Method, device and electronic device for generating automatic driving simulation scene

Abstract

The present invention provides a method, device and electronic device for generating an autonomous driving simulation scene, the method comprising: obtaining vehicle driving scene description information, and generating a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information; obtaining vehicle model information, and generating a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information; obtaining road environment information, and generating a road environment model that meets the OpenSCENARIO standard based on the road environment information; obtaining traffic flow information, and generating a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information; combining and synthesizing the scene description language, the vehicle model, the road environment model and the traffic flow model to obtain an autonomous driving simulation scene. The present invention can solve the technical problems in the prior art that the scene of the autonomous driving simulation scene is relatively single, the customizability is weak, and the generation cannot be automatically processed.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a method, device and electronic equipment for generating an automatic driving simulation scene. Background Art

[0002] The continuous development of autonomous driving technology makes field testing costly and may pose safety risks. Therefore, simulation-based autonomous driving system testing has become very important.

[0003] The current method of generating scenes for autonomous driving simulation uses traditional scene generators and editing tools, which usually have specific scene description languages ​​or standards, limiting the flexibility and scalability of generated scenes. The scenes are relatively simple and have weak customizability. These tools usually require manual operations and user input to create and edit scenes and lack automated processing capabilities. Summary of the invention

[0004] In view of this, it is necessary to provide a method, device and electronic device for generating an autonomous driving simulation scene, so as to solve the technical problems in the prior art that the autonomous driving simulation scene is relatively single, has weak customizability and cannot be automatically processed and generated.

[0005] In order to achieve the above object, the present invention provides a method for generating an autonomous driving simulation scene, comprising:

[0006] Acquire vehicle driving scene description information, and generate a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information;

[0007] Acquire vehicle model information, and generate a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information;

[0008] Acquire road environment information, and generate a road environment model that meets the OpenSCENARIO standard based on the road environment information;

[0009] Acquire traffic flow information, and generate a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information;

[0010] The scene description language, the vehicle model, the road environment model and the traffic flow model are combined and synthesized to obtain an autonomous driving simulation scene.

[0011] Furthermore, the step of generating a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information includes:

[0012] Performing semantic analysis and information extraction on the vehicle driving scene description information based on natural language text to obtain data elements, and constructing preliminary scene description information based on the data elements and a preset data structure;

[0013] Based on a preset mapping standard, the preliminary description information of the scene is mapped into the OpenSCENARIO standard to generate an initial description language;

[0014] The initial description language is verified, and when it is determined that the syntax of the initial description language meets the OpenSCENARIO standard, the initial description language is used as a scene description language that meets the OpenSCENARIO standard.

[0015] Further, the verifying the initial description language includes:

[0016] The initial description language is verified based on pattern matching or syntax analysis.

[0017] Furthermore, the method for generating an autonomous driving simulation scene further includes:

[0018] In the case where it is determined that the syntax of the initial description language does not meet the OpenSCENARIO standard, determining the information entropy of the initial description language;

[0019] Based on the information entropy, new words are discovered, confusion sets of new words are found, and candidate recall processing is performed on the confusion sets to obtain candidate sets;

[0020] The candidate set is sorted based on the N-Gram model to generate a new initial description language, and the new initial description language is used as a scene description language that meets the OpenSCENARIO standard.

[0021] Furthermore, the scenario description language includes: vehicle starting position, vehicle travel path, road selection information and traffic flow requirements;

[0022] The combining and synthesizing the scene description language, the vehicle model, the road environment model and the traffic flow model to obtain an automatic driving simulation scene includes:

[0023] The vehicle model is associated with the vehicle starting position and the vehicle driving path, the road environment model is associated with the road selection information, and the traffic flow model is associated with the traffic flow requirement to obtain an automatic driving simulation scenario.

[0024] Furthermore, the obtaining of traffic flow information includes:

[0025] Simulate the behavior of participants in the vehicle driving environment and generate diverse traffic flow information in the simulation scene.

[0026] Furthermore, the vehicle driving scene description information includes: vehicle starting position, vehicle target position, road selection information and traffic flow information;

[0027] The vehicle model information includes: the appearance and dynamic parameters of the vehicle;

[0028] The road environment information includes: road markings, road conditions and scenery information;

[0029] The traffic flow information includes: vehicle type, vehicle density and vehicle speed distribution information.

[0030] The present invention also provides a device for generating an automatic driving simulation scene, comprising:

[0031] A first generating module is used to obtain vehicle driving scene description information, and generate a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information;

[0032] A second generation module is used to obtain vehicle model information and generate a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information;

[0033] A third generation module is used to obtain road environment information and generate a road environment model that meets the OpenSCENARIO standard based on the road environment information;

[0034] A fourth generation module, used to obtain traffic flow information, and generate a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information;

[0035] A synthesis module is used to combine and synthesize the scene description language, the vehicle model, the road environment model and the traffic flow model to obtain an automatic driving simulation scene.

[0036] The present invention also provides an electronic device, comprising a memory and a processor, wherein:

[0037] The memory is used to store programs;

[0038] The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for generating an autonomous driving simulation scene as described in any one of the above items.

[0039] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating an autonomous driving simulation scene as described in any one of the above items is implemented.

[0040] The beneficial effect of adopting the above-mentioned implementation method is: the method, device and electronic device for generating the autonomous driving simulation scene provided by the present invention, by constructing a scene description language, a vehicle model, a road environment model and a traffic flow model that meet the OpenSCENARIO standard, the scene description language, the vehicle model, the road environment model and the traffic flow model are combined and synthesized to obtain an autonomous driving simulation scene. According to actual needs, the scene environment and vehicle parameters required for the simulation can be set and adjusted to perform model construction and scene synthesis. For example, define the friction coefficient, weather conditions, lighting, etc. of the road, as well as the dynamic characteristics, sensor parameters, etc. of the vehicle. Through appropriate parameter settings, ensure that the simulation scene can reflect the richness and variability of the actual driving scene, and design and write a storyline that meets the OpenSCENARIO standard. In the storyline, the behavior, interaction, tasks and trigger events of the participants can be defined through the scenario description language, vehicle model, road environment model and traffic flow model, creating a coherent scenario experience, simulating various situations and challenges in real driving scenarios, and solving the problem of relatively single scenarios in autonomous driving simulation scenarios in existing technologies. Users only need to input vehicle driving scenario description information, vehicle model information, road environment information and traffic flow information to automatically generate autonomous driving simulation scenarios, which is highly customizable. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 A flowchart of an embodiment of a method for generating an autonomous driving simulation scene provided by the present invention;

[0043] Figure 2 A schematic diagram of the structure of an embodiment of a device for generating an autonomous driving simulation scene provided by the present invention;

[0044] Figure 3 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0046] In the description of the embodiments of the present application, unless otherwise specified, “plurality” means two or more.

[0047] The terms "including" and "having" and any variations thereof in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or equipment comprising a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or equipment.

[0048] The naming or numbering of the steps in the embodiments of the present invention does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The execution order of the named or numbered process steps can be changed according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0049] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0050] The present invention provides a method, device and electronic device for generating an autonomous driving simulation scene, which are described below respectively.

[0051] like Figure 1 As shown, the present invention provides a method for generating an autonomous driving simulation scene, which includes:

[0052] Acquire vehicle driving scene description information, and generate a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information;

[0053] Acquire vehicle model information, and generate a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information;

[0054] Acquire road environment information, and generate a road environment model that meets the OpenSCENARIO standard based on the road environment information;

[0055] Acquire traffic flow information, and generate a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information;

[0056] The scene description language, the vehicle model, the road environment model and the traffic flow model are combined and synthesized to obtain an autonomous driving simulation scene.

[0057] The vehicle driving scene description information includes: vehicle starting position, vehicle target position, road selection information and traffic flow information;

[0058] The vehicle model information includes: the appearance and dynamic parameters of the vehicle;

[0059] The road environment information includes: road markings, road conditions and scenery information;

[0060] The traffic flow information includes: vehicle type, vehicle density and vehicle speed distribution information.

[0061] It is understandable that the OpenSCENARIO standard is a data format for describing dynamic scenes. The vehicle driving scene description information may include vehicle starting position, target position, road selection, traffic flow, etc. Users can provide vehicle driving scene description information through a graphical interface or text input to ensure that the generated simulation scene meets user requirements.

[0062] Convert the vehicle driving scene description information input by the user into the description language of the OpenSCENARIO standard, including RoadNetwork, Entities, Storyboard, etc. OpenSCENARIO is an open standard for describing autonomous driving scenes, with good scalability and compatibility. By parsing the scene description information and converting it into the OpenSCENARIO format, it is convenient for subsequent processing and generation.

[0063] The vehicle model generation step is as follows: based on the vehicle model information input by the user, a vehicle model based on the OpenSCENARIO standard is generated. The vehicle model includes information such as the vehicle's appearance and dynamic parameters, and can be customized according to the characteristics and requirements of the actual vehicle. The generated vehicle model will be associated with the starting position and path in the scene description information to ensure that the vehicle travels along the specified route.

[0064] Road environment model generation steps: Generate a road environment model based on the OpenS CENARIO standard based on the road environment information provided by the user. The road environment model includes information such as road markings, road conditions, and scenery, and can be customized according to actual road conditions and needs. The generated road environment model will be associated with the road selection in the scene description information to ensure that the vehicle is driving in a suitable road environment.

[0065] In some embodiments, generating a scene description language that meets the OpenSCEN ARIO standard from the vehicle driving scene description information includes:

[0066] Performing semantic analysis and information extraction on the vehicle driving scene description information based on natural language text to obtain data elements, and constructing preliminary scene description information based on the data elements and a preset data structure;

[0067] Based on a preset mapping standard, the preliminary description information of the scene is mapped into the OpenSCENARIO standard to generate an initial description language;

[0068] The initial description language is verified, and when it is determined that the syntax of the initial description language meets the OpenSCENARIO standard, the initial description language is used as a scene description language that meets the OpenSCENARIO standard.

[0069] Further, the verifying the initial description language includes:

[0070] The initial description language is verified based on pattern matching or syntax analysis.

[0071] It can be understood that the process of generating a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information, that is, the scene description parsing and conversion can be automatically realized, includes the following steps:

[0072] Data extraction: First, use natural language processing or other related technologies to perform semantic analysis and information extraction on the input scene description information. This includes extracting keywords, entities, actions, conditions and other elements from natural language text, and establishing corresponding data structures to represent scene information.

[0073] Data mapping: Mapping the data extracted from the scene description information to the description language of the OpenSCENARIO standard. This can be achieved by establishing mapping rules or templates. Rules can be defined based on the semantics and structure of the scene description information to determine how to map each element to the corresponding element in the OpenSCENARIO standard. For example, mapping actions to OpenSCENARIO action scripts, mapping conditions to OpenSCENARIO trigger conditions, etc.

[0074] Syntax generation: Based on the data mapping, the developed automation tool is used to generate the description language that conforms to the OpenSCENARIO syntax rules. This can be achieved through a rule-based grammar generator, which will generate a standard OpenSCENARIO description language file based on the mapped data structure.

[0075] Verification and Revision: Generated OpenSCENARIO description language files should be verified to ensure their syntactic correctness and compliance with the OpenSCENARIO standard. Verification tools can use pattern matching, syntax analysis and other techniques to check whether the generated files conform to the standard specifications. If errors or incomplete parts are found, error reports can be generated and revised accordingly.

[0076] In some embodiments, the method for generating an autonomous driving simulation scene further includes:

[0077] In the case where it is determined that the syntax of the initial description language does not meet the OpenSCENARIO standard, determining the information entropy of the initial description language;

[0078] Based on the information entropy, new words are discovered, confusion sets of new words are found, and candidate recall processing is performed on the confusion sets to obtain candidate sets;

[0079] The candidate set is sorted based on the N-Gram model to generate a new initial description language, and the new initial description language is used as a scene description language that meets the OpenSCENARIO standard.

[0080] It can be understood that information entropy refers to the average amount of information in a specific information after excluding redundancy. New word discovery based on information entropy does not rely on any existing vocabulary. It only extracts all text fragments that may become words in a large-scale corpus based on the common characteristics of words, regardless of whether they are new words or old words. Then, all the extracted words are compared with the existing vocabulary to find new words.

[0081] Specifically, all text sentences contained in the corpus corresponding to the initial description language are segmented, and all the different word strings segmented are used as candidate word strings; for the candidate word strings whose frequency in the corpus exceeds a fixed threshold, their internal aggregation degree and external discrete information entropy are calculated, and the candidate target word string is further judged whether it is a target new word based on the internal aggregation degree and external discrete information entropy of the candidate word string. The internal aggregation degree and external discrete information entropy of the candidate word string are used, and the stability, independence and integrity of the candidate word string are considered at the same time, which can effectively discover new words appearing on the Internet.

[0082] In some embodiments, the scenario description language includes: vehicle starting position, vehicle travel path, road selection information, and traffic flow requirements;

[0083] The combining and synthesizing the scene description language, the vehicle model, the road environment model and the traffic flow model to obtain an automatic driving simulation scene includes:

[0084] The vehicle model is associated with the vehicle starting position and the vehicle driving path, the road environment model is associated with the road selection information, and the traffic flow model is associated with the traffic flow requirement to obtain an automatic driving simulation scenario.

[0085] It is understood that the generated vehicle model, road environment model and traffic flow model are combined and synthesized according to the OpenSCENARIO standard to generate a complete autonomous driving simulation scene. The software program that performs this step will automatically generate a scene instance based on information such as the vehicle's starting position, path, road environment and traffic flow, and output the corresponding simulation scene file.

[0086] In some embodiments, the obtaining of traffic flow information includes:

[0087] Simulate the behavior of participants in the vehicle driving environment and generate diverse traffic flow information in the simulation scene.

[0088] It can be understood that the specific steps of traffic flow generation are: based on the traffic flow information input by the user, a traffic flow model based on the OpenSCENARIO standard is generated. The traffic flow model includes information such as vehicle type, vehicle density, and vehicle speed distribution, and can be customized according to actual traffic conditions and requirements. The generated traffic flow model will be associated with the traffic flow requirements in the scene description information to ensure that the appropriate number and type of vehicles participate in the scene.

[0089] The method for generating an autonomous driving simulation scene provided by the present invention includes: obtaining vehicle driving scene description information, and generating a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information; obtaining vehicle model information, and generating a vehicle model that meets the OpenSCE NARIO standard based on the vehicle model information; obtaining road environment information, and generating a road environment model that meets the OpenSCENARIO standard based on the road environment information; obtaining traffic flow information, and generating a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information; combining and synthesizing the scene description language, the vehicle model, the road environment model and the traffic flow model to obtain an autonomous driving simulation scene.

[0090] In the method for generating an autonomous driving simulation scene provided by the present invention, a scene description language, a vehicle model, a road environment model and a traffic flow model that meet the OpenSCE NARIO standard are constructed, and the scene description language, the vehicle model, the road environment model and the traffic flow model are combined and synthesized to obtain an autonomous driving simulation scene. According to actual needs, the scene environment and vehicle parameters required for the simulation can be set and adjusted to perform model construction and scene synthesis. For example, the friction coefficient, weather conditions, lighting, etc. of the road, as well as the dynamic characteristics, sensor parameters, etc. of the vehicle are defined. Through appropriate parameter settings, it is ensured that the simulation scene can reflect the richness and variability of the actual driving scene, and a storyline that meets the OpenSCENARIO standard is designed and written. In the storyline, the behavior, interaction, task and trigger event of the participants can be defined through the scene description language, vehicle model, road environment model and traffic flow model, creating a coherent scene experience, simulating various situations and challenges in real driving scenes, and solving the problem that the scene of the autonomous driving simulation scene in the prior art is relatively single; the user only needs to input the vehicle driving scene description information, vehicle model information, road environment information and traffic flow information to automatically realize the generation of the autonomous driving simulation scene, which is highly customizable.

[0091] like Figure 2 As shown, the present invention also provides a device 200 for generating an automatic driving simulation scene, which includes:

[0092] The first generating module 210 is used to obtain vehicle driving scene description information and generate a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information;

[0093] A second generating module 220 is used to obtain vehicle model information and generate a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information;

[0094] The third generation module 230 is used to obtain road environment information and generate a road environment model that meets the OpenSCENARIO standard based on the road environment information;

[0095] A fourth generation module 240, configured to obtain traffic flow information and generate a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information;

[0096] The synthesis module 250 is used to combine and synthesize the scene description language, the vehicle model, the road environment model and the traffic flow model to obtain an autonomous driving simulation scene.

[0097] The device for generating an autonomous driving simulation scene provided in the above-mentioned embodiment can implement the technical solution described in the above-mentioned embodiment of the method for generating an autonomous driving simulation scene. The specific implementation principles of the above-mentioned modules or units can refer to the corresponding contents in the above-mentioned embodiment of the method for generating an autonomous driving simulation scene, and will not be repeated here.

[0098] like Figure 3 As shown, the present invention also provides an electronic device 300. The electronic device 300 includes a processor 301, a memory 302 and a display 303. Figure 3 Only some of the components of the electronic device 300 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0099] In some embodiments, the memory 302 may be an internal storage unit of the electronic device 300, such as a hard disk or memory of the electronic device 300. In other embodiments, the memory 302 may also be an external storage device of the electronic device 300, such as a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 300.

[0100] Furthermore, the memory 302 may include both an internal storage unit of the electronic device 300 and an external storage device. The memory 302 is used to store application software installed in the electronic device 300 and various data.

[0101] In some embodiments, the processor 301 can be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 302, such as the method for generating an autonomous driving simulation scene in the present invention.

[0102] In some embodiments, the display 303 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 303 is used to display information on the electronic device 300 and to display a visual user interface. The components 301-303 of the electronic device 300 communicate with each other via a system bus.

[0103] In some embodiments of the present invention, when the processor 301 executes the program for generating the autonomous driving simulation scene in the memory 302, the following steps may be implemented:

[0104] Acquire vehicle driving scene description information, and generate a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information;

[0105] Acquire vehicle model information, and generate a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information;

[0106] Acquire road environment information, and generate a road environment model that meets the OpenSCENARIO standard based on the road environment information;

[0107] Acquire traffic flow information, and generate a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information;

[0108] The scene description language, the vehicle model, the road environment model and the traffic flow model are combined and synthesized to obtain an autonomous driving simulation scene.

[0109] It should be understood that: when the processor 301 executes the generation program of the autonomous driving simulation scene in the memory 302, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0110] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 300 mentioned, and the electronic device 300 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 300 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0111] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating an autonomous driving simulation scenario provided by the above methods is implemented, and the method includes:

[0112] Acquire vehicle driving scene description information, and generate a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information;

[0113] Acquire vehicle model information, and generate a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information;

[0114] Acquire road environment information, and generate a road environment model that meets the OpenSCENARIO standard based on the road environment information;

[0115] Acquire traffic flow information, and generate a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information;

[0116] The scene description language, the vehicle model, the road environment model and the traffic flow model are combined and synthesized to obtain an autonomous driving simulation scene.

[0117] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0118] The above is a detailed introduction to the method, device and electronic device for generating an autonomous driving simulation scene provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for generating an autonomous driving simulation scene, characterized in that: include: Acquire vehicle driving scene description information, and generate a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information; Acquire vehicle model information, and generate a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information; Acquire road environment information, and generate a road environment model that meets the OpenSCENARIO standard based on the road environment information; Acquire traffic flow information, and generate a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information; Combining and synthesizing the scenario description language, the vehicle model, the road environment model and the traffic flow model to obtain an autonomous driving simulation scenario; The step of generating a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information includes: Performing semantic analysis and information extraction on the vehicle driving scene description information based on natural language text to obtain data elements, and constructing preliminary scene description information based on the data elements and a preset data structure; Based on a preset mapping standard, the preliminary description information of the scene is mapped into the OpenSCENARIO standard to generate an initial description language; Verifying the initial description language, and if it is determined that the syntax of the initial description language meets the OpenSCENARIO standard, using the initial description language as a scene description language that meets the OpenSCENARIO standard; The method for generating an autonomous driving simulation scene also includes: In the case where it is determined that the syntax of the initial description language does not meet the OpenSCENARIO standard, determining the information entropy of the initial description language; Based on the information entropy, new words are discovered, confusion sets of new words are found, and candidate recall processing is performed on the confusion sets to obtain candidate sets; The candidate set is sorted based on the N-Gram model to generate a new initial description language, and the new initial description language is used as a scene description language that meets the OpenSCENARIO standard.

2. The method for generating an autonomous driving simulation scene according to claim 1, characterized in that: The verifying of the initial description language includes: The initial description language is verified based on pattern matching or syntax analysis.

3. The method for generating an autonomous driving simulation scene according to claim 1, characterized in that: The scenario description language includes: vehicle starting position, vehicle driving path, road selection information and traffic flow requirements; The combining and synthesizing the scene description language, the vehicle model, the road environment model and the traffic flow model to obtain an automatic driving simulation scene includes: The vehicle model is associated with the vehicle starting position and the vehicle driving path, the road environment model is associated with the road selection information, and the traffic flow model is associated with the traffic flow requirement to obtain an automatic driving simulation scenario.

4. The method for generating an autonomous driving simulation scene according to claim 1, characterized in that: The obtaining of traffic flow information includes: Simulate the behavior of participants in the vehicle driving environment and generate diverse traffic flow information in the simulation scene.

5. The method for generating an autonomous driving simulation scene according to any one of claims 1 to 4, characterized in that: The vehicle driving scene description information includes: vehicle starting position, vehicle target position, road selection information and traffic flow information; The vehicle model information includes: the appearance and dynamic parameters of the vehicle; The road environment information includes: road markings, road conditions and scenery information; The traffic flow information includes: vehicle type, vehicle density and vehicle speed distribution information.

6. A device for generating an automatic driving simulation scene, characterized in that: include: A first generating module is used to obtain vehicle driving scene description information, and generate a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information; A second generation module is used to obtain vehicle model information and generate a vehicle model that meets the OpenSCENARIO standard based on the vehicle model information; A third generation module is used to obtain road environment information and generate a road environment model that meets the OpenSCENARIO standard based on the road environment information; A fourth generation module, used to obtain traffic flow information, and generate a traffic flow model that meets the OpenSCENARIO standard based on the traffic flow information; A synthesis module, used for combining and synthesizing the scenario description language, the vehicle model, the road environment model and the traffic flow model to obtain an autonomous driving simulation scenario; The step of generating a scene description language that meets the OpenSCENARIO standard from the vehicle driving scene description information includes: Performing semantic analysis and information extraction on the vehicle driving scene description information based on natural language text to obtain data elements, and constructing preliminary scene description information based on the data elements and a preset data structure; Based on a preset mapping standard, the preliminary description information of the scene is mapped into the OpenSCENARIO standard to generate an initial description language; Verifying the initial description language, and if it is determined that the syntax of the initial description language meets the OpenSCENARIO standard, using the initial description language as a scene description language that meets the OpenSCENARIO standard; The device for generating the autonomous driving simulation scene is also used for: In the case where it is determined that the syntax of the initial description language does not meet the OpenSCENARIO standard, determining the information entropy of the initial description language; Based on the information entropy, new words are discovered, confusion sets of new words are found, and candidate recall processing is performed on the confusion sets to obtain candidate sets; The candidate set is sorted based on the N-Gram model to generate a new initial description language, and the new initial description language is used as a scene description language that meets the OpenSCENARIO standard.

7. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for generating an autonomous driving simulation scene as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating an autonomous driving simulation scene as described in any one of claims 1 to 5 is implemented.

Images