Simulation Test Method, Device, Equipment and System for Autopilot Algorithm

Abstract

The present application provides a simulation test method, device, equipment and system for an autonomous driving algorithm. The method includes: the simulation control middleware system receives a simulation resource acquisition request sent by the terminal device of the target user. The simulation resource acquisition request includes the identifier of the target user and the identifier of the target autonomous driving algorithm. According to the identifier of the target user and the mapping relationship, the target user role corresponding to the identifier of the target user is obtained. From the simulation resources corresponding to the target user role, the target simulation resource corresponding to the identifier of the target autonomous driving algorithm is determined. According to the target simulation resource and the identifier of the target autonomous driving algorithm, a simulation test instruction is sent to the vehicle simulation system. In this technical solution, the target simulation resource can be a simulation test case pre-written by other users, which can save the user's self-writing process, save labor costs, and improve the simulation test efficiency, server resource utilization rate and system security.

Description

Technical Field

[0001] The present application relates to the technical field of vehicles, and particularly to a simulation test method, device, equipment and system for an autonomous driving algorithm. Background Art

[0002] An autonomous driving vehicle is an intelligent vehicle that realizes driverless through a computer system. After the autonomous driving function of the intelligent vehicle is turned on, it can combine the real-time road conditions to control the intelligent vehicle to drive along the planned route, so as to safely send the user to the set destination. The autonomous driving function liberates the driver from some driving-related responsibilities, effectively reducing traffic accidents and traffic congestion. Therefore, intelligent vehicles with autonomous driving functions are the mainstream development direction of future vehicles.

[0003] Currently, the development of autonomous driving functions follows the process from simulation testing to real vehicle testing. As a zero-risk, fast-iterative, and reproducible testing method, simulation testing has laid a solid foundation for the on-road testing of autonomous driving technology. Simulation testing can quickly and effectively test the correctness and performance of autonomous driving algorithms. In the prior art, for the simulation testing of autonomous driving functions, mainly after developers log in to the vehicle simulation system, the vehicle simulation system performs simulation testing on the autonomous driving functions according to the pre-stored simulation test cases by itself, and obtains the simulation test results. Among them, the simulation test cases are developed and edited by the developers themselves.

[0004] However, in the prior art, developers need to edit simulation test cases for each part of the algorithms of autonomous driving functions respectively, resulting in the problem of low simulation testing efficiency. Summary of the Invention

[0005] The present application provides a simulation test method, device, equipment and system for an autonomous driving algorithm to solve the problem of low simulation testing efficiency existing in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a simulation test method for an autonomous driving algorithm, which is applied to a simulation control middle platform system, and the method includes:

[0007] Receiving a simulation resource acquisition request sent by a terminal device of a target user, where the simulation resource acquisition request includes an identifier of the target user and an identifier of a target autonomous driving algorithm;

[0008] According to the identifier of the target user and the mapping relationship, obtaining a target user role corresponding to the identifier of the target user, where the mapping relationship is used to represent the corresponding relationship between the identifier of the user and the user role;

[0009] Determine the target simulation resource corresponding to the identifier of the target autonomous driving algorithm from the simulation resources corresponding to the target user role. The simulation resources corresponding to the target user role include multiple simulation test cases respectively written by multiple users in advance according to multiple autonomous driving algorithms, and each user can write at least one simulation test case.

[0010] Send a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm.

[0011] In a possible design of the first aspect, the step of sending a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm includes:

[0012] Send the target simulation resource to the terminal device of the target user.

[0013] Receive the simulation test instruction sent by the terminal device of the target user, where the simulation test instruction is generated according to the target simulation resource and the identifier of the target autonomous driving algorithm.

[0014] Send the simulation test instruction to the vehicle simulation system.

[0015] Optionally, the step of sending the simulation test instruction to the vehicle simulation system includes:

[0016] Store the simulation test instruction in the first message queue middleware so that the vehicle simulation system can consume the simulation test instruction from the first message queue middleware, and the first message queue middleware is used to store the simulation test instruction.

[0017] Optionally, the method further includes:

[0018] Obtain the simulation test result from the second message queue middleware, where the second message queue middleware is used to store the simulation test result.

[0019] Send the simulation test result to the terminal device of the target user.

[0020] Optionally, after storing the simulation test instruction in the first message queue middleware, the method further includes:

[0021] Start timing through a timer, and release the resources of the first message queue middleware and the resources of the second message queue middleware after reaching the duration preset by the timer.

[0022] In another possible design of the first aspect, before receiving the simulation resource acquisition request sent by the terminal device of the target user, the method further includes:

[0023] Receive a target user registration request sent by the terminal device of the target user, where the target user registration request carries target user information;

[0024] Register the target user according to the target user registration request, and obtain the identifier of the target user;

[0025] Associate the identifier of the target user with a target user role according to the target user information;

[0026] Return a registration result to the terminal device of the user.

[0027] Optionally, the method further includes:

[0028] If the simulation resource carried in the simulation test instruction is the edited target simulation resource, store the edited target simulation resource, and establish a corresponding relationship between the edited target simulation resource and the target user.

[0029] In a second aspect, an embodiment of the present application provides a simulation test device for an autonomous driving algorithm, which is applied to a simulation control middleware system. The device includes:

[0030] A receiving module, configured to receive a simulation resource acquisition request sent by the terminal device of the target user, where the simulation resource acquisition request includes the identifier of the target user and the identifier of the target autonomous driving algorithm;

[0031] A processing module, configured to obtain the target user role corresponding to the identifier of the target user according to the identifier of the target user and the mapping relationship, where the mapping relationship is used to represent the corresponding relationship between the identifier of the user and the user role;

[0032] The processing module is further configured to determine, from the simulation resources corresponding to the target user role, the target simulation resource corresponding to the identifier of the target autonomous driving algorithm, where the simulation resources corresponding to the target user role include multiple simulation test programs written by users in advance according to the autonomous driving algorithm;

[0033] A sending module, configured to send a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm.

[0034] In a possible design of the second aspect, the sending module is specifically configured to:

[0035] Send the target simulation resource to the terminal device of the target user;

[0036] Receive the simulation test instruction sent by the terminal device of the target user, where the simulation test instruction is generated according to the target simulation resource and the identifier of the target autonomous driving algorithm;

[0037] Send the simulation test instruction to the vehicle simulation system.

[0038] Optionally, the sending module is specifically configured to:

[0039] Store the simulation test instruction in the first message queue middleware, so that the vehicle simulation system can consume the simulation test instruction from the first message queue middleware, and the first message queue middleware is used to store the simulation test instruction.

[0040] Optionally, the device further includes:

[0041] An obtaining module, configured to obtain a simulation test result from a second message queue middleware, where the second message queue middleware is used to store the simulation test result;

[0042] The sending module is further configured to send the simulation test result to the terminal device of the target user.

[0043] Optionally, after storing the simulation test instruction in the first message queue middleware, the processing module is further configured to:

[0044] Start timing through a timer, and release the resources of the first message queue middleware and the resources of the second message queue middleware after reaching the duration preset by the timer.

[0045] In another possible design of the second aspect, before receiving the simulation resource acquisition request sent by the terminal device of the target user, the receiving module is further configured to receive a target user registration request sent by the terminal device of the target user, where the target user registration request carries target user information;

[0046] The obtaining module is further configured to register the target user according to the target user registration request, and obtain the identifier of the target user;

[0047] The processing module is further configured to associate the identifier of the target user with the target user role according to the target user information;

[0048] The sending module is further configured to return a registration result to the terminal device of the user.

[0049] Optionally, the processing module is further configured to:

[0050] If the simulation resource carried by the simulation test instruction is the edited target simulation resource, store the edited target simulation resource and establish a corresponding relationship between the edited target simulation resource and the target user.

[0051] In a third aspect, an embodiment of the present application provides a simulation control middleware system, including:

[0052] A front-end user interface UI layer for receiving a simulation resource acquisition request sent by a terminal device of a target user, where the simulation resource acquisition request includes an identifier of the target user and an identifier of a target autonomous driving algorithm;

[0053] A data layer for obtaining a target user role corresponding to the identifier of the target user according to the identifier of the target user and the mapping relationship, where the mapping relationship is used to represent the corresponding relationship between the identifier of the user and the user role;

[0054] A service layer for determining, from the simulation resources corresponding to the target user role, a target simulation resource corresponding to the identifier of the target autonomous driving algorithm, where the simulation resources corresponding to the target user role include multiple simulation test programs written by users in advance according to the autonomous driving algorithm;

[0055] The front-end user interface UI layer is further configured to send a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm;

[0056] An application layer for storing the mapping relationship.

[0057] In a fourth aspect, an embodiment of the present application provides a computing device, including: a processor, a transceiver, a memory, and computer program instructions stored on the memory and executable on the processor. When the processor executes the computer program instructions, it is used to implement the methods provided in the first aspect and all possible designs.

[0058] In a fifth aspect, an embodiment of the present application may provide a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided in the first aspect and all possible designs.

[0059] In a sixth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it is used to implement the methods provided in the first aspect and all possible designs.

[0060] The simulation test method, device, equipment and system of the autonomous driving algorithm provided in the embodiment of the present application, the simulation control middle station system receives the simulation resource acquisition request sent by the terminal device of the target user, the simulation resource acquisition request includes the identification of the target user and the identification of the target autonomous driving algorithm, obtains the target user role corresponding to the identification of the target user according to the identification of the target user and the mapping relationship, determines the target simulation resource corresponding to the identification of the target autonomous driving algorithm from the simulation resources corresponding to the target user role, and sends the simulation test instruction to the vehicle simulation system according to the target simulation resource and the identification of the target autonomous driving algorithm. In this scheme, the target simulation resource is obtained according to the identification of the target user and the above-mentioned mapping relationship, and the target simulation resource can be a simulation test case pre-written by other users, thereby eliminating the user's self-writing process, saving manpower costs and simulation resource costs, simplifying the complexity of simulation testing, and improving simulation testing efficiency, server resource utilization and system security. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0062] Figure 1 A schematic diagram of the architecture of the first embodiment of the simulation control middle station system provided in the embodiment of the present application;

[0063] Figure 2 A schematic diagram of the architecture of the second embodiment of the simulation control middle station system provided in the embodiment of the present application;

[0064] Figure 3 A schematic diagram of the controller layer data processing flow provided in an embodiment of the present application;

[0065] Figure 4 A schematic diagram of the architecture of the simulation control middle station system embodiment 3 provided in the embodiment of the present application;

[0066] Figure 5 A flowchart of a first embodiment of a simulation test method for an autonomous driving algorithm provided in an embodiment of the present application;

[0067] Figure 6 A schematic diagram of the mapping relationship provided in the embodiment of the present application;

[0068] Figure 7 A flowchart of a second embodiment of a simulation test method for an autonomous driving algorithm provided in an embodiment of the present application;

[0069] Figure 8 A flowchart of a third embodiment of a simulation test method for an autonomous driving algorithm provided in an embodiment of the present application;

[0070] Figure 9 The structural schematic diagram of the simulation test device for the automatic driving algorithm provided by the embodiment of the present application;

[0071] Figure 10 The structural schematic diagram of the computer device provided by the embodiment of the present application.

[0072] Through the above-mentioned drawings, the specific embodiments of the present disclosure have been shown, and there will be more detailed descriptions hereinafter. These drawings and the text description are not intended to limit the scope of the concept of the present disclosure in any way, but to illustrate the concept of the present disclosure to those skilled in the art by referring to specific embodiments. Specific Embodiments

[0073] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0074] Before introducing the embodiments of the present application, first, the application background of the embodiments of the present application will be explained:

[0075] The simulation test technology mainly digitally restores the application scenarios of automatic driving in the form of mathematical modeling, establishes a system model as close as possible to the real world, and through this system model, the automatic driving algorithm can be simulated and tested to achieve the purpose of testing and verifying the correctness and performance of the automatic driving algorithm. In the prior art, the above-mentioned system model is pre-edited and developed by developers according to the automatic driving algorithm, and this system model is the simulation test case in the present application.

[0076] However, since the content involved in the automatic driving algorithm is relatively large, and the algorithm developers related to automatic driving will update the relevant algorithms according to the user experience, the developers need to edit simulation test cases for each part of the algorithm of the automatic driving function respectively, resulting in the problem of low simulation test efficiency.

[0077] Therefore, the embodiments of the present application provide a simulation test method, device, equipment and system for an autonomous driving algorithm. The simulation control middle platform system can pre - establish a mapping relationship between the identification of a user and the user role according to the user information. Then, the simulation test cases pre - written by the user according to each autonomous driving algorithm are associated with the user role corresponding to the user, so that each user role can correspond to multiple simulation test cases written by multiple users, and each user can write at least one simulation test case. Then, after the simulation control middle platform system receives a simulation resource acquisition request, it can determine the target user role corresponding to the identification of the target user in the simulation resource acquisition request according to the identification of the target user and the above - mentioned mapping relationship, and determine the target simulation resource from the simulation resources corresponding to the target user role. The target simulation resource can be a simulation test case pre - written by other users, thus saving the user's independent writing process, saving labor costs, and improving the simulation test efficiency.

[0078] Exemplarily, the simulation test method for an autonomous driving algorithm provided by the embodiments of the present application can be applied to Figure 1 the schematic architecture diagram of a simulation control middle platform system as shown. Figure 1 It is the schematic architecture diagram of the first embodiment of the simulation control middle platform system provided by the embodiments of the present application, which is used to solve the above - mentioned technical problems. As Figure 1 shown, the simulation control middle platform system can include: a front - end user interface (User Interface, UI) layer, a data layer, a business layer, and an application layer.

[0079] The front - end UI layer is used to receive a simulation resource acquisition request sent by the terminal device of the target user. The simulation resource acquisition request includes the identification of the target user and the identification of the target autonomous driving algorithm; it is also used to send a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identification of the target autonomous driving algorithm.

[0080] The front - end UI layer can include Hyper Text Markup Language (HTML), Cascading Style Sheets (CSS), React, and corresponding files. The front - end UI layer processes page logic through React, requests and schedules the data layer and the business layer through the Hyper Text Transfer Protocol (HTTP), and indirectly schedules the application layer. The front - end UI layer can also be used to increase log records and manage user permission control, so as to realize the scheduling, sharing, management, etc. of simulation resources. Among them, React is a JavaScript library for building user interfaces.

[0081] Among them, the simulation resource acquisition request received by the front-end UI layer can be a POST request or a Get request.

[0082] The data layer can implement the functions of processing transactions and reading and writing databases, and is used to obtain the target user role corresponding to the identifier of the target user according to the identifier of the target user and the mapping relationship, where the mapping relationship is used to represent the corresponding relationship between the identifier of the user and the user role.

[0083] The business layer is used to determine the target simulation resource corresponding to the identifier of the target autonomous driving algorithm from the simulation resources corresponding to the target user role, and the simulation resources corresponding to the target user role include multiple simulation test programs written by users in advance according to the autonomous driving algorithm.

[0084] The business layer can implement various business functions through Java code, and the business functions include at least one of user registration and login, creating simulation test tasks, system management, simulation resource management, and system logs.

[0085] Among them, the simulation control middle platform system can also implement the log recording function and the permission control function through the joint action of the business layer and the data layer.

[0086] The application layer is mainly used to store the mapping relationship between the identifier of the above user and the user role.

[0087] The application layer can install and use a relational database management system (MySQL) database to record and manage simulation-related information. It can also install KS8 (kubernetes), as well as application software such as JVM (Java Virtual Machine) virtual machines and rabbitmq message queues. The JVM can be deployed in a multi-node distributed manner, and when one JVM node fails, it can not affect the continuous operation of other JVM nodes, realizing distributed disaster tolerance and ensuring the high availability of the simulation control middle platform system.

[0088] Optionally, in Figure 1 the simulation control middle platform system may further include: an operating system layer.

[0089] Among them, the operating system layer is a Linux server.

[0090] Optionally, Figure 2 is a schematic diagram of the architecture of Embodiment 2 of the simulation control middle platform system provided by this application. As Figure 2 shown, the simulation control middle platform system may include a front-end server and a back-end server. The back-end server includes a controller layer, a service layer, a mapper layer, and an application layer. Among them, the front-end server is used to provide Figure 1In the front-end UI layer of the illustrated embodiment, the service layer is equivalent to Figure 1 the business layer in the illustrated embodiment, and the mapper layer is equivalent to Figure 1 the data layer in the illustrated embodiment.

[0091] Among them, the front-end server uses React to develop and render the page. After receiving the HTTP request (simulation resource acquisition request) sent by the user through this page, it forwards it to the back-end server. The back-end server calls the interface to forward the HTTP request to different service business layers through the controller layer ( Figure 2 only one service business layer is used as an example for illustration), so that different service business layers process different services. After that, the back-end server calls the mapper layer to persist to the MySQL database, or persist to ELK (used for log processing, which is the acronym of ElasticSearch, Logstash, and Kibana), RabbitMQ, and Remote Dictionary Server (Redis), etc.

[0092] Based on the above embodiment, exemplarily, Figure 3 This is a schematic flowchart of the data processing of the controller layer provided by the embodiment of the present application. As Figure 3 shown, when the front-end server forwards the received simulation resource acquisition request to the back-end server, it is mainly implemented through the following steps:

[0093] The front controller (DispatcherServlet) of Spring MVC is used to call the handler mapper (HandlerMapping) to identify the uniform resource locator (URL) of the simulation resource acquisition request, and obtain the corresponding HandlerChain according to this URL. Among them, the HandlerChain includes a processor object (handler) and a processor interceptor (Interceptor). Then, the handler adapter (HandlerAdapter) is called to execute the HandlerChain, and the request parameter encapsulation and Joson format conversion are completed to obtain the ModelAndView. Further, the ViewReslover is called to parse out a View object according to the ModelAndView, and then the request forwarding or redirection is completed.

[0094] Optionally, JSP (JavaServer Pages) may be called to render data into HTML, and the rendered HTML content may be output to the browser, thereby completing the response to the simulation resource acquisition request.

[0095] In the above Figure 2 and / or Figure 3 Based on the embodiments shown, exemplary, Figure 4 The schematic diagram of the architecture of the simulation control middle station system embodiment 3 provided in the embodiment of the present application is as follows: Figure 4 The simulation control middle-end system includes a front-end server, a back-end server, and nginx (engine x). The front-end server can forward HTTP requests to the back-end server through the forwarding algorithm of nginx. When the amount of HTTP request data is too large, resources are scheduled with a queuing mechanism through resource scheduling, which effectively improves the response speed and stability of the simulation control middle-end system, achieves the purpose of load balancing and high availability, and improves the utilization of system resources.

[0096] The technical solution of the present application is described in detail below through specific embodiments.

[0097] It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0098] Figure 5 The flowchart of the first embodiment of the simulation test method of the autonomous driving algorithm provided in the embodiment of the present application is shown in FIG. The simulation test method of the autonomous driving algorithm is applied to the simulation control middle station system, such as Figure 5 As shown, the simulation test method of the autonomous driving algorithm may include the following steps:

[0099] S501: Receive a simulation resource acquisition request sent by a terminal device of a target user.

[0100] In an embodiment of the present application, a communication connection is pre-established between the user's terminal device and the simulation control middle-office system, and the user can access the simulation control middle-office system through the browser of the terminal device, so that information interaction between the terminal device and the simulation control middle-office system can be achieved through the communication connection.

[0101] Exemplarily, the terminal device may be, for example, a mobile phone, a computer, a tablet computer or the like, and the embodiment of the present application does not limit the specific type of the terminal device.

[0102] Among them, the target users are developers who have simulation testing needs.

[0103] Among them, the simulation resource acquisition request includes the identifier of the target user and the identifier of the target autonomous driving algorithm. The identifier of the target user can be generated when the target user pre-registers in the simulation control middleware system. The identifier of the target user can be the username of the target user, the phone number of the target user, the ID number of the target user, etc., and the embodiments of the present application do not specifically limit this.

[0104] Among them, the simulation resources are the test resources required for simulating and testing the autonomous driving algorithm. The simulation resources can include the simulation test cases written by each user for each autonomous driving algorithm. Optionally, the simulation resources can also include simulation files, simulation environments, server resources, etc. It should be understood that the embodiments of the present application do not limit the content included in the simulation resources.

[0105] S502. According to the identifier of the target user and the mapping relationship, obtain the target user role corresponding to the identifier of the target user.

[0106] Among them, the above mapping relationship is used to represent the corresponding relationship between the identifier of the user and the user role.

[0107] Among them, the user role is used to characterize the role of the user in the simulation control middleware system, and different user roles correspond to different simulation resources. Optionally, different user roles can also correspond to different permissions, such as data permissions, interface permissions, and menu permissions.

[0108] Exemplarily, Figure 6 is a schematic diagram of the mapping relationship provided by the embodiments of the present application. As Figure 6 shown, User 1, User 2, and User 3 correspond to User Role 1; User 3 corresponds to User Role 1 and User Role 2. Among them, User Role 1 corresponds to Menu Permission 1, Interface Permission 1, Interface Permission 2, and Data Permission 2, and User Role 2 corresponds to Menu Permission 1, Menu Permission 2, Interface Permission 1, Interface Permission 2, Interface Permission 3, Data Permission 1, Data Permission 2, and Data Permission 3.

[0109] Among them, the data permission is used to manage the simulation resources, and different data permissions can call different simulation resources.

[0110] Exemplarily, the user role can be employee, management, manager, etc.; it can also be Simulation Department 1, Simulation Department 2, Simulation Department 3; it can also be Simulation Test Department, Algorithm Writing Department, System Management Department, etc. The embodiments of the present application do not limit the specific names and actual contents of the user roles.

[0111] It should be understood that the above mapping relationship can be pre-stored in the database of the simulation control center system by the technical personnel corresponding to the simulation control center system, or can be obtained from a database external to the simulation control center system in advance. The embodiments of the present application do not specifically limit this.

[0112] Exemplarily, the above mapping relationship can be represented by Table 1.

[0113] Table 1

[0114]

[0115] Taking the mapping relationship shown in Table 1 as an example, if the identifier of the target user is User Identifier 1, then according to this mapping relationship, it can be determined that the target user roles corresponding to the identifier of the target user are User Role 1 and User Role 2.

[0116] Before S501, it is also possible to receive a simulation test case sent by the user and associate the simulation test case with the user role corresponding to the user.

[0117] S503. Determine the target simulation resource corresponding to the identifier of the target autonomous driving algorithm from the simulation resources corresponding to the target user role.

[0118] Among them, the simulation resources corresponding to the target user role include multiple simulation test cases respectively written by multiple users according to multiple autonomous driving algorithms, and each user can write at least one simulation test case.

[0119] That is to say, the target simulation resource determined from the simulation resources corresponding to the target user role can be pre-edited by the target user for the target autonomous driving algorithm, or can be pre-edited by other users for the target autonomous driving algorithm.

[0120] In a possible implementation manner, according to the data permission corresponding to the target user role, obtain the simulation resources corresponding to this data permission, so as to determine the target simulation resource from the simulation resources.

[0121] Among them, the target simulation resource can include multiple simulation resources or can include one simulation resource. The embodiments of the present application do not limit the number of simulation resources included in the target simulation resource.

[0122] S504. Send a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm.

[0123] Among them, the vehicle simulation system is used to perform a simulation test on the target autonomous driving algorithm through the target simulation resource according to the simulation test instruction.

[0124] After obtaining the target simulation resources, the simulation control center system can interact with the user's terminal device, enabling the user to send simulation test instructions to the simulation control center system through the terminal device based on the received target simulation resources. For the simulation control center system, after receiving the simulation test instructions, it forwards the simulation test instructions to the vehicle simulation system.

[0125] The specific implementation method and implementation principle of this step can refer to Figure 7 the embodiments shown, which will not be elaborated here.

[0126] In the simulation test method of the autonomous driving algorithm provided by the embodiments of this application, the simulation control center system receives a simulation resource acquisition request sent by the terminal device of the target user. The simulation resource acquisition request includes the identifier of the target user and the identifier of the target autonomous driving algorithm. According to the identifier of the target user and the mapping relationship, the target user role corresponding to the identifier of the target user is obtained. From the simulation resources corresponding to the target user role, the target simulation resources corresponding to the identifier of the target autonomous driving algorithm are determined. According to the target simulation resources and the identifier of the target autonomous driving algorithm, a simulation test instruction is sent to the vehicle simulation system. In this solution, according to the identifier of the target user and the above mapping relationship, the target simulation resources are obtained. The target simulation resources can be simulation test cases pre-written by other users, thus eliminating the need for users to write independently, saving labor costs and simulation resource costs, simplifying the complexity of simulation tests, and improving simulation test efficiency, server resource utilization rate, and system security.

[0127] Based on any of the above embodiments, Figure 7 This is a schematic flowchart of the second embodiment of the simulation test method of the autonomous driving algorithm provided by the embodiments of this application. As Figure 7 shown, S504 can be implemented through the following steps:

[0128] S701. The simulation control center system sends the target simulation resources to the terminal device of the target user.

[0129] Correspondingly, the terminal device of the target user receives the target simulation resources sent by the simulation control center system.

[0130] For the terminal device, it can generate a simulation test instruction in response to the user's operation.

[0131] Among them, the above user's operation can be a selection operation or an editing operation on the simulation resources in the target simulation resources.

[0132] That is to say, the simulation test instruction is generated according to the target simulation resources and the identifier of the target autonomous driving algorithm.

[0133] S702. The simulation control middleware system receives the simulation test instruction sent by the terminal device of the target user.

[0134] Optionally, if the simulation resource carried by the simulation test instruction is the edited target simulation resource, store the edited target simulation resource and establish the corresponding relationship between the edited target simulation resource and the target user, so that the edited target simulation resource can be retrieved again in subsequent simulation test requests, further improving the efficiency of the simulation test.

[0135] That is to say, the simulation control middleware system can update the above mapping relationship according to the edited target simulation resource.

[0136] S703. Send the simulation test instruction to the vehicle simulation system.

[0137] Optionally, in some embodiments, the simulation test instruction can also be stored in the first message queue middleware, so that the vehicle simulation system can consume the simulation test instruction from the first message queue middleware, where the first message queue middleware is used to store the simulation test instruction.

[0138] In the above embodiments, by storing the simulation test instruction in the first message queue middleware, application coupling can be achieved, and at the same time, asynchronous processing and current limiting and peak shaving of the simulation test instruction can be performed, improving the robustness and availability of the system.

[0139] Optionally, the first message queue middleware can be rabbitmq.

[0140] Optionally, in some embodiments, after the vehicle simulation system processes the simulation test instruction, it can generate a simulation test result and send the simulation test result to the second message queue middleware. For the simulation control middleware system, it can obtain the simulation test result from the second message queue middleware and then send the simulation test result to the terminal device of the target user so that the user can view it through the terminal device. The second message queue middleware is used to store the simulation test result.

[0141] In this embodiment, the simulation control middleware system interacts with the vehicle simulation system through the second message queue middleware to obtain the simulation test result, thereby improving the robustness and availability of the system. At the same time, after the simulation control middleware system obtains the simulation test result, it sends the simulation test result to the terminal device of the target user, so that the target user can perform the next step of processing in a timely manner according to the simulation test result.

[0142] Optionally, when the test result indicates that there is a problem with the simulation resources used in the simulation test instruction, the user can modify the above simulation resources according to the test result, so as to send the modified simulation test instruction to the simulation control middleware system, so that the simulation control middleware system forwards the modified simulation test instruction to the vehicle simulation system.

[0143] Optionally, in some embodiments, a timer can also be started to release the resources of the first message queue middleware and the resources of the second message queue middleware after reaching the preset duration of the timer.

[0144] Exemplarily, the preset duration can be 6 hours, 12 hours, or 1 day, 2 days, 3 days, etc., and can be determined according to the actual data volume. The embodiments of the present application do not specifically limit this.

[0145] In the embodiments of the present application, releasing the resources of the first message queue middleware and the resources of the second message queue middleware through the timer can solve the data backlog problem of the first message queue middleware and the second message queue middleware, and avoid the problem that the simulation resource acquisition request cannot be processed in time due to data backlog.

[0146] Based on any of the above embodiments, Figure 8 is a schematic flowchart of the third embodiment of the simulation test method for the autonomous driving algorithm provided by the embodiments of the present application. As Figure 8 shown, before S501, the simulation test method for the autonomous driving algorithm can also be implemented through the following steps:

[0147] S801. Receive a target user registration request sent by the terminal device of the target user.

[0148] The target user registration request carries target user information.

[0149] Optionally, the target user information can be information such as name, position, department, etc., or information such as birthday, ID card, place of residence, etc. The present application does not specifically limit the content included in the target user information.

[0150] Optionally, the target user registration request can also carry a user name and a password.

[0151] S802. Register the target user according to the target user registration request to obtain the identifier of the target user.

[0152] In a possible implementation manner, user registration can be performed according to the user name and password in the target user registration request, and after the registration is completed, the identifier of the target user is generated.

[0153] In another possible implementation, user registration can be performed according to the target user registration request. After the registration is completed, the user name, password, and identifier of the target user are generated.

[0154] S803. According to the target user information, associate the identifier of the target user with the target user role.

[0155] In one possible implementation, according to information such as the position and department in the target user information, the target user role corresponding to the target user can be determined, so as to associate the identifier of the target user with the target user role.

[0156] That is to say, according to the target user information, the mapping relationship between the identifier of the user and the user role can be established and / or updated.

[0157] S804. Return the registration result to the terminal device of the user.

[0158] Exemplarily, the registration result can be "registration successful" or "registration failed".

[0159] In the embodiments of the present application, by registering the target user according to the target user registration request and establishing and / or updating the mapping relationship between the identifier of the user and the user role after registration, so that the simulation test cases written by the target user can be associated with the target user role according to the above mapping relationship in the subsequent process, and the target simulation resources can also be obtained according to the above mapping relationship, laying a foundation for the subsequent simulation test.

[0160] Optionally, in some embodiments, a user login instruction sent by the terminal device of the target user can also be received. The user login instruction includes the account and password of the target user. Login processing is performed according to the user login instruction, and the page after login is rendered to the terminal device of the user.

[0161] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For the details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the present application.

[0162] Figure 9 It is a schematic structural diagram of a simulation test device for an autonomous driving algorithm provided by an embodiment of the present application. As Figure 9 shown, the simulation test device for the autonomous driving algorithm is applied to the simulation control middleware system. The device includes:

[0163] A receiving module 91, configured to receive a simulation resource acquisition request sent by the terminal device of the target user. The simulation resource acquisition request includes the identifier of the target user and the identifier of the target autonomous driving algorithm;

[0164] A processing module 92, configured to obtain a target user role corresponding to the identifier of the target user according to the identifier of the target user and a mapping relationship, where the mapping relationship is used to represent the corresponding relationship between the identifier of the user and the user role;

[0165] The processing module 92 is further configured to determine, from the simulation resources corresponding to the target user role, a target simulation resource corresponding to the identifier of the target automatic driving algorithm, where the simulation resources corresponding to the target user role include multiple simulation test programs written by users in advance according to the automatic driving algorithm;

[0166] A sending module 93, configured to send a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identifier of the target automatic driving algorithm.

[0167] In a possible design of the embodiment of the present application, the sending module 93 is specifically configured to:

[0168] Send the target simulation resource to the terminal device of the target user;

[0169] Receive a simulation test instruction sent by the terminal device of the target user, where the simulation test instruction is generated according to the target simulation resource and the identifier of the target automatic driving algorithm;

[0170] Send the simulation test instruction to the vehicle simulation system.

[0171] Optionally, the sending module 93 is specifically configured to:

[0172] Store the simulation test instruction in a first message queue middleware, so that the vehicle simulation system can consume the simulation test instruction from the first message queue middleware, and the first message queue middleware is used to store the simulation test instruction.

[0173] Optionally, the device further includes:

[0174] An obtaining module, configured to obtain a simulation test result from a second message queue middleware, where the second message queue middleware is used to store the simulation test result;

[0175] The sending module 93 is further configured to send the simulation test result to the terminal device of the target user.

[0176] Optionally, after storing the simulation test instruction in the first message queue middleware, the processing module 92 is further configured to:

[0177] Start timing through a timer, and release the resources of the first message queue middleware and the resources of the second message queue middleware after the duration preset by the timer is reached.

[0178] In another possible design of the embodiment of the present application, before receiving the simulation resource acquisition request sent by the terminal device of the target user, the receiving module 91 is further configured to receive the target user registration request sent by the terminal device of the target user, where the target user registration request carries target user information;

[0179] The acquisition module is further configured to register the target user according to the target user registration request and obtain the identifier of the target user;

[0180] The processing module 92 is further configured to associate the identifier of the target user with the target user role according to the target user information;

[0181] The sending module 93 is further configured to return the registration result to the terminal device of the user.

[0182] Optionally, the processing module 92 is further configured to:

[0183] If the simulation resource carried in the simulation test instruction is the edited target simulation resource, store the edited target simulation resource and establish the corresponding relationship between the edited target simulation resource and the target user.

[0184] The simulation test device for the automatic driving algorithm provided by the embodiment of the present application can be used to execute the simulation test method of the automatic driving algorithm in any of the above embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0185] It should be noted that it should be understood that the division of each module of the above device is only a logical function division. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by a processing element; they can also all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. In addition, all or part of these modules can be integrated together or independently implemented. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the integrated logic circuit in the processor element or the instruction in the form of software.

[0186] Figure 10 This is a schematic structural diagram of the computer device provided by the embodiment of the present application. As Figure 10 shown, the computer device may include: a processor 1001, a transceiver 1002, a memory 1003, and computer program instructions stored on the memory 1003 and executable on the processor 1001. When the processor 1001 executes the computer program instructions, it implements the simulation test method of the automatic driving algorithm provided in any of the above embodiments.

[0187] Optionally, the various components of the computer device may be connected via a system bus.

[0188] The memory 1003 may be a separate storage unit or an integrated storage unit within the processor. The number of processors is one or more.

[0189] Optionally, the computer device may further include an interface for interacting with other devices.

[0190] The transceiver 1002 is used to communicate with other computers, and the transceiver 1002 constitutes a communication interface.

[0191] Optionally, in terms of hardware implementation, in the above Figure 9 In the illustrated embodiment: the receiving module 91 and the transmitting module 93 correspond to the transceiver 1002 in this embodiment, and in the above Figure 9 In the illustrated embodiment, the processing module 92 corresponds to the processor 1001 in this embodiment.

[0192] It should be understood that the processor 1001 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the present application may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0193] The system bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity, only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus. The memory may include a random access memory (RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0194] All or part of the steps of the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a readable memory. When the program is executed, it performs the steps of the above method embodiments; and the foregoing memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state drive, magnetic tape, floppy disk, optical disc, and any combination thereof.

[0195] The computer device provided in the embodiments of the present application can be used to execute the simulation test method of the autonomous driving algorithm provided in any of the above method embodiments, and its implementation principle and technical effects are similar, and will not be elaborated here.

[0196] The embodiments of the present application provide a computer-readable storage medium, in which computer instructions are stored. When the computer instructions run on a computer, the computer is enabled to execute the simulation test method of the above autonomous driving algorithm.

[0197] The above computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic memory, flash memory, magnetic disk or optical disc. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0198] Optionally, the readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0199] The embodiments of the present application further provide a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, the simulation test method of the above autonomous driving algorithm can be implemented.

[0200] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A simulation test method for an autonomous driving algorithm, characterized in that Applied to the simulation control middleware system, the method includes: Receiving a simulation resource acquisition request sent by the terminal device of the target user, where the simulation resource acquisition request includes the identifier of the target user and the identifier of the target autonomous driving algorithm; Obtaining the target user role corresponding to the identifier of the target user according to the identifier of the target user and the mapping relationship, where the mapping relationship is used to represent the corresponding relationship between the user identifier and the user role; Determining the target simulation resource corresponding to the identifier of the target autonomous driving algorithm from the simulation resources corresponding to the target user role, where the simulation resources corresponding to the target user role include multiple simulation test cases respectively written by multiple users according to multiple autonomous driving algorithms, and each user can write at least one simulation test case; Sending a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm; The step of sending a simulation test instruction to the vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm includes: Sending the target simulation resource to the terminal device of the target user; Receiving the simulation test instruction sent by the terminal device of the target user, where the simulation test instruction is generated according to the target simulation resource and the identifier of the target autonomous driving algorithm; Sending the simulation test instruction to the vehicle simulation system.

2. The method according to claim 1, wherein The step of sending the simulation test instruction to the vehicle simulation system includes: Storing the simulation test instruction in the first message queue middleware so that the vehicle simulation system can consume the simulation test instruction from the first message middleware, and the first message queue middleware is used to store the simulation test instruction.

3. The method according to claim 2, wherein The method further includes: Obtaining the simulation test result from the second message queue middleware, where the second message queue middleware is used to store the simulation test result; Sending the simulation test result to the terminal device of the target user.

4. The method according to claim 3, characterized in that, After storing the simulation test instruction in the first message queue middleware, the method further includes: Starting to time through a timer, and releasing the resources of the first message queue middleware and the resources of the second message queue middleware after reaching the duration preset by the timer.

5. The method according to claim 1, characterized in that, Before receiving the simulation resource acquisition request sent by the terminal device of the target user, the method further includes: Receiving a target user registration request sent by the terminal device of the target user, where the target user registration request carries target user information; Registering the target user according to the target user registration request to obtain the identifier of the target user; Associating the identifier of the target user with the target user role according to the target user information; Returning a registration result to the terminal device of the user.

6. The method according to claim 1, wherein The method further includes: If the simulation resource carried by the simulation test instruction is the edited target simulation resource, storing the edited target simulation resource and establishing the corresponding relationship between the edited target simulation resource and the target user.

7. A simulation test device for an autonomous driving algorithm, characterized in that, Applied to the simulation control middleware system, the device includes: A receiving module, configured to receive a simulation resource acquisition request sent by a terminal device of a target user, where the simulation resource acquisition request includes an identifier of the target user and an identifier of a target autonomous driving algorithm; A processing module, configured to obtain a target user role corresponding to the identifier of the target user according to the identifier of the target user and a mapping relationship, where the mapping relationship is used to represent the corresponding relationship between the identifier of the user and the user role; The processing module is further configured to determine, from the simulation resources corresponding to the target user role, a target simulation resource corresponding to the identifier of the target autonomous driving algorithm, where the simulation resources corresponding to the target user role include multiple simulation test programs written by users in advance according to the autonomous driving algorithm; A sending module, configured to send a simulation test instruction to a vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm; Specifically, the sending module is configured to send the target simulation resource to the terminal device of the target user; receive the simulation test instruction sent by the terminal device of the target user, where the simulation test instruction is generated according to the target simulation resource and the identifier of the target autonomous driving algorithm; and send the simulation test instruction to the vehicle simulation system.

8. A simulation control middle platform system, characterized in that, It includes: A front-end user interface UI layer, configured to receive a simulation resource acquisition request sent by a terminal device of a target user, where the simulation resource acquisition request includes an identifier of the target user and an identifier of a target autonomous driving algorithm; A data layer, configured to obtain a target user role corresponding to the identifier of the target user according to the identifier of the target user and a mapping relationship, where the mapping relationship is used to represent the corresponding relationship between the identifier of the user and the user role; A service layer, configured to determine, from the simulation resources corresponding to the target user role, a target simulation resource corresponding to the identifier of the target autonomous driving algorithm, where the simulation resources corresponding to the target user role include multiple simulation test programs written by users in advance according to the autonomous driving algorithm; The front-end user interface UI layer is further configured to send a simulation test instruction to a vehicle simulation system according to the target simulation resource and the identifier of the target autonomous driving algorithm; Specifically, the front-end user interface UI layer is configured to send the target simulation resource to the terminal device of the target user; receive the simulation test instruction sent by the terminal device of the target user, where the simulation test instruction is generated according to the target simulation resource and the identifier of the target autonomous driving algorithm; and send the simulation test instruction to the vehicle simulation system; An application layer, configured to store the mapping relationship.

9. A computing device, comprising: A processor, a transceiver, a memory, and computer program instructions stored on the memory and executable on the processor, wherein when the processor executes the computer program instructions, it is used to implement the simulation test method of the autonomous driving algorithm according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by the processor, they are used to implement the simulation test method of the autonomous driving algorithm according to any one of claims 1 to 6.

Images