Automatic driving simulation test method and system based on element correlation

Abstract

The present invention relates to the field of autonomous driving technology, and provides an autonomous driving simulation test method and system based on element correlation. The method comprises: combining environmental elements according to an interactive unit set in environmental attributes to obtain a first correlation set including at least two environmental elements; determining a behavior element set matching the first correlation set as a second correlation set according to an interactive unit set in a behavior attribute; generating relevant test scenarios, and executing autonomous driving simulation tests to obtain test results. The present invention combines environmental elements and behavior element sets with correlation through an interactive unit set, and generates relevant test scenarios for autonomous driving simulation tests based on environmental elements and behavior element sets with correlation, which can exclude invalid scenarios and repeated scenarios and improve the efficiency of simulation tests.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving simulation test method and system based on element correlation. Background Art

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

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

[0004] Simulation testing is a low-cost testing method that can test a large number of simulation test scenarios in a short time. The existing simulation scenario generation method is based on the combination of scenario elements. Although this method can quickly generate a large number of simulation test scenarios, it inevitably contains many invalid and repeated scenarios.

[0005] Therefore, how to more accurately generate simulation test scenarios to facilitate the execution of autonomous driving simulation tests has become a technical problem that urgently needs to be solved in the industry. Summary of the invention

[0006] The present invention provides an autonomous driving simulation test method and system based on element correlation, which are used to solve the defects of invalid scenes and repeated scenes in the prior art, and more accurately generate simulation test scenes for the execution of autonomous driving simulation tests.

[0007] The present invention provides an automatic driving simulation test method based on element correlation, comprising:

[0008] Acquire environmental attributes corresponding to environmental elements one by one, and under a set mutual exclusion constraint, combine the environmental elements according to an interactive unit set in the environmental attributes to obtain a first related set including at least two environmental elements;

[0009] Acquire behavior attributes corresponding one-to-one to the behavior element sets, and determine the behavior element set matching the first related set as the second related set according to the interaction unit set in the behavior attributes;

[0010] Generate a relevant test scenario based on the union of the first relevant set and the second relevant set, and perform an autonomous driving simulation test with the relevant test scenario to obtain a test result;

[0011] The environmental elements are components of the test scene, including road information or weather information; the interactive units are components of the automatic driving system; the behavioral elements are components of the test scene, including type information and motion information of traffic participants.

[0012] According to an automatic driving simulation test method based on element correlation provided by the present invention, the step of combining the environmental elements according to the interactive unit set in the environmental attributes to obtain a first correlation set including at least two environmental elements comprises:

[0013] At least two of the environment elements having the same subset of interaction unit sets in the environment attributes are combined into a first related set.

[0014] According to an automatic driving simulation test method based on element correlation provided by the present invention, the step of determining the behavior element set matching the first correlation set as the second correlation set according to the interaction unit set in the behavior attribute includes:

[0015] A set of behavior elements in which the set of interaction units in the behavior attributes and the set of interaction units of the environmental elements in the first related set have the same subset is determined as a second related set.

[0016] According to an element correlation-based autonomous driving simulation test method provided by the present invention, after the step of generating a relevant test scenario based on the union of the first correlation set and the second correlation set, the method further includes:

[0017] Marking the relevant test scenarios according to matching conditions;

[0018] The matching condition refers to: the largest identical subset existing in the interaction unit set of the first related set and the interaction unit set of the environmental elements in the first related set.

[0019] According to an automatic driving simulation test method based on element correlation provided by the present invention, the steps of generating a relevant test scenario based on the union of the first relevant set and the second relevant set, and performing an automatic driving simulation test with the relevant test scenario to obtain a test result include:

[0020] Obtain a plurality of key-value pairs according to the union of the first related set and the second related set; the key-value pairs include variable names and variable values;

[0021] After determining the intervals between the variable values ​​that have continuous values, the variable values ​​that have discrete or continuous values ​​are arranged and combined to obtain a plurality of scene parameter groups;

[0022] Converting the scenario parameter group into an input format of a simulation program and inputting the format into the simulation program to obtain a relevant test scenario;

[0023] Run the simulation software under the relevant test scenario, perform the autonomous driving simulation test, and obtain the test results.

[0024] According to an automatic driving simulation test method based on element correlation provided by the present invention, the mutually exclusive constraint means that there is no mutually exclusive environmental element pair in the first correlation set; the mutually exclusive element pair includes:

[0025] The road is the environmental element of the tunnel, and the lighting is the environmental element of turning on the lights at night;

[0026] The road is a tunnel environment element, and the lighting is a night environment element without lights;

[0027] The road is a tunnel environment element, the light is dawn and dusk environment element; or,

[0028] The road is the environmental element of a tunnel, and the weather is the environmental element of a rainy day.

[0029] The present invention also provides an automatic driving simulation test system based on element correlation, comprising:

[0030] An environment module is used to obtain environment attributes corresponding to environment elements one by one, and under a set mutually exclusive constraint, combine the environment elements according to the interactive unit set in the environment attributes to obtain a first related set including at least two environment elements;

[0031] A behavior module, used to obtain behavior attributes corresponding to the behavior element sets one by one, and determine the behavior element set matching the first related set as the second related set according to the interaction unit set in the behavior attributes;

[0032] A testing module, configured to generate a relevant test scenario based on a union of the first relevant set and the second relevant set, and perform an autonomous driving simulation test with the relevant test scenario to obtain a test result;

[0033] The environmental elements are components of the test scene, including road information or weather information; the interactive units are components of the automatic driving system; the behavioral elements are components of the test scene, including type information and motion information of traffic participants.

[0034] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned automatic driving simulation test methods based on element correlation are implemented.

[0035] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the automatic driving simulation test method based on element correlation as described in any one of the above are implemented.

[0036] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the above-mentioned element correlation-based autonomous driving simulation test methods.

[0037] The element correlation-based autonomous driving simulation test method and system provided by the present invention combine a set of environmental elements and a set of behavioral elements with correlation through a set of interactive units, and generate relevant test scenarios for autonomous driving simulation testing based on the set of environmental elements and behavioral elements with correlation, which can eliminate invalid scenarios and repeated scenarios and improve the efficiency of simulation testing. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0039] Figure 1 It is a flow chart of an automatic driving simulation test method based on element correlation provided by the present invention;

[0040] Figure 2 It is a flowchart of a simulation test method provided by an embodiment of the present invention;

[0041] Figure 3 is a structural schematic diagram of an automatic driving simulation system based on element correlation provided by the present invention;

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

[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Combine the following Figure 1-Figure 2 Description of the invention

[0045] like Figure 1 As shown, an embodiment of the present invention provides an automatic driving simulation test method based on element correlation, comprising:

[0046] Step 102, obtaining environmental attributes corresponding to environmental elements one by one, and combining the environmental elements according to the interactive unit set in the environmental attributes under the set mutual exclusion constraint to obtain a first related set including at least two environmental elements;

[0047] Step 104, acquiring behavior attributes corresponding to the behavior element sets one by one, and determining the behavior element set matching the first related set as the second related set according to the interaction unit set in the behavior attributes;

[0048] Step 106, generating a relevant test scenario based on the union of the first relevant set and the second relevant set, and performing an autonomous driving simulation test with the relevant test scenario to obtain a test result;

[0049] The environmental elements are components of the test scene, including road information or weather information; the interactive units are components of the automatic driving system; the behavioral elements are components of the test scene, including type information and motion information of traffic participants.

[0050] In this embodiment, the behavior element is a scene dynamic behavior constituent element related to the dynamic driving behavior DDT, wherein the type of traffic participants may be cars, trucks, etc., and the motion information of traffic participants may be position, speed, direction, acceleration, etc.

[0051] The environmental elements are scene static environment elements related to the operating design domain (ODD).

[0052] It is worth noting that not all ODDs belong to environmental elements. The environmental elements in this embodiment mainly consider road information (such as tunnels, straight roads, curve curvature, slope curvature, etc.) and weather information (such as daytime, sunny days, no street lights, turning on car lights, etc.).

[0053] In a preferred embodiment, the autonomous driving system includes a perception unit (perception), a control unit (planning & control, PNC) and a positioning unit (loclization); in some other embodiments, the perception unit (perception), the control unit (planning & control) and the positioning unit (loclization) can be further subdivided into more specific functional units.

[0054] The beneficial effects of this embodiment are:

[0055] By combining a set of correlated environmental elements and a set of behavioral elements through a set of interactive units, and generating relevant test scenarios based on the set of correlated environmental elements and behavioral elements for autonomous driving simulation testing, invalid scenarios and repeated scenarios can be eliminated, thereby improving the efficiency of simulation testing.

[0056] like Figure 2 As shown, according to the above embodiment, this embodiment includes:

[0057] Step 1021, obtaining environmental attributes corresponding to environmental elements one by one;

[0058] The step of combining the environmental elements according to the interactive unit set in the environmental attributes to obtain a first related set including at least two environmental elements comprises:

[0059] Step 1022: combine at least two of the environmental elements having the same subset of the interactive unit set in the environmental attributes into a first related set.

[0060] Step 1041, obtaining behavior attributes corresponding to the behavior element set one by one;

[0061] The step of determining the set of behavior elements matching the first related set as the second related set according to the set of interaction units in the behavior attributes comprises:

[0062] Step 1042: determine a set of behavior elements in which the interaction unit set in the behavior attribute and the interaction unit set of the environmental elements in the first related set have the same subset as a second related set.

[0063] Step 1061: Generate a relevant test scenario based on the union of the first relevant set and the second relevant set

[0064] After the step of generating a relevant test scenario based on the union of the first relevant set and the second relevant set, the method further includes:

[0065] Step 1062, marking the relevant test scenarios according to the matching conditions;

[0066] The matching condition refers to: the largest identical subset existing in the interaction unit set of the first related set and the interaction unit set of the environmental elements in the first related set.

[0067] The execution result of step 1062 can provide a label for the simulation test scenario, so that in the subsequent simulation test process, the label can be searched according to different test requirements to perform more targeted simulation tests.

[0068] Step 1063, perform an autonomous driving simulation test using the relevant test scenario to obtain a test result.

[0069] Furthermore, the step of generating a relevant test scenario based on the union of the first relevant set and the second relevant set, and performing an autonomous driving simulation test with the relevant test scenario to obtain a test result includes:

[0070] Obtain a plurality of key-value pairs according to the union of the first related set and the second related set; the key-value pairs include variable names and variable values;

[0071] The variable value may be a discrete variable value or a continuous variable value interval existing in the first related set and the second related set, or a discrete variable value or a continuous variable value interval assigned according to test requirements;

[0072] The assignment process also has assignment constraints; the assignment constraints are obtained based on the execution logic of the behavior element. For example, for the behavior element where the target vehicle overtakes the host vehicle from the side and rear and cuts in and slows down, its execution logic is:

[0073] The main vehicle is traveling at the speed limit k_hv_speed. The target vehicle is approaching the main vehicle from behind at a speed k_tv_speed01 in the adjacent lane k_side of the main vehicle. When the target vehicle exceeds the main vehicle k_dis, the target vehicle cuts in front of the main vehicle and decelerates from k_tv_acc to k_tv_speed02.

[0074] In order to complete the above execution logic, there must be restrictions on the speed, acceleration, and relative position of the target vehicle and the main vehicle, so that the target vehicle can successfully overtake the main vehicle, cut in, and retrieve. This restriction is an assignment constraint.

[0075] After determining the intervals between the variable values ​​that have continuous values, the variable values ​​that have discrete or continuous values ​​are arranged and combined to obtain a plurality of scene parameter groups;

[0076] Converting the scenario parameter group into an input format of a simulation program and inputting the format into the simulation program to obtain a relevant test scenario;

[0077] In a preferred embodiment, the simulation program can complete the missing parameters in the scene parameter group with default elements based on the necessary elements of the scene composition. For example, the necessary elements of the scene composition include a load type environmental element, a road attribute type environmental element, a road curvature type environmental element, a weather type environmental element, and a lighting type environmental element. If any one or more of the environmental elements are missing in the union of the first related set and the second related set, the simulation program can generate parameter completion with the following default elements to generate a complete simulation test scene.

[0078] The environmental element whose load type is full load, the environmental element whose road attribute type is highway, the environmental element whose road curvature type is straight road, the environmental element whose weather type is sunny day, or the environmental element whose light type is daytime.

[0079] Run the simulation software under the relevant test scenario, perform the autonomous driving simulation test, and obtain the test results.

[0080] The mutually exclusive constraint means that there is no mutually exclusive environmental element pair in the first related set; the mutually exclusive element pair includes:

[0081] The road is the environmental element of the tunnel, and the lighting is the environmental element of turning on the lights at night;

[0082] The road is a tunnel environment element, and the lighting is a night environment element without lights;

[0083] The road is a tunnel environment element, the light is dawn and dusk environment element; or,

[0084] The road is the environmental element of a tunnel, and the weather is the environmental element of a rainy day.

[0085] Furthermore, there are impossible constraints in the construction process of the first related set and the second related set; the impossible constraints refer to that conflicting elements cannot exist in the first related set and the second related set, such as straight roads and curves, day and night, etc.

[0086] In a preferred embodiment, executing step 1021 may obtain the following table:

[0087]

[0088] In the table, Y means that the environmental element can affect the unit, and a null value means that the environmental element cannot affect the unit;

[0089] Furthermore, considering that two environmental elements are combined to form the first related set, the execution description of step 1022 is given as follows.

[0090] For example, the interactive units of the tunnel environment element are perception units and loclization units, and the interactive units of the ramp environment element are PNC units. The interactive unit sets of the two have no intersection, and therefore cannot form the first related set.

[0091] For another example, the interaction units of the rainy day environment element are perception units and PNC units, and the interaction unit of the ramp environment element is the PNC unit. The intersection of the interaction unit sets of the two exists, which is the PNC unit, and they can constitute the first related set.

[0092] According to the execution result of step 1022, the following table can be obtained:

[0093]

[0094] In the table, Y indicates that the two environmental elements corresponding to the row and column can be combined to form the first related set, NA indicates that there is no correlation between the two ODDs and no combination is required, and EX indicates that the two ODDs are mutually exclusive and no combination is required (mutually exclusive constraint);

[0095] It is worth noting that there are default environmental elements in the above table, namely, full load, straight road, high speed, daytime and sunny day, so that the simulation program can complete the default environmental elements in the first related set.

[0096] The execution result of step 1041 is as follows:

[0097]

[0098] In the table, Y means that the behavior element set can affect the unit, and a null value means that the behavior element set cannot affect the unit;

[0099] The execution of step 1042 is illustrated as follows.

[0100] For example, for the behavior element set with serial number 1, its interaction unit set includes loclization unit and PNC unit. For the first related set composed of rainy day and ramp, the interaction unit of the rainy day environment element is perception unit and PNC unit, and the interaction unit of the ramp environment element is PNC unit. Then the interaction unit set of rainy day, ramp and the behavior element set with serial number 1 exists, which is PNC unit. Therefore, (relative to the first related set composed of rainy day and ramp) the second related set of the behavior element set with serial number 1 can be determined.

[0101] The beneficial effects of this embodiment are:

[0102] By using the component units in the autonomous driving system as intermediate variables, the behavioral elements and environmental elements in the construction of the simulation test scenario are effectively linked. On the premise that only related (i.e., there is an intersection in the set of interactive units) behavioral elements and environmental elements are selected to combine to form a simulation test scenario, the final obtained simulation test scenario set has a higher proportion of valid scenarios, which makes it possible to expose problems of the autonomous driving model based on a simulation test scenario set with a higher proportion of valid scenarios more quickly, thereby improving the iteration, update, and learning speed of the autonomous driving model.

[0103] The following is a description of the autonomous driving simulation test device based on element correlation provided by the present invention. The autonomous driving simulation test device based on element correlation described below and the autonomous driving simulation test method based on element correlation described above can be referenced to each other.

[0104] An embodiment of the present invention further provides an automatic driving simulation test system based on element correlation, comprising:

[0105] Environmental module 1, used to obtain environmental attributes corresponding to environmental elements one by one, and under a set mutually exclusive constraint, combine the environmental elements according to the interactive unit set in the environmental attributes to obtain a first related set including at least two environmental elements;

[0106] Behavior module 2, used to obtain behavior attributes corresponding to behavior element sets one by one, and determine the behavior element set matching the first related set as the second related set according to the interaction unit set in the behavior attributes;

[0107] A test module 3 is used to generate a relevant test scenario based on the union of the first relevant set and the second relevant set, and perform an autonomous driving simulation test with the relevant test scenario to obtain a test result;

[0108] The environmental elements are components of the test scene, including road information or weather information; the interactive units are components of the automatic driving system; the behavioral elements are components of the test scene, including type information and motion information of traffic participants.

[0109] The environmental module 1 comprises:

[0110] The first related submodule is used to combine at least two of the environmental elements having the same subset of the interactive unit set in the environmental attributes into a first related set.

[0111] The behavior module 2 includes:

[0112] The second correlation submodule is used to determine the set of behavior elements in which the interaction unit set in the behavior attribute and the interaction unit set of the environmental elements in the first correlation set have the same subset as the second correlation set.

[0113] The test module 3 comprises:

[0114] A key-value pair submodule, used to obtain a plurality of key-value pairs according to the union of the first related set and the second related set; the key-value pairs include variable names and variable values;

[0115] An arrangement submodule, for determining the interval between the variable values ​​with continuous values, and then arranging and combining the variable values ​​with discrete or continuous values ​​to obtain a plurality of scene parameter groups;

[0116] A simulation scenario submodule, used for converting the scenario parameter group into an input format of a simulation program, and inputting the format into the simulation program to obtain a relevant test scenario;

[0117] The simulation test submodule is used to run the simulation software under the relevant test scenario, perform the autonomous driving simulation test, and obtain the test results.

[0118] The system further comprises:

[0119] A matching submodule, used for marking the relevant test scenarios according to matching conditions;

[0120] The matching condition refers to: the largest identical subset existing in the interaction unit set of the first related set and the interaction unit set of the environmental elements in the first related set.

[0121] The mutually exclusive constraint means that there is no mutually exclusive environmental element pair in the first related set; the mutually exclusive element pair includes:

[0122] The road is the environmental element of the tunnel, and the lighting is the environmental element of turning on the lights at night;

[0123] The road is a tunnel environment element, and the lighting is a night environment element without lights;

[0124] The road is a tunnel environment element, the light is dawn and dusk environment element; or,

[0125] The road is the environmental element of a tunnel, and the weather is the environmental element of a rainy day.

[0126] The beneficial effects of this embodiment are:

[0127] By combining a set of correlated environmental elements and a set of behavioral elements through a set of interactive units, and generating relevant test scenarios based on the set of correlated environmental elements and behavioral elements for autonomous driving simulation testing, invalid scenarios and repeated scenarios can be eliminated, thereby improving the efficiency of simulation testing.

[0128] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor (processor) 410, a communication interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call the logic instructions in the memory 430 to execute an autonomous driving simulation test method based on element correlation, which includes: obtaining environmental attributes that correspond one-to-one to environmental elements, and under set mutual exclusion constraints, combining the environmental elements according to the set of interaction units in the environmental attributes to obtain a first related set including at least two environmental elements; obtaining behavioral attributes that correspond one-to-one to the set of behavioral elements, and determining the set of behavioral elements that matches the first related set as a second related set according to the set of interaction units in the behavioral attributes; generating a related test scenario based on the union of the first related set and the second related set, and performing an autonomous driving simulation test with the related test scenario to obtain a test result; the environmental elements are constituent elements of the test scenario, including road information or weather information; the interaction units are constituent units of the autonomous driving system; the behavioral elements are constituent elements of the test scenario, including type information and motion information of traffic participants.

[0129] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0130] 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 automatic driving simulation test method based on element correlation provided by the above methods, which method includes: obtaining environmental attributes corresponding one-to-one to environmental elements, and under set mutual exclusion constraints, combining the environmental elements according to the set of interactive units in the environmental attributes to obtain a first related set including at least two environmental elements; obtaining behavioral attributes corresponding one-to-one to a set of behavioral elements, and determining a set of behavioral elements matching the first related set as a second related set according to the set of interactive units in the behavioral attributes; generating a related test scenario based on the union of the first related set and the second related set, and performing an automatic driving simulation test with the related test scenario to obtain a test result; the environmental elements are constituent elements of the test scenario, including road information or weather information; the interactive units are constituent units of the automatic driving system; the behavioral elements are constituent elements of the test scenario, including type information and motion information of traffic participants.

[0131] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the autonomous driving simulation test method based on element correlation provided by the above-mentioned methods, the method comprising: obtaining environmental attributes corresponding one-to-one to environmental elements, and under set mutually exclusive constraints, combining the environmental elements according to a set of interactive units in the environmental attributes to obtain a first related set including at least two environmental elements; obtaining behavioral attributes corresponding one-to-one to a set of behavioral elements, and determining a set of behavioral elements matching the first related set as a second related set according to a set of interactive units in the behavioral attributes; generating a related test scenario based on the union of the first related set and the second related set, and performing an autonomous driving simulation test with the related test scenario to obtain a test result; the environmental elements are constituent elements of the test scenario, including road information or weather information; the interactive units are constituent units of the autonomous driving system; the behavioral elements are constituent elements of the test scenario, including type information and motion information of traffic participants.

[0132] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0133] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic driving simulation test method based on element correlation, characterized in that: include: Acquire environmental attributes corresponding to environmental elements one by one, and under a set mutual exclusion constraint, combine the environmental elements according to an interactive unit set in the environmental attributes to obtain a first related set including at least two environmental elements; Acquire behavior attributes corresponding one-to-one to the behavior element sets, and determine the behavior element set matching the first related set as the second related set according to the interaction unit set in the behavior attributes; Generate a relevant test scenario based on the union of the first relevant set and the second relevant set, and perform an autonomous driving simulation test with the relevant test scenario to obtain a test result; The environmental elements are components of the test scenario, including road information or weather information; The interaction unit is a component unit of the autonomous driving system; the behavior element is a component element of the test scenario, including type information and motion information of traffic participants; The mutually exclusive constraint means that there are no mutually exclusive pairs of environment elements in the first related set; The mutually exclusive environmental element pair includes: The road is the environmental element of the tunnel, and the lighting is the environmental element of turning on the lights at night; The road is a tunnel environment element, and the lighting is a night environment element without lights; The road is a tunnel environment element, the light is dawn and dusk environment element; or, The road is an environmental element of a tunnel, and the weather is an environmental element of a rainy day; The step of combining the environmental elements according to the interactive unit set in the environmental attributes to obtain a first related set including at least two environmental elements comprises: Combining at least two of the environment elements having the same subset of interaction unit sets in the environment attributes into a first related set; The step of determining the set of behavior elements matching the first related set as the second related set according to the set of interaction units in the behavior attributes comprises: Determine a set of behavior elements in which the interaction unit set in the behavior attribute and the interaction unit set of the environmental elements in the first related set have the same subset as a second related set; The automatic driving system includes a perception unit, a control unit and a positioning unit.

2. The automatic driving simulation test method based on element correlation according to claim 1, characterized in that: After the step of generating a relevant test scenario based on the union of the first relevant set and the second relevant set, the method further includes: Marking the relevant test scenarios according to matching conditions; The matching condition refers to: the largest identical subset existing in the interaction unit set of the first related set and the interaction unit set of the environmental elements in the first related set.

3. The automatic driving simulation test method based on element correlation according to claim 1, characterized in that: The step of generating a relevant test scenario based on the union of the first relevant set and the second relevant set, and performing an autonomous driving simulation test with the relevant test scenario to obtain a test result comprises: Obtain a plurality of key-value pairs according to the union of the first related set and the second related set; the key-value pairs include variable names and variable values; After determining the intervals between the variable values ​​that have continuous values, the variable values ​​that have discrete or continuous values ​​are arranged and combined to obtain a plurality of scene parameter groups; Converting the scenario parameter group into an input format of a simulation program and inputting the format into the simulation program to obtain a relevant test scenario; Run the simulation software under the relevant test scenario, perform the autonomous driving simulation test, and obtain the test results.

4. An automatic driving simulation test system based on element correlation, characterized in that: include: An environment module is used to obtain environment attributes corresponding to environment elements one by one, and under a set mutually exclusive constraint, combine the environment elements according to the interactive unit set in the environment attributes to obtain a first related set including at least two environment elements; A behavior module, used to obtain behavior attributes corresponding to the behavior element sets one by one, and determine the behavior element set matching the first related set as the second related set according to the interaction unit set in the behavior attributes; A testing module, configured to generate a relevant test scenario based on a union of the first relevant set and the second relevant set, and perform an autonomous driving simulation test with the relevant test scenario to obtain a test result; The environmental elements are components of the test scenario, including road information or weather information; The interaction unit is a component unit of the autonomous driving system; the behavior element is a component element of the test scenario, including type information and motion information of traffic participants; The mutually exclusive constraint means that there are no mutually exclusive pairs of environment elements in the first related set; The mutually exclusive environmental element pair includes: The road is the environmental element of the tunnel, and the lighting is the environmental element of turning on the lights at night; The road is a tunnel environment element, and the lighting is a night environment element without lights; The road is a tunnel environment element, the light is dawn and dusk environment element; or, The road is an environmental element of a tunnel, and the weather is an environmental element of a rainy day; The environment module includes: A first correlation submodule is configured to combine at least two of the environmental elements having the same subset of the interactive unit set in the environmental attributes into a first correlation set; The behavior module includes: A second related submodule, determining a set of behavior elements having the same subset of the interaction unit set in the behavior attribute and the interaction unit set of the environmental elements in the first related set as a second related set; The automatic driving system includes a perception unit, a control unit and a positioning unit.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the element correlation-based autonomous driving simulation test method as described in any one of claims 1 to 3 are implemented.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the element correlation-based autonomous driving simulation test method as described in any one of claims 1 to 3 are implemented.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the element correlation-based autonomous driving simulation test method as described in any one of claims 1 to 3 are implemented.

Images