Method and device for generating intelligent network connection vehicle analog simulation test scene

Abstract

The invention provides a method and device for generating an analog simulation test scene of an intelligent networked vehicle, and the method comprises the steps: obtaining an automatic driving function parameter of a target vehicle according to a factory function architecture of the target vehicle which is expected to be subjected to an automatic driving simulation test for the target vehicle in the intelligent networked vehicles; determining scene feature information used for generating a simulation test scene according to scene classification features corresponding to a preset scene element model based on the automatic driving function parameters and test requirements corresponding to the automatic driving simulation test; the scene element model is a feature element model pre-established for an expected function safety test in a vehicle automatic driving test; and based on the scene feature information, generating a simulation test scene for automatic driving simulation test of the target vehicle in a mode of combining dynamic and static scenes. Through the method, the flexibility and applicability of the safety test of the automatic driving expected function are improved, and the comprehensiveness and accuracy of the test are further improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving testing technology, and more particularly to a method and device for generating a simulation test scenario for an intelligent connected vehicle. Background Art

[0002] With the continuous advancement of autonomous driving technology, more and more advanced autonomous driving functions have been developed and put into practical application. While these technologies improve road safety and travel convenience, they also introduce new safety hazards. Since autonomous driving systems need to operate in various complex environments and scenarios, such as different weather conditions, road conditions and traffic behaviors, these complexities are far beyond the operating scope of traditional vehicles, bringing unprecedented safety challenges.

[0003] At present, the autonomous driving tests for intelligent connected vehicles are mainly vehicle safety system tests centered on quality assurance. In the scenarios established by such tests, the tests are carried out through the prevention, detection and elimination of random hardware failures and systematic failures, which are less applicable to autonomous driving vehicles. In addition, in actual operation, autonomous driving vehicles may have non-fault safety issues due to insufficient design, performance limitations or external environmental factors, which cannot be reflected in this test scenario, reducing the comprehensiveness and accuracy of the vehicle's autonomous driving tests. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a method and device for generating a simulation test scenario for an intelligent connected vehicle, by obtaining the autonomous driving function parameters from the pre-defined factory function architecture of the intelligent connected vehicle, and combining the test requirements of the autonomous driving test, according to the scene classification characteristics corresponding to the scene element model established in advance for the expected functional safety test in the vehicle autonomous driving test, determine the scene feature information, and then generate a simulation test scenario for the vehicle to perform autonomous driving simulation testing by combining dynamic and static scenes, thereby improving the flexibility and applicability of the expected functional safety test of autonomous driving, and thereby improving the comprehensiveness and accuracy of the autonomous driving test of the intelligent connected vehicle.

[0005] The present application provides a method for generating a simulation test scenario for an intelligent connected vehicle, the method comprising:

[0006] For a target vehicle among intelligent connected vehicles, the automatic driving function parameters of the target vehicle are obtained according to the pre-defined factory function architecture of the target vehicle for which the automatic driving simulation test is expected to be performed;

[0007] Based on the autonomous driving function parameters and the test requirements corresponding to the autonomous driving simulation test, scene feature information for generating a simulation test scene is determined according to scene classification features corresponding to a preset scene element model; the scene element model is a feature element model pre-established for an expected functional safety test in a vehicle autonomous driving test;

[0008] Based on the scene feature information, a simulation test scene for the target vehicle to perform an autonomous driving simulation test is generated by combining dynamic and static scenes.

[0009] Furthermore, after generating a simulation test scene for the target vehicle to perform an autonomous driving test by combining dynamic and static scenes, the method further includes:

[0010] Using the target vehicle to perform an autonomous driving simulation test in the simulation test scenario, and obtaining safety test data corresponding to the autonomous driving simulation test;

[0011] An evaluation result of the simulation test scenario is determined based on the safety test data.

[0012] Further, determining the evaluation result of the simulation test scenario according to the safety test data includes:

[0013] Determining a loss of control degree parameter corresponding to the simulation test scenario based on the number of accidents included in the safety test data;

[0014] Determining a criticality parameter corresponding to the simulation test scenario based on the degree of vehicle damage included in the safety test data;

[0015] Determining whether the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals;

[0016] If the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals, determining that the evaluation result of the simulation test scenario is qualified;

[0017] If at least one of the out-of-control degree parameter and the criticality degree parameter does not belong to the corresponding evaluation parameter interval, it is determined that the evaluation result of the simulation test scenario is unqualified.

[0018] Furthermore, the scene classification features include: road features, main vehicle features, traffic participant features and environment features.

[0019] Furthermore, based on the scene feature information, generating a simulation test scene for the target vehicle to perform an autonomous driving simulation test by combining dynamic and static scenes includes:

[0020] Based on the first scene feature information corresponding to the road feature, generating a static test scene corresponding to the simulation test scene;

[0021] Generate a dynamic test scene corresponding to the simulation test scene based on the static test scene, the second scene feature information corresponding to the main vehicle feature, and the third scene feature information corresponding to the traffic participant feature;

[0022] Determining the environmental factors corresponding to the simulation test scenario based on fourth scenario feature information corresponding to the environmental features;

[0023] The dynamic test scenario and the environmental factors are combined to generate a simulation test scenario for the target vehicle to perform an autonomous driving simulation test.

[0024] Furthermore, the generating of the static test scene corresponding to the simulation test scene based on the first scene feature information corresponding to the road feature includes:

[0025] Based on the first scene feature information, determining map data, road data and static element data corresponding to the simulation test scene;

[0026] Based on the map data and the road data, construct a road model corresponding to the simulation test scenario;

[0027] The static element data is integrated into the road model to generate a static test scene corresponding to the simulation test scene.

[0028] Furthermore, the generating of the dynamic test scene corresponding to the simulation test scene based on the static test scene, the second scene feature information corresponding to the main vehicle feature and the third scene feature information corresponding to the traffic participant feature includes:

[0029] Initialize the static test scene to construct an initialized dynamic scene model;

[0030] Determining test condition information corresponding to the simulation test scenario based on the second scenario feature information and the third scenario feature information;

[0031] Based on the initialized dynamic scenario model and the test condition information, a dynamic test scenario corresponding to the simulation test scenario is generated.

[0032] The present application also provides a device for generating a simulation test scenario for an intelligent connected vehicle, the device comprising:

[0033] A parameter acquisition module, for acquiring the automatic driving function parameters of a target vehicle in the intelligent connected vehicle according to a pre-defined factory function architecture of the target vehicle for which an automatic driving simulation test is desired;

[0034] a feature determination module, configured to determine, based on the autonomous driving function parameters and the test requirements corresponding to the autonomous driving simulation test, scene feature information for generating a simulation test scene according to scene classification features corresponding to a preset scene element model; the scene element model is a feature element model pre-established for an expected functional safety test in a vehicle autonomous driving test;

[0035] The scenario generation module is used to generate a simulation test scenario for the target vehicle to perform an autonomous driving simulation test based on the scenario feature information by combining dynamic and static scenarios.

[0036] Furthermore, the generating device further comprises a scene evaluation module, and the scene evaluation module is used to:

[0037] Using the target vehicle to perform an autonomous driving simulation test in the simulation test scenario, and obtaining safety test data corresponding to the autonomous driving simulation test;

[0038] An evaluation result of the simulation test scenario is determined based on the safety test data.

[0039] Further, when the scenario evaluation module is used to determine the evaluation result of the simulation test scenario according to the safety test data, the scenario evaluation module is used to:

[0040] Determining a loss of control degree parameter corresponding to the simulation test scenario based on the number of accidents included in the safety test data;

[0041] Determining a criticality parameter corresponding to the simulation test scenario based on the degree of vehicle damage included in the safety test data;

[0042] Determining whether the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals;

[0043] If the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals, determining that the evaluation result of the simulation test scenario is qualified;

[0044] If at least one of the out-of-control degree parameter and the criticality degree parameter does not belong to the corresponding evaluation parameter interval, it is determined that the evaluation result of the simulation test scenario is unqualified.

[0045] Furthermore, when the scenario generation module is used to generate a simulation test scenario for a target vehicle to perform an autonomous driving simulation test by combining dynamic and static scenarios based on the scenario feature information, the scenario generation module is used to:

[0046] Based on the first scene feature information corresponding to the road feature, generating a static test scene corresponding to the simulation test scene;

[0047] Generate a dynamic test scene corresponding to the simulation test scene based on the static test scene, the second scene feature information corresponding to the main vehicle feature, and the third scene feature information corresponding to the traffic participant feature;

[0048] Determining the environmental factors corresponding to the simulation test scenario based on fourth scenario feature information corresponding to the environmental features;

[0049] The dynamic test scenario and the environmental factors are combined to generate a simulation test scenario for the target vehicle to perform an autonomous driving simulation test.

[0050] Further, when the scenario generation module is used to generate a static test scenario corresponding to the simulation test scenario based on the first scenario feature information corresponding to the road feature, the scenario generation module is used to:

[0051] Based on the first scene feature information, determining map data, road data and static element data corresponding to the simulation test scene;

[0052] Based on the map data and the road data, construct a road model corresponding to the simulation test scenario;

[0053] The static element data is integrated into the road model to generate a static test scene corresponding to the simulation test scene.

[0054] Furthermore, when the scenario generation module is used to generate a dynamic test scenario corresponding to the simulation test scenario based on the static test scenario, the second scenario feature information corresponding to the main vehicle feature, and the third scenario feature information corresponding to the traffic participant feature, the scenario generation module is used to:

[0055] Initialize the static test scene to construct an initialized dynamic scene model;

[0056] Determining test condition information corresponding to the simulation test scenario based on the second scenario feature information and the third scenario feature information;

[0057] Based on the initialized dynamic scenario model and the test condition information, a dynamic test scenario corresponding to the simulation test scenario is generated.

[0058] An embodiment of the present application also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for generating a simulation test scenario for an intelligent connected vehicle as described above are performed.

[0059] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for generating a simulation test scenario for an intelligent connected vehicle as described above are executed.

[0060] The method and device for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application obtain the automatic driving function parameters of the target vehicle in the intelligent connected vehicle according to the pre-defined factory function architecture of the target vehicle that is expected to undergo an automatic driving simulation test; based on the automatic driving function parameters and the test requirements corresponding to the automatic driving simulation test, the scene feature information for generating the simulation test scenario is determined according to the scene classification features corresponding to a preset scene element model; the scene element model is a feature element model pre-established for an expected functional safety test in a vehicle automatic driving test; based on the scene feature information, a simulation test scenario for the target vehicle to undergo an automatic driving simulation test is generated by combining dynamic and static scenes.

[0061] Compared with the existing technology in which the autonomous driving test for intelligent connected vehicles is mainly a vehicle safety system test centered on quality assurance, and the testing method is carried out through the prevention, detection and elimination of random hardware failures and systematic failures in the scenario established by this test, the autonomous driving function parameters are obtained from the pre-defined factory function architecture of the intelligent connected vehicle, and combined with the test requirements of the autonomous driving test, the scene feature information is determined according to the scene classification characteristics corresponding to the scene element model established in advance for the expected functional safety test in the vehicle autonomous driving test, and then a simulation test scenario for the vehicle autonomous driving simulation test is generated by combining dynamic and static scenes, which improves the flexibility and applicability of the expected functional safety test of autonomous driving, thereby improving the comprehensiveness and accuracy of the autonomous driving test of intelligent connected vehicles.

[0062] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 One of the flowcharts of a method for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application;

[0065] Figure 2 A second flowchart of a method for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application;

[0066] Figure 3 A generation effect diagram of a simulation test scenario provided in an embodiment of the present application;

[0067] Figure 4 One of the structural schematic diagrams of a device for generating a simulation test scenario of an intelligent connected vehicle provided in an embodiment of the present application;

[0068] Figure 5 A second structural diagram of a device for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application;

[0069] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0071] Research has found that, at present, autonomous driving tests for intelligent connected vehicles are mainly vehicle safety system tests centered on quality assurance. In the scenarios established by this test, tests are carried out through the prevention, detection and elimination of random hardware failures and systematic failures, which are less applicable to autonomous driving vehicles. In addition, in actual operation, autonomous driving vehicles may have non-fault safety issues due to insufficient design, performance limitations or external environmental factors, which cannot be reflected in this test scenario, reducing the comprehensiveness and accuracy of vehicle autonomous driving tests.

[0072] For example, when analyzing the testing needs of autonomous vehicles at different R&D stages, the EU PEGASUS project system divides scenarios into functional scenarios, logical scenarios, specific scenarios, and abstract scenario levels based on the degree of abstraction and expression. In combination with test requirements, the scenarios are divided into multiple levels, including road layer, traffic facility layer, temporarily adjusted traffic facility layer, moving object layer, environmental status layer, and communication layer.

[0073] Specifically, firstly, the PEGASUS project system is highly complex. For developers and testers, understanding and applying this layering may require high expertise and time costs; secondly, there may be intersections and overlaps between different layers. For example, the moving object layer and the environmental state layer may be difficult to distinguish clearly in some cases, leading to confusion and redundancy in the design of test scenarios; among them, when simulating and testing the communication protocols and data exchange of autonomous driving systems, the independent setting of the communication layer may complicate the interaction and coordination with other layers; finally, an overly detailed hierarchy may limit the flexibility of scenario design, making it more difficult to adapt to new testing requirements or changing technical environments.

[0074] Exemplarily, the PEGASUS method uses a six-layer model to describe the test scenario, including: road model (road layer), road facilities and rules model (traffic facilities layer), temporary modification and event model (temporarily adjusted traffic facilities layer), moving object model (moving object layer), environmental condition model (environmental state layer) and digital information model (communication layer).

[0075] Among them, the road model includes road geometry, slope, curvature, intersections and lanes; the road facility and rule model includes traffic signs, signal lights, speed limit signs, stop lines, shoulders and related traffic rules; temporary modification and event models include road construction, traffic accidents, weather events and emergencies; the moving object model includes traffic participants related to the target vehicle, such as other vehicles, pedestrians, bicycles and animals, and their movement status; the environmental condition model includes light conditions, weather conditions and road conditions; the digital information model includes communication information between the vehicle and the external environment (V2X) and map data.

[0076] Based on this, an embodiment of the present application provides a method for generating a simulation test scenario for an intelligent connected vehicle. The method obtains the autonomous driving function parameters from the pre-defined factory function architecture of the intelligent connected vehicle, and combines the test requirements of the autonomous driving test. The scene feature information is determined according to the scene classification characteristics corresponding to the scene element model established in advance for the expected functional safety test in the vehicle autonomous driving test. A simulation test scenario for the vehicle autonomous driving simulation test is generated by combining dynamic and static scenes, thereby improving the flexibility and applicability of the expected functional safety test of autonomous driving, and thereby improving the comprehensiveness and accuracy of the autonomous driving test of the intelligent connected vehicle.

[0077] See also Figure 1 , Figure 1 This is one of the flow charts of a method for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application. Figure 1 As shown in, the method for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application includes:

[0078] S101. For a target vehicle in the intelligent connected vehicle, obtain the autonomous driving function parameters of the target vehicle according to the pre-defined factory function architecture of the target vehicle for which an autonomous driving simulation test is desired.

[0079] It should be noted that for the target vehicles among the intelligent connected vehicles, the intelligent connected vehicles refer to the organic combination of the Internet of Vehicles and smart cars. By carrying on-board sensors, controllers, actuators and other devices, and integrating modern communication and network technologies, a new generation of cars are created to realize the intelligent information exchange and sharing between vehicles and people, vehicles, roads, and background. The purpose is that intelligent connected vehicles can autonomously identify the surrounding environment, make intelligent decisions and collaborative control through perception, decision-making, control and other technical means, and achieve safe and efficient driving.

[0080] When a vehicle leaves the factory, the functional architecture of the entire vehicle will be pre-defined, that is, the factory functional architecture will be pre-defined for the target vehicle that is expected to undergo autonomous driving simulation testing.

[0081] Among them, when defining the factory functional architecture of the target vehicle, it is broken down into four parts. The functional architecture is defined by creating vehicle-level functions, then the sub-function description and component splitting are carried out, and finally, the system safety and response strategy is formulated, as well as the specific content of each part.

[0082] Specifically, the pre-defined factory functional architecture includes vehicle-level functions, functional architecture definition, sub-function description and component splitting, and system safety and response strategy.

[0083] Exemplarily, the vehicle-level function is a description of the overall functions to be performed by the autonomous driving system, including the automation level and autonomous driving operating range (ODD) corresponding to the vehicle-level autonomous driving; the functional architecture is defined as a sorted-out overall system description architecture, such as environmental perception and perception information processing, decision-making system, execution system, human-computer interaction system and driver monitoring system; sub-function description and component splitting include sub-function descriptions based on the autonomous driving system architecture, as well as a description of the system split into software, hardware and interface levels; system safety and response strategies include specified safety and response strategies for autonomous driving systems to enable the system to reach and maintain a reasonable level of safety.

[0084] In this step, based on the pre-defined factory functional architecture of the target vehicle for which the autonomous driving simulation test is expected, the performance parameters of the autonomous driving system of the vehicle for which the autonomous driving simulation test is expected are analyzed and determined in the factory functional architecture, and the autonomous driving functional parameters indicating the performance and functions of the autonomous driving system of the target vehicle are obtained.

[0085] S102. Based on the autonomous driving function parameters and the test requirements corresponding to the autonomous driving simulation test, determine the scene feature information used to generate the simulation test scene according to the scene classification features corresponding to the preset scene element model.

[0086] It should be noted that the popularization of autonomous driving technology requires public trust. Only through strict safety verification and clear safety standards can the public's confidence in this new technology be enhanced. The expected functional safety has become an important part of autonomous driving technology. The requirements of expected functional safety enable potential risks to be identified and evaluated during the design and testing phases of the vehicle, so as to promote continuous system optimization of the vehicle and improve system performance.

[0087] Specifically, the intended functional safety technology is mainly about the in-depth understanding of the development of autonomous driving technology and safety issues. As the autonomous driving technology leaps from Level 2 to Level 3, in response to the problem that the current safety assurance measures cannot fully meet the safety needs of autonomous driving vehicles, the intended functional safety (Safety of The Intended Functionality, SOTIF) for autonomous driving systems is proposed; intended functional safety focuses on safety issues caused by design deficiencies, performance limitations or external environmental factors even if the system operates normally as designed.

[0088] Among them, the scenario element model is a feature element model pre-established for the expected functional safety test in the vehicle autonomous driving test.

[0089] Specifically, the scene element model includes a road model, an environment model, a vehicle model and a traffic participant model; wherein the road model is a physical infrastructure element in the scene; the environment model is an important source of perceived behavior; the vehicle model is used to build dynamic scenes; and the traffic participant model specifies the behavior and interaction relationship.

[0090] Here, the scenario element model is different from the scenario hierarchy theory of the PEGASUS method. At the same time, the scenario element model can meet the analysis and use of the intended functional safety (SOTIF), and refines the vague standards in the PEGASUS method at the parameter level, which is more practical.

[0091] Furthermore, the scene classification features include: road features, main vehicle features, traffic participant features and environmental features; wherein, road features are used to generate static scenes; main vehicle features and traffic participant features are used to generate dynamic scenes; and environmental features are used to determine environmental factors.

[0092] Here, for the six-layer model used by the PEGASUS method, the road features in the scene element model include the contents included in the road model, road facilities and rule model; the traffic participant features include the contents included in the digital information model and the moving object model; the environmental features include the contents included in the temporary modification and event model and the environmental condition model; the main vehicle features are the basis for generating a dynamic scene model, and have no corresponding basis with the six-layer model used by the PEGASUS method.

[0093] In this way, the preset scenario element model simplifies the theoretical structure of expected functional safety, reduces the complexity of element analysis, and makes the development and testing process of the autonomous driving system more efficient and easier to manage; fewer levels can increase the flexibility of scenario design and make it easier to adapt to the ever-changing technological environment and emerging testing needs; in addition, by merging related levels, the intersection and overlap between different levels can be reduced, and confusion and redundancy in test scenario design can be reduced; the scenario element model is easier to be understood and used by team members from different disciplinary backgrounds, thereby promoting interdisciplinary cooperation and accelerating the development of autonomous driving technology; at the same time, since the number of levels and details that need to be processed is reduced, the cost of development and testing is reduced, and resources can be more concentrated on the core testing phase of the vehicle.

[0094] In this step, during the specific implementation, first, obtain the user's test requirements for the target vehicle's autonomous driving test; then, determine the scene classification features corresponding to the preset scene element model; finally, in the autonomous driving function parameters and test requirements, determine the scene feature information used to generate the simulation test scene in accordance with the division rules of the scene classification features.

[0095] Exemplarily, an example of the scenario feature information used to generate a simulation test scenario is shown in the following table.

[0096]

[0097]

[0098] S103. Based on the scene feature information, a simulation test scene for performing an autonomous driving simulation test on a target vehicle is generated by combining dynamic and static scenes.

[0099] Here, the scene feature information corresponding to the road feature is the first scene feature information; the scene feature information corresponding to the main vehicle feature is the second scene feature information; the scene feature information corresponding to the traffic participant feature is the third scene feature information; and the scene feature information corresponding to the environmental feature is the fourth scene feature information.

[0100] In this step, during the specific implementation, first, based on the first scene feature information, a static test scene corresponding to the simulation test scene is generated; then, based on the static test scene, the second scene feature information and the third scene feature information, a dynamic test scene corresponding to the simulation test scene is generated; thereafter, based on the fourth scene feature information, the environmental factors corresponding to the simulation test scene are determined; finally, the dynamic test scene and the environmental factors are combined to generate a simulation test scene for the target vehicle to perform autonomous driving simulation testing.

[0101] In one implementation of the present application, during specific implementation, step S103 may include:

[0102] S1031. Generate a static test scene corresponding to the simulation test scene based on the first scene feature information corresponding to the road feature.

[0103] In this step, during the specific implementation, first, based on the first scene feature information, the map data, road data and static element data corresponding to the simulation test scene are determined; then, based on the map data and road data, a road model corresponding to the simulation test scene is constructed; finally, the static element data is integrated into the road model to generate a static test scene corresponding to the simulation test scene.

[0104] In one implementation of the present application, during specific implementation, step S1031 may include:

[0105] S10311. Based on the first scene feature information, determine the map data, road data and static element data corresponding to the simulation test scene.

[0106] In this step, road feature data is collected in the first scene feature information to determine map data, road data, and static element data corresponding to the simulation test scene.

[0107] Among them, map data can be obtained through satellite remote sensing, LiDAR scanning, drone aerial photography and other methods when historical data is collected; in addition, for areas that map data cannot cover or require special attention, field measurements can be carried out to obtain more detailed and accurate map data and road data.

[0108] Furthermore, static element data includes traffic signs and markings and infrastructure; for example, infrastructure includes buildings, bridges, tunnels, intersections, etc.

[0109] S10312. Construct a road model corresponding to the simulation test scenario based on the map data and the road data.

[0110] In this step, based on the map data and road data, a road model corresponding to the simulation test scenario is constructed using a preset 3D modeling tool and a geographic information system.

[0111] Exemplarily, the preset 3D modeling tools include AutoCAD, SketchUp, and 3ds Max, etc.; the preset geographic information system includes GIS software.

[0112] Among them, the road model corresponding to the simulation test scene includes material and texture parts to enhance the realism of the road model; for example, different material properties can be added for different types of road surfaces (such as asphalt, concrete); texture maps can be added for trees, buildings, etc.

[0113] S10313. Integrate the static element data into the road model to generate a static test scene corresponding to the simulation test scene.

[0114] In this step, based on the road model, the static element data is integrated into the road model to generate a static test scene corresponding to the simulation test scene, and a scene file corresponding to the static test scene is determined.

[0115] S1032. Generate a dynamic test scene corresponding to the simulation test scene based on the static test scene, the second scene feature information corresponding to the main vehicle feature, and the third scene feature information corresponding to the traffic participant feature.

[0116] In this step, during the specific implementation, first, the static test scene is initialized and an initialized dynamic scene model is constructed; then, based on the second scene feature information and the third scene feature information, the test condition information corresponding to the simulation test scene is determined; finally, based on the initialized dynamic scene model and the test condition information, a dynamic test scene corresponding to the simulation test scene is generated.

[0117] In one implementation of the present application, during specific implementation, step S1032 may include:

[0118] S10321. Initialize the static test scene to construct an initialized dynamic scene model.

[0119] In this step, based on the logical and spatial relationships of the static test scene, the static test scene is integrated with the dynamic elements, and the relevant parameters of the dynamic scene model are configured according to the test requirements to construct an initialized dynamic scene model.

[0120] S10322. Determine test condition information corresponding to the simulation test scenario based on the second scenario feature information and the third scenario feature information.

[0121] In this step, the second scenario feature information and the third scenario feature information are collected and integrated to determine the test condition information corresponding to the simulation test scenario, so as to form a data input package for generating a dynamic test scenario.

[0122] S10323. Generate a dynamic test scenario corresponding to the simulation test scenario based on the initialized dynamic scenario model and the test condition information.

[0123] In this step, based on the initialized dynamic scene model, the test condition information is integrated and fused into the initialized dynamic scene model, a dynamic test scene corresponding to the simulation test scene is generated, and a scene file corresponding to the dynamic test scene is determined.

[0124] S1033. Determine the environmental factors corresponding to the simulation test scenario based on the fourth scenario feature information corresponding to the environmental features.

[0125] In this step, data analysis is performed on the fourth scenario characteristic information to determine environmental factors in the fourth scenario characteristic information for generating a simulation test scenario.

[0126] S1034. Combine the dynamic test scenario and the environmental factors to generate a simulation test scenario for the target vehicle to perform an autonomous driving simulation test.

[0127] In this step, the scene files corresponding to the static test scene and the scene files corresponding to the dynamic test scene are matched and synthesized, and the environmental factors are combined with the synthesized files to generate a simulation test scene for the target vehicle to perform autonomous driving simulation testing.

[0128] Specifically, use the preset simulation test scenario editor to layout and set the scenario files corresponding to the static test scenario and the dynamic test scenario according to the actual roads and traffic rules; and perform parameterized configuration on each element in the simulation scenario, such as vehicle speed, acceleration, road friction coefficient, etc., to simulate different test conditions; finally, combine environmental factors to improve the authenticity and accuracy of the simulation scenario.

[0129] For example, see Figure 3 , Figure 3 This is a generation effect diagram of a simulation test scenario provided in an embodiment of the present application. Figure 3 As shown in , the road characteristics, environmental characteristics, main vehicle characteristics and traffic participant characteristics are respectively used as input to construct a scenario diagram of the simulation test scenario. For this simulation test scenario, it is necessary to further confirm whether the road characteristics, environmental characteristics, main vehicle characteristics and traffic participant characteristics are within the coverage of the system performance and functions of the target vehicle's autonomous driving technology (ODD).

[0130] Optional, see Figure 2 , Figure 2 This is a second flow chart of a method for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application. Figure 2 As shown in, in addition to the method for generating a smart connected vehicle simulation test scenario provided by an embodiment of the present application described in steps S101 to S103, steps S104 to S105 are also included. Specifically, steps S104 to S105 are used to illustrate a method for evaluating the generated vehicle simulation test scenario to ensure the accuracy and safety of the simulation test scenario generation.

[0131] S104: Use the target vehicle to perform an autonomous driving simulation test in the simulation test scenario, and obtain safety test data corresponding to the autonomous driving simulation test.

[0132] In this step, before conducting an actual autonomous driving test on the target vehicle, the generated simulation test scenario is evaluated, a simulated autonomous driving test is conducted in the simulation test scenario using the target vehicle, and safety test data corresponding to the simulated autonomous driving test is obtained.

[0133] The safety test data includes, but is not limited to, the number of accidents occurring in the simulation test scenario and the degree of vehicle damage to the target vehicle.

[0134] S105. Determine an evaluation result of the simulation test scenario according to the safety test data.

[0135] In this step, during the specific implementation, first, based on the number of accidents, the out-of-control degree parameter corresponding to the simulation test scenario is determined; then, based on the degree of damage to the vehicle, the hazard degree parameter corresponding to the simulation test scenario is determined; thereafter, it is determined whether the out-of-control degree parameter and the hazard degree parameter both belong to the corresponding evaluation parameter range; finally, based on the judgment result, the evaluation result of the simulation test scenario is determined.

[0136] In one implementation of the present application, during specific implementation, step S105 may include:

[0137] S1051. Determine a loss of control degree parameter corresponding to the simulation test scenario based on the number of accidents included in the safety test data.

[0138] In this step, the number of accidents and the total number of occurrences of the logical scenarios of the simulated autonomous driving test are proportionally calculated to determine the out-of-control degree parameters corresponding to the simulation test scenarios.

[0139] S1052. Determine a hazard parameter corresponding to the simulation test scenario based on the degree of vehicle damage included in the safety test data.

[0140] In this step, the percentage values ​​of the vehicle damage degree of multiple simulated accidents are averaged, and the average calculation result is determined as the criticality parameter corresponding to the simulation test scenario.

[0141] S1053: Determine whether the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals.

[0142] In this step, the out-of-control degree parameter is compared with the first evaluation parameter interval corresponding to the out-of-control degree parameter, and at the same time, the hazard degree parameter is compared with the second evaluation parameter interval corresponding to the hazard degree parameter, and comparison results of the out-of-control degree parameter and the hazard degree parameter are obtained respectively to determine whether the out-of-control degree parameter and the hazard degree parameter both belong to the first evaluation parameter interval and the second evaluation parameter interval.

[0143] In one possible implementation of the present application, the first evaluation parameter interval corresponding to the out-of-control degree parameter and the second evaluation parameter interval corresponding to the hazard degree parameter are both specifically calibrated according to actual test requirements and the automatic driving function parameters of the target vehicle.

[0144] S1054: If the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals, then determining that the evaluation result of the simulation test scenario is qualified.

[0145] In this step, if the out-of-control degree parameter and the hazard degree parameter both belong to the corresponding first evaluation parameter interval and second evaluation parameter interval, indicating that the accuracy and safety of the simulation test scenario meet the test requirements and needs of the autonomous driving test, then the evaluation result of the simulation test scenario is determined to be qualified.

[0146] S1055. If at least one of the out-of-control degree parameter and the criticality degree parameter does not belong to the corresponding evaluation parameter interval, determine that the evaluation result of the simulation test scenario is unqualified.

[0147] In this step, if at least one of the out-of-control degree parameter and the hazard degree parameter does not belong to the corresponding first evaluation parameter interval and second evaluation parameter interval, it indicates that the accuracy and safety of the simulation test scenario do not meet the test requirements and needs of the autonomous driving test, and the evaluation result of the simulation test scenario is determined to be unqualified.

[0148] Furthermore, for simulation test scenarios with unqualified evaluation results, the intelligent connected vehicle simulation test scenarios are regenerated based on the comparison results of specific loss of control parameters and hazard parameters.

[0149] The method for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application obtains the autonomous driving function parameters from the pre-defined factory function architecture of the intelligent connected vehicle, and combines the test requirements of the autonomous driving test, determines the scene feature information according to the scene classification characteristics corresponding to the scene element model established in advance for the expected functional safety test in the vehicle autonomous driving test, and then generates a simulation test scenario for the vehicle to perform an autonomous driving simulation test by combining dynamic and static scenes, thereby improving the flexibility and applicability of the expected functional safety test of autonomous driving, and thereby improving the comprehensiveness and accuracy of the autonomous driving test of the intelligent connected vehicle.

[0150] See also Figure 4 , Figure 5 , Figure 4 This is one of the structural schematic diagrams of a device for generating a simulation test scenario of an intelligent connected vehicle provided in an embodiment of the present application. Figure 5 The second structural schematic diagram of a device for generating a simulation test scenario for an intelligent connected vehicle provided in an embodiment of the present application.

[0151] like Figure 4 As shown in , the generating device 400 includes:

[0152] The parameter acquisition module 410 is used to acquire the automatic driving function parameters of the target vehicle in the intelligent connected vehicle according to the pre-defined factory function architecture of the target vehicle for which the automatic driving simulation test is expected to be performed;

[0153] A feature determination module 420 is used to determine scene feature information for generating a simulation test scene based on the autonomous driving function parameters and the test requirements corresponding to the autonomous driving simulation test and according to scene classification features corresponding to a preset scene element model; the scene element model is a feature element model pre-established for an expected functional safety test in a vehicle autonomous driving test;

[0154] The scene generation module 430 is used to generate a simulation test scene for the target vehicle to perform an autonomous driving simulation test based on the scene feature information by combining dynamic and static scenes.

[0155] Further, such as Figure 5 As shown, the generating device 400 further includes a scene evaluation module 440, and the scene evaluation module 440 is used to:

[0156] Using the target vehicle to perform an autonomous driving simulation test in the simulation test scenario, and obtaining safety test data corresponding to the autonomous driving simulation test;

[0157] An evaluation result of the simulation test scenario is determined based on the safety test data.

[0158] Further, when the scenario evaluation module 440 is used to determine the evaluation result of the simulation test scenario according to the safety test data, the scenario evaluation module 440 is used to:

[0159] Determining a loss of control degree parameter corresponding to the simulation test scenario based on the number of accidents included in the safety test data;

[0160] Determining a criticality parameter corresponding to the simulation test scenario based on the degree of vehicle damage included in the safety test data;

[0161] Determining whether the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals;

[0162] If the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals, determining that the evaluation result of the simulation test scenario is qualified;

[0163] If at least one of the out-of-control degree parameter and the criticality degree parameter does not belong to the corresponding evaluation parameter interval, it is determined that the evaluation result of the simulation test scenario is unqualified.

[0164] Furthermore, when the scenario generation module 430 is used to generate a simulation test scenario for the target vehicle to perform an autonomous driving simulation test by combining dynamic and static scenarios based on the scenario feature information, the scenario generation module 430 is used to:

[0165] Based on the first scene feature information corresponding to the road feature, generating a static test scene corresponding to the simulation test scene;

[0166] Generate a dynamic test scene corresponding to the simulation test scene based on the static test scene, the second scene feature information corresponding to the main vehicle feature, and the third scene feature information corresponding to the traffic participant feature;

[0167] Determining the environmental factors corresponding to the simulation test scenario based on fourth scenario feature information corresponding to the environmental features;

[0168] The dynamic test scenario and the environmental factors are combined to generate a simulation test scenario for the target vehicle to perform an autonomous driving simulation test.

[0169] Further, when the scenario generation module 430 is used to generate a static test scenario corresponding to the simulation test scenario based on the first scenario feature information corresponding to the road feature, the scenario generation module 430 is used to:

[0170] Based on the first scene feature information, determining map data, road data and static element data corresponding to the simulation test scene;

[0171] Based on the map data and the road data, construct a road model corresponding to the simulation test scenario;

[0172] The static element data is integrated into the road model to generate a static test scene corresponding to the simulation test scene.

[0173] Further, when the scenario generation module 430 is used to generate a dynamic test scenario corresponding to the simulation test scenario based on the static test scenario, the second scenario feature information corresponding to the host vehicle feature, and the third scenario feature information corresponding to the traffic participant feature, the scenario generation module 430 is used to:

[0174] Initialize the static test scene to construct an initialized dynamic scene model;

[0175] Determining test condition information corresponding to the simulation test scenario based on the second scenario feature information and the third scenario feature information;

[0176] Based on the initialized dynamic scenario model and the test condition information, a dynamic test scenario corresponding to the simulation test scenario is generated.

[0177] The device for generating simulation test scenarios for intelligent connected vehicles provided in the embodiment of the present application obtains the automatic driving function parameters from the pre-defined factory function architecture of the intelligent connected vehicle, and combines the test requirements of the automatic driving test, determines the scene feature information according to the scene classification characteristics corresponding to the scene element model established in advance for the expected functional safety test in the vehicle automatic driving test, and then generates a simulation test scenario for the vehicle to perform automatic driving simulation testing by combining dynamic and static scenes, thereby improving the flexibility and applicability of the expected functional safety test of the automatic driving, and thereby improving the comprehensiveness and accuracy of the automatic driving test of the intelligent connected vehicle.

[0178] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown in , the electronic device 600 includes a processor 610 , a memory 620 and a bus 630 .

[0179] The memory 620 stores machine-readable instructions executable by the processor 610. When the electronic device 600 is running, the processor 610 communicates with the memory 620 via the bus 630. When the machine-readable instructions are executed by the processor 610, the above-mentioned Figure 1 as well as Figure 2 The steps of the method for generating a simulation test scenario for an intelligent connected vehicle in the method embodiment shown, and the specific implementation method thereof can be referred to the method embodiment, which will not be repeated here.

[0180] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 as well as Figure 2 The steps of the method for generating a simulation test scenario for an intelligent connected vehicle in the method embodiment shown, and the specific implementation method thereof can be referred to the method embodiment, which will not be repeated here.

[0181] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0182] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0183] 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 distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0185] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several 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 application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0186] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for generating a simulation test scenario for an intelligent connected vehicle, characterized in that: The generation method comprises: For a target vehicle among intelligent connected vehicles, the automatic driving function parameters of the target vehicle are obtained according to the pre-defined factory function architecture of the target vehicle for which the automatic driving simulation test is expected to be performed; Based on the autonomous driving function parameters and the test requirements corresponding to the autonomous driving simulation test, scene feature information for generating a simulation test scene is determined according to scene classification features corresponding to a preset scene element model; the scene element model is a feature element model pre-established for an expected functional safety test in a vehicle autonomous driving test; Based on the scene feature information, a simulation test scene for the target vehicle to perform an autonomous driving simulation test is generated by combining dynamic and static scenes.

2. The method according to claim 1, characterized in that After generating a simulation test scene for the target vehicle to perform an autonomous driving test by combining dynamic and static scenes, the method further includes: Using the target vehicle to perform an autonomous driving simulation test in the simulation test scenario, and obtaining safety test data corresponding to the autonomous driving simulation test; An evaluation result of the simulation test scenario is determined based on the safety test data.

3. The method according to claim 2, characterized in that Determining the evaluation result of the simulation test scenario according to the safety test data includes: Determining a loss of control degree parameter corresponding to the simulation test scenario based on the number of accidents included in the safety test data; Determining a criticality parameter corresponding to the simulation test scenario based on the degree of vehicle damage included in the safety test data; Determining whether the out-of-control degree parameter and the criticality degree parameter both belong to corresponding evaluation parameter intervals; If both the out-of-control degree parameter and the criticality degree parameter belong to the corresponding evaluation parameter interval, determining that the evaluation result of the simulation test scenario is qualified; If at least one of the out-of-control degree parameter and the criticality degree parameter does not belong to the corresponding evaluation parameter interval, it is determined that the evaluation result of the simulation test scenario is unqualified.

4. The method according to claim 1, characterized in that: The scene classification features include: road features, main vehicle features, traffic participant features and environment features.

5. The method according to claim 4, characterized in that The method of generating a simulation test scene for a target vehicle to perform an automatic driving simulation test based on the scene feature information by combining dynamic and static scenes includes: Based on the first scene feature information corresponding to the road feature, generating a static test scene corresponding to the simulation test scene; Generate a dynamic test scene corresponding to the simulation test scene based on the static test scene, the second scene feature information corresponding to the main vehicle feature, and the third scene feature information corresponding to the traffic participant feature; Determining the environmental factors corresponding to the simulation test scenario based on fourth scenario feature information corresponding to the environmental features; The dynamic test scenario and the environmental factors are combined to generate a simulation test scenario for the target vehicle to perform an autonomous driving simulation test.

6. The method according to claim 5, characterized in that The generating, based on the first scene feature information corresponding to the road feature, a static test scene corresponding to the simulation test scene, comprises: Based on the first scene feature information, determining map data, road data and static element data corresponding to the simulation test scene; Based on the map data and the road data, construct a road model corresponding to the simulation test scenario; The static element data is integrated into the road model to generate a static test scene corresponding to the simulation test scene.

7. The method according to claim 5, characterized in that The generating of the dynamic test scene corresponding to the simulation test scene based on the static test scene, the second scene feature information corresponding to the main vehicle feature and the third scene feature information corresponding to the traffic participant feature comprises: Initialize the static test scene to construct an initialized dynamic scene model; Determining test condition information corresponding to the simulation test scenario based on the second scenario feature information and the third scenario feature information; Based on the initialized dynamic scenario model and the test condition information, a dynamic test scenario corresponding to the simulation test scenario is generated.

8. A device for generating a simulation test scenario for an intelligent connected vehicle, characterized in that: The generating device comprises: A parameter acquisition module, for acquiring the automatic driving function parameters of a target vehicle in the intelligent connected vehicle according to a pre-defined factory function architecture of the target vehicle for which an automatic driving simulation test is desired; a feature determination module, configured to determine, based on the autonomous driving function parameters and the test requirements corresponding to the autonomous driving simulation test, scene feature information for generating a simulation test scene according to scene classification features corresponding to a preset scene element model; the scene element model is a feature element model pre-established for an expected functional safety test in a vehicle autonomous driving test; The scenario generation module is used to generate a simulation test scenario for the target vehicle to perform an autonomous driving simulation test based on the scenario feature information by combining dynamic and static scenarios.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus. When the processor is running, the machine-readable instructions execute the steps of the method for generating a simulation test scenario for an intelligent connected vehicle as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for generating a simulation test scenario for an intelligent connected vehicle as described in any one of claims 1 to 7 are executed.

Images