Intelligent driving scene generalization generation method and device, medium and equipment

Abstract

The invention belongs to the technical field of intelligent driving, and provides an intelligent driving scene generalization generation method and device, a medium and equipment, and the method comprises the steps: obtaining scene types, and determining the vehicle states and main scene elements of different types of scenes; determining a scene generalization scheme and generating a function test scene through a Sudoku theory and a parameter combination mode according to the self-vehicle state and the main scene elements; carrying out batch automatic operation on the function test scene so as to realize function test; wherein the Sudoku theory specifically comprises the steps that a vehicle is placed in the center of the Sudoku, vehicles located at the non-center position of the Sudoku serve as surrounding vehicles, and after the movement of the surrounding vehicles is divided into cut-in, cut-out, acceleration and deceleration according to the states of the vehicle and the surrounding vehicles, the surrounding vehicles hindering the traveling track of the vehicle are determined to serve as target vehicles. Therefore, a scene which is most meaningful to the function test of the intelligent driving system is generated in a generalization manner.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent driving technology, and in particular relates to a method, device, medium and equipment for generalizing and generating intelligent driving scenarios. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Before self-driving cars can be truly commercialized, they need to go through a lot of tests to ensure their safety. Traditional road testing methods can no longer meet the requirements of self-driving safety testing. Therefore, self-driving virtual simulation testing based on virtual simulation technology has become the self-driving testing method currently chosen by most car manufacturers on the market.

[0004] In the intelligent driving test system, simulation testing has become an important part of the development and testing of intelligent driving vehicles due to its advantages of reducing test cycles and costs, improving test coverage, and avoiding safety issues of real-car road tests. As the cornerstone of simulation testing, the scenario library contains rich attribute information. At present, building a complete simulation test scenario library has become a prerequisite for the development of intelligent driving systems. The more common way to generate scenarios is to use scenario simulation tools to generalize a large number of test scenarios. This method can quickly generate a large number of test scenarios. However, since generalizing scenarios requires generalizing multiple parameters at the same time, it is difficult to intuitively and quickly judge whether the generalized scenarios are reasonable or effective from the data level. Then, screening or verifying the effectiveness and rationality of the test scenarios through various other methods reduces the efficiency of scenario library construction.

[0005] On the other hand, there is no fast and effective method to check and verify a large number of generalized virtual test scenarios. Relying solely on manual inspection or spot checks of each scenario is inefficient and cannot guarantee the effectiveness and rationality of the virtual test scenarios. Summary of the invention

[0006] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a method, device, medium and equipment for generalizing and generating intelligent driving scenarios. After analyzing and listing the scene parameters that have the greatest impact on the functions, the scene generalization scheme is determined based on the nine-square grid theory. The scene library of scene generalization is generalized and generated for specific functions. Therefore, the scene is targeted, thereby generalizing and generating the most meaningful scenes for the functional testing of the intelligent driving system.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A first aspect of the present invention provides a method for generalizing and generating intelligent driving scenarios.

[0009] A generalized generation method for intelligent driving scenarios, comprising:

[0010] Obtain scene categories and determine the vehicle status and main scene elements of different scene categories;

[0011] According to the vehicle status and main scene elements, the scene generalization scheme is determined through the nine-square grid theory and parameter combination method to generate functional test scenes;

[0012] For functional testing scenarios, batch automation is performed to achieve functional testing;

[0013] The Nine-square Grid Theory is as follows: place the vehicle at the center of the Nine-square Grid, and regard vehicles located at non-central positions of the Nine-square Grid as surrounding vehicles. According to the states of the vehicle and surrounding vehicles, the movement of surrounding vehicles is divided into cutting in, cutting out, acceleration and deceleration, and then the surrounding vehicles that hinder the driving trajectory of the vehicle are determined as target vehicles.

[0014] Furthermore, the parameter combination method includes: for the self-vehicle and the target vehicle, after selecting parameters, dividing the parameters into multiple groups, performing pairwise independent combination on each group of data, and then traversing and combining the results of the pairwise independent combination.

[0015] Furthermore, the influencing factors include: road structure, lane information, road driving conditions, weather factors, traffic participant types and traffic participant states.

[0016] Furthermore, the steps for implementing the batch automated operation include:

[0017] Extract the files of functional test scenarios into a table containing serial numbers and scenario names, and place them in the working directory of the test software;

[0018] Modify the parameter generator so that it can read and process cell data in the table and convert it into scenario name parameters in the test software;

[0019] Create new packages, variables, and projects in sequence, and drag the package into the project. Use the parameter generator to load the table, and regenerate the project to display the list of file parameters for the functional test scenario. The newly generated project can be used to realize batch automated running of the functional test scenarios.

[0020] A second aspect of the present invention provides a generalized generation device for intelligent driving scenarios.

[0021] A generalized generation device for intelligent driving scenarios, comprising:

[0022] An element determination module is configured to: obtain a scene category and determine the vehicle state and main scene elements of different categories of scenes;

[0023] The scenario generalization module is configured to: determine the scenario generalization scheme and generate the functional test scenario based on the vehicle status and main scenario elements through the nine-square grid theory and parameter combination;

[0024] The functional testing module is configured to: perform batch automatic operation for functional testing scenarios to implement functional testing;

[0025] The Nine-square Grid Theory is as follows: place the vehicle at the center of the Nine-square Grid, and regard vehicles located at non-central positions of the Nine-square Grid as surrounding vehicles. According to the states of the vehicle and surrounding vehicles, the movement of surrounding vehicles is divided into cutting in, cutting out, acceleration and deceleration, and then the surrounding vehicles that hinder the driving trajectory of the vehicle are determined as target vehicles.

[0026] Furthermore, the parameter combination method includes: for the self-vehicle and the target vehicle, after selecting parameters, dividing the parameters into multiple groups, performing pairwise independent combination on each group of data, and then traversing and combining the results of the pairwise independent combination.

[0027] Furthermore, the influencing factors include: road structure, lane information, road driving conditions, weather factors, traffic participant types and traffic participant states.

[0028] Furthermore, the steps for implementing the batch automated operation include:

[0029] Extract the files of functional test scenarios into a table containing serial numbers and scenario names, and place them in the working directory of the test software;

[0030] Modify the parameter generator so that it can read and process cell data in the table and convert it into scenario name parameters in the test software;

[0031] Create new packages, variables, and projects in sequence, and drag the package into the project. Use the parameter generator to load the table, and regenerate the project to display the list of file parameters for the functional test scenario. The newly generated project can be used to realize batch automated running of the functional test scenarios.

[0032] A third aspect of the present invention provides a computer-readable storage medium.

[0033] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the generalized generation method for intelligent driving scenarios as described in the first aspect above.

[0034] A fourth aspect of the present invention provides a computer device.

[0035] A computer device comprises 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 in the generalized generation method of an intelligent driving scenario as described in the first aspect above are implemented.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] After analyzing and listing the scenario parameters that have the greatest impact on the functions, the present invention determines a scenario generalization scheme based on the Nine-square Grid Theory. The scenario library of scenario generalization is generalized and generated for specific functions, so the scenarios are targeted, thereby generalizing and generating the most meaningful scenarios for the functional testing of the intelligent driving system.

[0038] The present invention enables the generalized scenarios to cover functional testing more comprehensively through exploration, screening, and parameter combination of parameter space, thereby ensuring that the generalized scenarios are reasonable and effective for functional testing.

[0039] The present invention is based on the automated testing software ECU-TEST and utilizes the parameterization idea to parameterize the generalized generated functional test scenarios, build a test case Package, and then put it into the Project to generate a new executable Project, so that the functional test scenarios can be automatically run in batches, greatly reducing the time for manual scenario checking. It has important research and application value in the field of intelligent driving virtual test scenario library construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 is a flow chart of a generalized generation method of an intelligent driving scenario shown in Embodiment 1 of the present invention;

[0042] Figure 2 is a schematic diagram of generalized analysis based on the "Nine-grid" scenario shown in the first embodiment of the present invention;

[0043] Figure 3 is a schematic diagram of a three-car scene shown in Embodiment 1 of the present invention;

[0044] Figure 4 It is a structural diagram of a computer device shown in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0045] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0046] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0047] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0048] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the methods and devices according to various embodiments of the present invention. It should be noted that each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the module, the program segment, or a part of the code may include one or more executable instructions for implementing the logical functions specified in the various embodiments. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the flowchart and / or block diagram, and the combination of boxes in the flowchart and / or block diagram can be implemented using a dedicated hardware-based device that performs a specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0049] Embodiment 1

[0050] This embodiment provides a method for generalizing and generating intelligent driving scenarios.

[0051] A method for generating generalized intelligent driving scenarios provided in this embodiment aims to provide a scenario generalization method based on an intelligent driving virtual test scenario library and a description of actual vehicle functional requirements to ensure the rationality and effectiveness of scenario generalization; and to provide a method for batch automated run verification of scenarios to save time for manually verifying scenarios one by one and improve work efficiency.

[0052] This embodiment provides a method for generalizing and generating intelligent driving scenarios. Based on a basic expert experience scenario library and combined with specific intelligent driving system function descriptions, such as H-NOP, ELK, TSR, H-AVP, APA, RPA, RA, AEB, EBA, and DCLC, a scenario generalization method for specific functions is proposed. This method analyzes and lists the scenario parameters that have the greatest impact on the function, such as the vehicle speed, the status of traffic participants, and the scenario environment, based on the scenario files in the current basic scenario library. The parameters in the scenario files are changed or added by means of parameter combinations, thereby generalizing and generating the most meaningful scenarios for the intelligent driving system function testing.

[0053] This embodiment provides a method for generalizing and generating intelligent driving scenarios, and also proposes a method for automatically checking and verifying generalized scenarios in batches. The method is based on ECU-TEST software and uses parameterization ideas to parameterize the generalized functional test scenarios, build a test case Package, and then put it into the Project to generate a new executable Project, so that the functional test scenarios can be automatically run in batches, greatly reducing the time for manually running scenario checks. It has important research and application value in the field of intelligent driving virtual test scenario library construction.

[0054] This embodiment provides a generalized generation method for intelligent driving scenarios, such as Figure 1 As shown, the specific implementation mainly includes the following steps:

[0055] Step 1: Classify the scenarios in the scenario library according to the functions of the autonomous driving system, such as basic driving functions (ADAS), highway / city pilot driving, parking functions, and warning functions, so as to generalize and test and verify specific functional test scenarios.

[0056] Step 2: Based on the description and requirements of each function of autonomous driving, determine the vehicle status in the scenario and the main scenario elements that affect the function test. Scenario elements include road network (including the type of road structure, lane information, road driving conditions, etc.), weather or other traffic participant types and status.

[0057] The vehicle status includes speed, position, turning, U-turn, etc.

[0058] Types of road structures, such as straights, curves, ramps, intersections, parking lots, etc.

[0059] Lane information, such as single and double lanes, number of lanes, road width, lane line type, etc.

[0060] Road driving conditions, whether the road surface is flat, whether there are potholes or cracks, horizontal and vertical slopes, road surface type, road surface friction coefficient, traffic signs, whether the field of vision is blocked, visibility, etc.

[0061] Weather factors, such as rain, snow, fog, haze, early morning, noon, evening, night, backlight, glare, etc.

[0062] Types of traffic participants, including passenger cars, large vehicles, pedestrians, motorcycles, etc.

[0063] Traffic participant status, behavior analysis, including motion parameters combined with specific actions, such as pedestrians crossing the road, the vehicle in front suddenly slowing down, turning around, etc.

[0064] In this embodiment, each scene category will screen out multiple main scene elements. For example, for basic driving functions AEB / ACC, the main influencing elements of the scene are the speed and position of the host vehicle and the target vehicle; while the main elements of the parking function scene are the position of the host vehicle, the type and size of the parking space, etc.

[0065] Step 3: List the main elements of the specific scenario, determine the scenario generalization plan through parameter combination based on the "Nine-square Grid" theory, and generate test scenarios for each function.

[0066] Referring to the relevant standards of ISO34502, the scene position information was analyzed based on the "Nine-square grid", and the possible movements of the surrounding vehicles were divided into four groups: cut-in, cut-out, acceleration and deceleration. This classification is based on the state of the surrounding vehicles relative to the self-vehicle, so acceleration or deceleration actually refers to the relative speed difference with the self-vehicle; combined with the initial positions of the host vehicle and the target vehicle, such as Figure 2 In the left figure, if the target car is at position 1 or 2, its impact on the main car can only be cut-out, and the other positions are cut-in. Cut-in / cut-out refers to the behavior of the target car. After dividing the movement of the surrounding vehicles into cut-in, cut-out, acceleration and deceleration, the surrounding vehicles that hinder the driving trajectory of the self-vehicle are determined as target vehicles (target vehicles), and the position and movement of the target participants that hinder the driving trajectory of the self-vehicle are determined. This can reduce repeated scenes to a certain extent. For example, if the target car is at position 2 / 5 / 8, its deceleration behavior will not affect the driving of the main car. For example, the cut-in scenes of the target cars at positions 4 and 7 are equivalent, and only one situation needs to be considered when generalizing the scene. Figure 2 The circles in indicate that the corresponding combinations of surrounding vehicle positions and motions may hinder the ego vehicle and therefore need to be considered in the analysis.

[0067] According to the position and movement of the target vehicle that is blocking the driving trajectory of the self-vehicle, the parameters are selected: Figure 3 In the scene, Figure 3 The scene shown is Figure 2 In the "1-ego-5" combination, select the main vehicle (Ego) speed, the initial and final speeds of the target vehicle 1 (Obj1), the initial and final speeds of the target vehicle 2 (Obj2), and the distance trigger range between the target vehicles 1 and 2, a total of 7 parameters, based on Figure 2 The analysis will select the speed range of target vehicle 1 as deceleration, that is, the range in which the speed is smaller than that of the main vehicle, and the speed range of target vehicle 2 as larger than that of the main vehicle, because these parameters will hinder the driving trajectory of the ego vehicle.

[0068] Combination method: The basis for grouping here is not limited. In this embodiment, the parameters are divided into two groups for processing. The first group includes: the initial and final speeds of target vehicle 1, and the initial and final speeds of target vehicle 2; the second group includes: the speed of the vehicle, and the distance trigger range of target vehicles 1 and 2; the two groups of data are independently combined in pairs, and then the results of the two groups of independent combinations are traversed and combined again.

[0069] Specifically, (1) for combination 1: the initial and final speeds of target vehicle 1, the initial and final speeds of target vehicle 2, define the parameter range and step size, and use the paired independent combination method to generate the parameter list of combination 1; similarly for combination 2: the vehicle speed, the distance trigger range of target vehicles 1 and 2, define the parameter range and step size, and generate another set of parameter lists. (2) Both combinations are Figure 3 The key parameters of the scenario shown are traversed and combined with the two sets of parameters. For example, combination 1 generates 120 pairs of results, combination 2 generates 51 pairs of results, and the results of the traversal combination are 6120 cases.

[0070] Combination result screening: Due to the generalization space of parameters, there are often use cases in the combination results that do not meet the test requirements. For each combination, determine whether they will affect the vehicle's driving trajectory to set the screening conditions, such as Figure 3 As shown, the condition for triggering the deceleration of target vehicle 1 is that the main vehicle and the target vehicle reach the set trigger distance. Therefore, the initial speed of target vehicle 1 needs to be less than the speed of the main vehicle to meet the trigger condition. If the speed of the own vehicle is less than the initial speed of target vehicle 1, the deceleration behavior of target vehicle 1 will not be triggered, which is meaningless for the test. Therefore, a filtering condition is added to the combination result for filtering (filtering condition: the speed of the own vehicle is greater than the initial speed of target vehicle 1).

[0071] Finally, the scenario files for functional testing are generated in batches. The above generalized combination results replace the corresponding parameters of the scenario files, and finally the scenario files for functional testing are generated.

[0072] Step 4: Write a script to extract the file names of the basic scene and the generalized scene .xosc files into an Excel spreadsheet containing the serial number and scene name. The generalization is the generalization of the basic scene, and the generalized scene is the result of the output of step 3.

[0073] Step 5. Put the generated table into the Parameter folder of the ECU-TEST test software working directory to facilitate the calling and reading of the ProjectGenerators file in the automated test software.

[0074] Step 6. Modify the Python code of the parameter generator VTD_ParamGenerator_xosc (copy the ParamSetGenerator folder under the path ECU-TEST\ProjectGenerators and rename it to VTD_ParamGenerator_xosc, and modify the ParameterSetGenerators.py file) so that the parameter generator VTD_ParamGenerator_xosc can read and process cell data from Excel and convert it into the scene name parameter of the Project-Package in the ECU-TEST software.

[0075] Step 7. Create a new Package: Set the basic simulation process, including pulling scene files, starting simulation, setting scene running time, and ending simulation.

[0076] Step 8. Create a new variable in the software, create a string variable that matches the scene name in the scene list table, and enable the Variables input parameter.

[0077] Specifically, right-click in Variables, create a new string, name it "XOSC_Name" (corresponding to the name of the scene list, it will automatically pull the "Load element" scene file from the parameter table we created at runtime), and check the first box to enable the function of the Variables input parameter; double-click Load element to call the defined string.

[0078] Step 9. Create a new Project: Drag the newly created Package into the new Project, click to select the custom parameter generator VTD_ParamGenerator_xosc, and load the scene form (i.e., the scene file form).

[0079] Step 10. Right-click to regenerate a new Project file, and the list of scene file parameters will be displayed to realize the parameterization of the scene file.

[0080] Step 11. Click Run to run the newly generated Project file to realize batch automatic running of scene files, so that the generated scenes can be run and verified automatically in batches to ensure that the scenes can be used normally for functional testing, reduce the time for manual verification of scenes, and greatly improve work efficiency.

[0081] The present embodiment provides a method for generalizing and generating intelligent driving scenarios. Based on the "Nine-square Grid" theory, the scenario library of scenario generalization is generalized and generated for specific functions. Therefore, the scenarios are targeted. By exploring the parameter space and adding screening conditions, the generalized scenarios can cover functional testing more comprehensively, ensuring that the generalized scenarios are reasonable and effective for functional testing.

[0082] The present embodiment provides a method for generalizing and generating intelligent driving scenarios. It uses the parameterization idea of ​​automated testing software for the first time to parameterize the generalized generated scenarios, so that the generated scenarios can be automatically run and verified in batches to ensure that the scenarios can be used normally for functional testing, greatly improving work efficiency.

[0083] This embodiment provides a generalized generation method for intelligent driving scenarios. Based on the basic expert experience scenario library and combined with the specific intelligent driving system function description, such as H-NOP, ELK, TSR, H-AVP, APA, RPA, RA, AEB, EBA and DCLC, a scenario generalization method for specific functions is proposed. This method is based on the "Nine-square grid" theory and combined with the scenario files in the current basic scenario library. By analyzing and listing the scenario parameters that have the greatest impact on the function, such as the vehicle speed, the status of traffic participants and the scenario environment, etc., the most meaningful scenarios for the intelligent driving system function test are generalized and generated through the exploration, screening and parameter combination of the parameter space.

[0084] This embodiment provides a method for generalizing and generating intelligent driving scenarios, and also proposes a method for automatically checking and verifying generalized scenarios in batches. The method is based on the automated testing software ECU-TEST, and uses the parameterization idea to parameterize the generalized functional test scenarios, build a test case Package, and then put it into the Project to generate a new executable Project, so that the functional test scenarios can be automatically run in batches, greatly reducing the time for manually running scenario checks. It has important research and application value in the field of intelligent driving virtual test scenario library construction.

[0085] Embodiment 2

[0086] This embodiment provides a generalized generation device for intelligent driving scenarios.

[0087] A generalized generation device for intelligent driving scenarios, comprising:

[0088] An element determination module is configured to: obtain a scene category and determine the vehicle state and main scene elements of different categories of scenes;

[0089] The scenario generalization module is configured to: determine the scenario generalization scheme and generate the functional test scenario based on the vehicle status and main scenario elements through the nine-square grid theory and parameter combination;

[0090] The functional testing module is configured to: perform batch automatic operation for functional testing scenarios to implement functional testing;

[0091] The Nine-square Grid Theory is as follows: place the vehicle at the center of the Nine-square Grid, and regard vehicles located at non-central positions of the Nine-square Grid as surrounding vehicles. According to the states of the vehicle and surrounding vehicles, the movement of surrounding vehicles is divided into cutting in, cutting out, acceleration and deceleration, and then the surrounding vehicles that hinder the driving trajectory of the vehicle are determined as target vehicles.

[0092] The parameter combination method includes: for the self-vehicle and the target vehicle, after selecting the parameters, dividing the parameters into multiple groups, performing pairwise independent combination on each group of data, and then traversing and combining the results of the pairwise independent combination.

[0093] Among them, the influencing factors include: road structure, lane information, road driving conditions, weather factors, traffic participant type and traffic participant status.

[0094] The steps for implementing batch automation include:

[0095] Extract the files of functional test scenarios into a table containing serial numbers and scenario names, and place them in the working directory of the test software;

[0096] Modify the parameter generator so that it can read and process cell data in the table and convert it into scenario name parameters in the test software;

[0097] Create new packages, variables, and projects in sequence, and drag the package into the project. Use the parameter generator to load the table, and regenerate the project to display the list of file parameters for the functional test scenario. The newly generated project can be used to realize batch automated running of the functional test scenarios.

[0098] It should be noted that the generalized generation device for intelligent driving scenarios provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the electronic device is divided into different functional modules to complete all or part of the functions described above. In addition, the generalized generation device for intelligent driving scenarios provided in the above embodiment and the generalized generation method embodiment of intelligent driving scenarios belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0099] Embodiment 3

[0100] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the generalization generation method for intelligent driving scenarios as described in the first embodiment above are implemented.

[0101] Embodiment 4

[0102] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the generalization generation method for intelligent driving scenarios as described in the first embodiment are implemented.

[0103] Figure 4 The schematic diagram of the structure of a computer device provided by an exemplary embodiment of the present application is shown. The computer device includes: a processor and a memory.

[0104] The processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), and PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content that needs to be displayed on the display screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0105] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store at least one computer program, which is used to be used by the processor to implement the vehicle occupant detection method provided in the method embodiment of the present application.

[0106] Those skilled in the art will appreciate that the illustrated structure does not constitute a limitation on the computer device, and may include more or fewer components than illustrated, or combine certain components, or adopt a different component arrangement.

[0107] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A generalized generation method for intelligent driving scenarios, characterized in that: include: Obtain scene categories and determine the vehicle status and main scene elements of different scene categories; According to the vehicle status and main scene elements, the scene generalization scheme is determined through the nine-square grid theory and parameter combination method to generate functional test scenes; For functional testing scenarios, batch automation is performed to achieve functional testing; The Nine-square Grid Theory is as follows: place the vehicle at the center of the Nine-square Grid, and regard vehicles located at non-central positions of the Nine-square Grid as surrounding vehicles. According to the states of the vehicle and surrounding vehicles, the movement of surrounding vehicles is divided into cutting in, cutting out, acceleration and deceleration, and then the surrounding vehicles that hinder the driving trajectory of the vehicle are determined as target vehicles.

2. The generalized generation method of intelligent driving scenarios according to claim 1, characterized in that: The parameter combination method includes: for the self-vehicle and the target vehicle, after selecting parameters, dividing the parameters into multiple groups, performing pairwise independent combination on each group of data, and then traversing and combining the results of the pairwise independent combination.

3. The generalized generation method of intelligent driving scenarios according to claim 1, characterized in that: The influencing factors include: road structure, lane information, road driving conditions, weather factors, traffic participant types and traffic participant status.

4. The generalized generation method of intelligent driving scenarios according to claim 1, characterized in that: The steps for implementing the batch automation operation include: Extract the files of functional test scenarios into a table containing serial numbers and scenario names, and place them in the working directory of the test software; Modify the parameter generator so that it can read and process cell data in the table and convert it into scenario name parameters in the test software; Create new packages, variables, and projects in sequence, and drag the package into the project. Use the parameter generator to load the table, and regenerate the project to display the list of file parameters for the functional test scenario. The newly generated project can be used to realize batch automated running of the functional test scenarios.

5. A generalized generation device for intelligent driving scenarios, characterized in that: include: An element determination module is configured to: obtain a scene category and determine the vehicle state and main scene elements of different categories of scenes; The scenario generalization module is configured to: determine the scenario generalization scheme and generate the functional test scenario based on the vehicle status and main scenario elements through the nine-square grid theory and parameter combination; The functional testing module is configured to: perform batch automatic operation for functional testing scenarios to implement functional testing; The Nine-square Grid Theory is as follows: place the vehicle at the center of the Nine-square Grid, and regard vehicles located at non-central positions of the Nine-square Grid as surrounding vehicles. According to the states of the vehicle and surrounding vehicles, the movement of surrounding vehicles is divided into cutting in, cutting out, acceleration and deceleration, and then the surrounding vehicles that hinder the driving trajectory of the vehicle are determined as target vehicles.

6. The intelligent driving scenario generalization generation system according to claim 5, characterized in that: The parameter combination method includes: for the self-vehicle and the target vehicle, after selecting parameters, dividing the parameters into multiple groups, performing pairwise independent combination on each group of data, and then traversing and combining the results of the pairwise independent combination.

7. The intelligent driving scenario generalization generation system according to claim 5, characterized in that: The influencing factors include: road structure, lane information, road driving conditions, weather factors, traffic participant types and traffic participant status.

8. The intelligent driving scenario generalization generation system according to claim 5, characterized in that: The steps for implementing the batch automation operation include: Extract the files of functional test scenarios into a table containing serial numbers and scenario names, and place them in the working directory of the test software; Modify the parameter generator so that it can read and process cell data in the table and convert it into scenario name parameters in the test software; Create new packages, variables, and projects in sequence, and drag the package into the project. Use the parameter generator to load the table, and regenerate the project to display the list of file parameters for the functional test scenario. The newly generated project can be used to realize batch automated running of the functional test scenarios.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the generalization generation method for intelligent driving scenarios as described in any one of claims 1 to 4 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the generalization generation method of an intelligent driving scenario as described in any one of claims 1-4 are implemented.

Images