, scenario parameterization, test execution description, test evaluation setting, and function requirement correspondence steps are sequentially executed with the RM as the input to obtain the logical scenario form case_lib.

[0093] S2. Parameter definition stage.

[0094] Based on the logical scenario form case_lib, the real vehicle test parameter setting (i.e., the scheme given in any of the above embodiments), the simulation test parameter setting, and the simulation signal sorting steps are respectively executed to obtain the real vehicle parameter form para_veh_lib, the simulation parameter form para_sim_lib, and the signal form signal_lib.

[0095] S3. Automatic generation stage.

[0096] Generate test cases that can be used for real vehicles based on the real vehicle parameter form para_veh_lib;

[0097] Generate test cases that can be used for simulation based on the simulation parameter form para_sim_lib and the signal form signal_lib.

[0098] The beneficial effects of this embodiment are as follows:

[0099] 1. By conducting targeted tests on road geometric variables and ODD, the number of repetitions of on-road vehicle tests is reduced, and the test efficiency is improved.

[0100] 2. Variables based on discrete values can further reduce the number of repetitions of on-road vehicle tests and improve the test efficiency.

[0101] 3. By deploying the program at different locations, the requirements for local device computing power are reduced, and the flexibility of on-road vehicle tests is increased.

[0102] 4. By expanding the form, a test scenario generation method compatible with simulation and on-road vehicle tests is provided, enabling the parsing processes of FD and RM to be effectively utilized in both the simulation and on-road vehicle test scenario generation steps.

[0103] The following describes the on-road vehicle test device for autonomous driving based on a functional design document provided by the present invention. The on-road vehicle test device for autonomous driving based on a functional design document described below can be mutually referred to and corresponding to the on-road vehicle test method for autonomous driving based on a functional design document described above.

[0104] As Figure 4 shown, an embodiment of the present invention provides an on-road vehicle test system for autonomous driving based on a functional design document, including:

[0105] A construction module 1, configured to construct a logical scenario and parameter pairs, and add at least one of the parameter pairs to the logical scenario;

[0106] An instance test module 2, configured to instantiate the parameter space of the logical scenario to obtain a set of on-road vehicle test scenarios, and perform on-road vehicle tests for autonomous driving based on the set of on-road vehicle test scenarios;

[0107] The logical scenario corresponds one-to-one to requirement management information; the requirement management information is extracted from a functional design document;

[0108] The parameter pair includes a corresponding execution variable and a road geometric variable; the execution variable refers to the execution action parameter of an autonomous driving test vehicle; the road geometric variable refers to the road parameter of an on-road vehicle test for autonomous driving;

[0109] At least one parameter pair added to the logical scenario includes a first execution variable set and a second execution variable set; the execution variables in the first execution variable set all correspond one-to-one to a first road geometric variable; the execution variables in the second execution variable set all correspond one-to-one to a second road geometric variable; the second execution variable set is a proper subset of the first execution variable set, and the difference between the test execution results of the execution variables in the second execution variable set under the first road geometric variable and under the second road geometric variable satisfies a set first condition.

[0110] The example test module 2 includes:

[0111] A first scenario sub-module, configured to instantiate a parameter space of the logic scenario based on a first design operating domain element, so as to obtain a first scenario set;

[0112] A second scenario sub-module, configured to instantiate a parameter space of the logic scenario based on a second design operating domain element, so as to obtain a second scenario set, and use a union of the first scenario set and the second scenario set as a real vehicle test scenario set;

[0113] The second scenario set is a proper subset of the first scenario set, and a difference between a test result of a real vehicle test scenario in the second scenario set in combination with the first design operating domain element and a test result in combination with the second design operating domain element satisfies a set second condition.

[0114] The first design operating domain element is a test vehicle type; the second design operating domain element is a test vehicle type different from the first design operating domain element.

[0115] The execution variable includes an execution variable name and an execution variable value; the road geometry variable includes a road geometry variable name and a road geometry variable value.

[0116] The execution variable value is composed of execution variable discrete values; the road geometry variable value is composed of road geometry variable discrete values.

[0117] The first road geometry variable is a straight road; the second road geometry variable is a curve or a slope.

[0118] The requirement management information is obtained by extracting from a functional design document and then parsing and classifying it in sequence.

[0119] Figure 5 An entity structure diagram of an electronic device is exemplified, as shown in Figure 5As shown in the figure, the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communications interface 520, and the memory 530 complete communication with each other through the communication bus 540. The processor 510 may call the logical instructions in the memory 530 to execute the real vehicle test method for autonomous driving based on the functional design document. The method includes: constructing a logical scenario and parameter pairs, and adding at least one of the parameter pairs to the logical scenario; instantiating the parameter space of the logical scenario to obtain a set of real vehicle test scenarios, and performing a real vehicle test for autonomous driving based on the set of real vehicle test scenarios; the logical scenario corresponds one-to-one with the requirement management information; the requirement management information is extracted from the functional design document; the parameter pair includes a corresponding execution variable and a road geometry variable; the execution variable refers to the execution action parameter of the autonomous driving test vehicle; the road geometry variable refers to the road parameter of the real vehicle test for autonomous driving; the at least one parameter pair added to the logical scenario includes a first set of execution variables and a second set of execution variables; the execution variables in the first set of execution variables all correspond one-to-one to the first road geometry variable; the execution variables in the second set of execution variables all correspond one-to-one to the second road geometry variable; the second set of execution variables is a proper subset of the first set of execution variables, and the difference between the test execution results of the execution variables in the second set of execution variables under the first road geometry variable and under the second road geometry variable satisfies a set first condition.

[0120] In addition, when the logical instructions in the above-mentioned memory 530 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a 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 such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0121] 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 method for real vehicle testing of autonomous driving based on a functional design document provided by each of the above methods. The method includes: constructing a logical scenario and parameter pairs, and adding at least one of the parameter pairs to the logical scenario; instantiating the parameter space of the logical scenario to obtain a set of real vehicle test scenarios, and performing real vehicle testing of autonomous driving based on the set of real vehicle test scenarios; the logical scenario corresponds one-to-one with requirement management information; the requirement management information is extracted from the functional design document; the parameter pair includes a corresponding execution variable and a road geometry variable; the execution variable refers to the execution action parameter of the autonomous driving test vehicle; the road geometry variable refers to the road parameter of the real vehicle testing of autonomous driving; at least one parameter pair added to the logical scenario includes a first execution variable set and a second execution variable set; the execution variables in the first execution variable set all correspond one-to-one to a first road geometry variable; the execution variables in the second execution variable set all correspond one-to-one to a second road geometry variable; the second execution variable set is a proper subset of the first execution variable set, and the difference between the test execution results of the execution variables in the second execution variable set under the first road geometry variable and under the second road geometry variable satisfies a set first condition.

[0122] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements an on-road autonomous driving test method based on a functional design document provided by the above-mentioned various methods. The method includes: constructing a logical scenario and parameter pairs, and adding at least one of the parameter pairs to the logical scenario; instantiating a parameter space of the logical scenario to obtain a set of on-road test scenarios, and performing an on-road autonomous driving test based on the set of on-road test scenarios; the logical scenario corresponds one-to-one with requirement management information; the requirement management information is extracted from the functional design document; the parameter pair includes a corresponding execution variable and a road geometry variable; the execution variable refers to an execution action parameter of an autonomous driving test vehicle; the road geometry variable refers to a road parameter of an on-road autonomous driving test; at least one parameter pair added to the logical scenario includes a first execution variable set and a second execution variable set; the execution variables in the first execution variable set all correspond one-to-one to a first road geometry variable; the execution variables in the second execution variable set all correspond one-to-one to a second road geometry variable; the second execution variable set is a proper subset of the first execution variable set, and the difference between the test execution results of the execution variables in the second execution variable set under the first road geometry variable and under the second road geometry variable satisfies a set first condition.

[0123] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0124] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment 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 such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which may 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.

[0125] 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 foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for real vehicle testing of autonomous driving based on a functional design document, characterized in that, Including: Construct logical scenarios and parameter pairs, and select at least one of the parameter pairs and add it to the logical scenario; Instantiate the parameter space of the logical scenario to obtain a set of real vehicle test scenarios, and perform an autonomous driving real vehicle test based on the set of real vehicle test scenarios; The logical scenarios correspond one-to-one with the requirement management information; the requirement management information is extracted from the functional design document; The parameter pair includes a corresponding execution variable and a road geometry variable; The execution variable refers to the execution action parameter of the autonomous driving test vehicle; the road geometry variable refers to the road parameter of the autonomous driving real vehicle test; At least one parameter pair added to the logical scenario includes a first execution variable set and a second execution variable set; the execution variables in the first execution variable set all correspond one-to-one to a first road geometry variable; the execution variables in the second execution variable set all correspond one-to-one to a second road geometry variable; the second execution variable set is a proper subset of the first execution variable set, and the difference between the test execution results of the execution variables in the second execution variable set under the first road geometry variable and the test execution results under the second road geometry variable satisfies a set first condition.

2. The method for real vehicle testing of autonomous driving based on a functional design document according to claim 1, characterized in that, The step of instantiating the parameter space of the logical scenario to obtain a set of real vehicle test scenarios includes: Based on the first design operating domain element, instantiate the parameter space of the logical scenario to obtain a first scenario set; Based on the second design operating domain element, instantiate the parameter space of the logical scenario to obtain a second scenario set, and use the union of the first scenario set and the second scenario set as the set of real vehicle test scenarios; The second scenario set is a proper subset of the first scenario set, and the difference between the test results of the real vehicle test scenarios in the second scenario set combined with the first design operating domain element and the test results combined with the second design operating domain element satisfies a set second condition.

3. The method for real vehicle testing of autonomous driving based on a functional design document according to claim 2, wherein The first design operating domain element is the test vehicle type; the second design operating domain element is a test vehicle type different from the first design operating domain element.

4. The method for real vehicle testing of autonomous driving based on a functional design document according to claim 1, characterized in that, The execution variable includes an execution variable name and an execution variable value; the road geometry variable includes a road geometry variable name and a road geometry variable value.

5. The method for actual vehicle testing of autonomous driving based on a functional design document according to claim 4, wherein, The execution variable value consists of execution variable discrete values; the road geometry variable value consists of road geometry variable discrete values.

6. The method for real vehicle testing of autonomous driving based on a functional design document according to claim 1, characterized in that The first road geometry variable is a straight road; the second road geometry variable is a curve or a slope.

7. The method for real vehicle testing of autonomous driving based on a functional design document according to claim 1, wherein The requirement management information is obtained by sequentially parsing and classifying after being extracted from the functional design document.

8. An on-vehicle test system for autonomous driving based on a functional design document, characterized in that, Including: A construction module for constructing logical scenarios and parameter pairs, and adding at least one of the parameter pairs to the logical scenario; An instance test module for instantiating the parameter space of the logical scenario to obtain a set of real vehicle test scenarios, and performing an autonomous driving real vehicle test based on the set of real vehicle test scenarios; The logical scenarios correspond one-to-one with the requirement management information; the requirement management information is extracted from the functional design document; The parameter pair includes a corresponding execution variable and a road geometry variable; The execution variable refers to the execution action parameters of the autonomous driving test vehicle; the road geometry variable refers to the road parameters of the real vehicle test of autonomous driving; At least one parameter pair added to the logical scenario includes a first execution variable set and a second execution variable set; the execution variables in the first execution variable set all correspond one-to-one to the first road geometry variable; the execution variables in the second execution variable set all correspond one-to-one to the second road geometry variable; the second execution variable set is a proper subset of the first execution variable set, and the difference between the test execution results of the execution variables in the second execution variable set under the first road geometry variable and under the second road geometry variable satisfies a set first condition.

9. The on-road test system for autonomous driving based on a functional design document according to claim 8, wherein The instance test module includes: A first scenario sub-module, configured to instantiate the parameter space of the logical scenario based on the first design operating domain element to obtain a first scenario set; A second scenario sub-module, configured to instantiate the parameter space of the logical scenario based on the second design operating domain element to obtain a second scenario set, and use the union of the first scenario set and the second scenario set as the real vehicle test scenario set; The second scenario set is a proper subset of the first scenario set, and the difference between the test results of the real vehicle test scenarios in the second scenario set in combination with the first design operating domain element and in combination with the second design operating domain element satisfies a set second condition.

10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, When the processor executes the program, it implements the steps of the autonomous driving real vehicle test method based on the functional design document according to any one of claims 1 to 7.

11. 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 real vehicle test method based on the functional design document according to any one of claims 1 to 7.

12. 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 real vehicle test method based on the functional design document according to any one of claims 1 to 7.

Images