Intelligent driving test platform, test methods, storage media and program products

Abstract

This application relates to the field of testing technology, and in particular to an intelligent driving testing platform, testing method, storage medium, and program product. The testing platform includes: a controller under test (DUT); a real-time machine (RTM) for generating a target simulation environment based on the target test task of the autonomous driving system; sensor components for collecting environmental data of the virtual vehicle within the target simulation environment; a switch for sending the target simulation environment to the sensor components and sending the environmental data collected by the sensor components to the DUT, which then controls the virtual vehicle to perform the target test task within the target simulation environment based on the environmental data; and a host computer for sending the target test task to the RTM and generating test results for the autonomous driving system based on the test data from the virtual vehicle's execution of the target test task. This solves the problems of related technologies that rely on real-world road testing of driving performance, resulting in high costs, low efficiency, and difficulty in comprehensively covering test scenarios.

Description

Technical Field

[0001] This application relates to the field of testing technology, and in particular to an intelligent driving testing platform, testing method, storage medium, and program product. Background Technology

[0002] With the rapid development of artificial intelligence and autonomous driving technology, intelligent driving systems are gradually changing the automotive industry. Due to the complex and ever-changing road environment, the reliability and safety of intelligent driving systems have become important factors restricting their development. In order to ensure that intelligent driving systems can cope with various possible driving scenarios, it is essential to conduct thorough testing and evaluation.

[0003] In related technologies, the testing and evaluation of intelligent driving systems mainly relies on real-world road testing, which involves deploying autonomous vehicles on real roads for extended periods of driving testing. While this testing method directly reflects the vehicle's performance in a real-world environment, real-vehicle testing requires special modifications to the test vehicles to install necessary sensors and computing equipment. This not only increases hardware investment but may also involve ongoing costs for subsequent maintenance and upgrades. Furthermore, it is subject to external factors such as weather and traffic conditions, leading to uncontrollable testing time and the inability to repeat or reproduce specific scenarios within a short period, significantly reducing testing efficiency. Summary of the Invention

[0004] This application provides an intelligent driving test platform, test method, storage medium, and program product to solve the problems of high cost, low efficiency, and difficulty in fully covering test scenarios that related technologies rely on real-world road testing of driving performance.

[0005] The first aspect of this application provides an intelligent driving test platform, including: a controller under test (DUT); a real-time machine (RTM) for generating a target simulation environment based on a target test task of an autonomous driving system; a sensor component for collecting environmental data of a virtual vehicle in the target simulation environment; a switch for sending the target simulation environment to the sensor component and sending the environmental data collected by the sensor component to the DUT, wherein the DUT controls the virtual vehicle to perform a target test task in the target simulation environment based on the environmental data; and a host computer for sending the target test task to the RTM and generating test results of the autonomous driving system based on the test data of the virtual vehicle performing the target test task.

[0006] Optionally, the sensor assembly includes at least one of a camera, a lidar, and a millimeter-wave radar.

[0007] Optionally, cameras, lidar, and millimeter-wave radar are positioned at the target location on the platform.

[0008] Optionally, the switch includes an Ethernet converter and a video converter, wherein the Ethernet converter is used to send the sensing data from the LiDAR and millimeter-wave radar to the controller under test, and the video converter is used to send the sensing data from the camera to the controller under test.

[0009] Optionally, the host computer includes a data processing and analysis module and a user interface module. The data processing and analysis module is used to process and analyze test data of the virtual vehicle performing the target test task, and the user interface module is used to set the target test task of the autonomous driving system, display the test accuracy, and display at least one of the test results.

[0010] Optionally, the target simulation environment includes at least one of an urban road environment, a highway environment, an intersection environment, and a weather environment.

[0011] Optionally, the target test task includes at least one of lane keeping task, following task, and lane changing task.

[0012] The second aspect of this application provides a testing method for an intelligent driving test platform. This method, based on the intelligent driving test platform described in the above embodiment, includes the following steps: setting a target test task for an autonomous driving system; sending the target test task to a real-time machine, wherein the real-time machine generates a target simulation environment based on the target test task of the autonomous driving system; sensor components collect environmental data of a virtual vehicle in the target simulation environment; a switch sends the target simulation environment to the sensor components and sends the environmental data collected by the sensor components to the controller under test; the controller under test controls the virtual vehicle to execute the target test task in the target simulation environment based on the environmental data; acquiring test data of the virtual vehicle executing the target test task; and generating test results for the autonomous driving system based on the processing and analysis results of the test data.

[0013] A third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the testing method of the intelligent driving test platform as described in the above embodiments.

[0014] The fourth aspect of this application provides a computer program or instruction that, when executed, is used to implement a testing method for an intelligent driving test platform as described in the above embodiments.

[0015] Therefore, this application has the following beneficial effects:

[0016] This application's embodiments can utilize a real-time machine to build a virtual simulation environment for vehicle driving. This allows for flexible control of the test environment and parameters to meet diverse testing needs. Environmental data collected by sensor components is sent to the controller under test (DUT), which then controls the virtual vehicle to perform target test tasks within the target simulation environment based on this data. This effectively reduces testing costs and risks, and enables rapid and accurate evaluation of the autonomous driving system's performance. Therefore, it solves the problems of related technologies that rely on real-world road testing for driving performance, resulting in high costs, low efficiency, and difficulty in comprehensively covering test scenarios.

[0017] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0018] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0019] Figure 1 This is a block diagram of an intelligent driving test platform provided according to an embodiment of this application;

[0020] Figure 2 This is an example diagram of the network topology of an intelligent driving test platform according to an embodiment of this application;

[0021] Figure 3 This is an example diagram of a sensor network topology according to an embodiment of this application;

[0022] Figure 4 This is a flowchart of a testing method for an intelligent driving testing platform provided according to an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] The intelligent driving test platform, test method, storage medium, and program product of this application are described below with reference to the accompanying drawings. Addressing the problems mentioned in the background section, this application provides an intelligent driving test platform that utilizes a real-time machine to build a virtual simulation environment for vehicle driving. This allows for flexible control of the test environment and parameters to meet diverse testing needs. Environmental data collected by sensor components is sent to the controller under test (DUT), which then controls the virtual vehicle to perform target test tasks in the target simulation environment based on the environmental data. This effectively reduces testing costs and risks, and enables rapid and accurate evaluation of the performance of autonomous driving systems. Therefore, this solves the problems of related technologies that rely on real-world road testing for driving performance, resulting in high costs, low efficiency, and difficulty in comprehensively covering test scenarios.

[0025] Specifically, Figure 1 This is a block diagram of an intelligent driving test platform according to an embodiment of this application.

[0026] like Figure 1 As shown, the intelligent driving test platform includes: a controller under test 100, a real-time machine 200, a sensor assembly 300, a switch 400, and a host computer 500.

[0027] The system includes a real-time machine 200 for generating a target simulation environment based on the target test task of the autonomous driving system; a sensor component 300 for collecting environmental data of the virtual vehicle in the target simulation environment; a switch 400 for sending the target simulation environment to the sensor component 300 and sending the environmental data collected by the sensor component 300 to the controller under test 100, which controls the virtual vehicle to perform the target test task in the target simulation environment based on the environmental data; and a host computer 500 for sending the target test task to the real-time machine 200 and generating test results of the autonomous driving system based on the test data of the virtual vehicle performing the target test task.

[0028] The target simulation environment includes at least one of the following: urban road environment, highway environment, intersection environment, and weather environment. The target test tasks include at least one of the following: lane keeping task, following vehicle task, and lane changing task.

[0029] It is understood that the embodiments of this application can evaluate and verify the performance of the vehicle autonomous driving system through the intelligent driving test platform. The test platform uses sensor components 300 to collect environmental data of the virtual vehicle in the target simulation environment, which can simulate various driving scenarios. According to the test requirements, the controller under test 100 controls the virtual vehicle to perform specific driving tasks in the simulation environment to ensure the safety and stability of the autonomous driving system under different conditions. It can quickly and accurately evaluate the performance of the autonomous driving system in the virtual environment, thereby improving test efficiency and reliability.

[0030] In this embodiment, the sensor assembly 300 includes at least one of a camera, a lidar, and a millimeter-wave radar. The camera, lidar, and millimeter-wave radar are positioned at a target location on the platform to acquire real-time data about the virtual vehicle's surrounding environment. The target location can be configured according to actual conditions, such as... Figure 2 As shown in the embodiment of this application, the sensor assembly 100 is placed in two locations, namely image station 1 and image station 2. The host computer 500, real-time machine 200, image station 1, image station 2 and the controller under test 100 are connected through a switch 400, which not only realizes data sharing and interconnection, but also realizes time synchronization.

[0031] It should be noted that both image station 1 and image station 2 in this application embodiment may include multiple 4D radar sensors, multiple surround-view cameras, and multiple forward-view cameras. For example, Figure 2 As shown in Figure ①, data from the 4D radar sensor and the lidar industrial Ethernet sensor are converted to automotive Ethernet via an Ethernet converter and transmitted to the controller under test 100. For example... Figure 2 As shown in ② and ③, station 1 and station 2 transmit camera video data to the controller under test 100 through the video board.

[0032] Furthermore, such as Figure 3 As shown, the switch 400 includes an Ethernet converter and a video converter. The Ethernet converter is used to send the sensing data from the LiDAR and millimeter-wave radar to the controller under test 100, and the video converter is used to send the sensing data from the camera to the controller under test 100.

[0033] In one embodiment of this application, the host computer 500 includes a data processing and analysis module and a user interface module. The data processing and analysis module processes and analyzes test data from the virtual vehicle performing a target test task, evaluates the functionality of the intelligent driving system, and generates a test report. The user interface module is used to set the target test task of the autonomous driving system, display test accuracy, and display at least one of the following: test results. An intuitive and user-friendly interface is provided for setting test parameters, monitoring test progress, and viewing test results.

[0034] The intelligent driving test platform proposed in this application utilizes a real-time machine to build a virtual simulation environment for vehicle driving. This allows for flexible control of the test environment and parameters to meet diverse testing needs. Environmental data collected by sensor components is sent to the controller under test (DUT), which then controls the virtual vehicle to perform target test tasks within the target simulation environment based on the environmental data. This effectively reduces testing costs and risks, and enables rapid and accurate evaluation of the autonomous driving system's performance. Therefore, it solves the problems of high cost, low efficiency, and difficulty in comprehensively covering test scenarios inherent in related technologies that rely on real-world road testing of driving performance.

[0035] Next, referring to the accompanying drawings, a test method for an intelligent driving test platform according to an embodiment of this application is described, which is based on the intelligent driving test platform of the above embodiment for testing.

[0036] Figure 4 This is a flowchart illustrating a testing method for an intelligent driving testing platform provided in an embodiment of this application.

[0037] like Figure 4 As shown, the testing method for this intelligent driving test platform includes the following steps:

[0038] In step S101, the target test task for the autonomous driving system is set.

[0039] The target test task is the specific driving task that the virtual vehicle needs to perform, such as driving to the destination and avoiding obstacles.

[0040] In step S102, the target test task is sent to the real-time machine, which generates a target simulation environment based on the target test task of the autonomous driving system. The sensor components are used to collect environmental data of the virtual vehicle in the target simulation environment. The switch is used to send the target simulation environment to the sensor components and send the environmental data collected by the sensor components to the controller under test. The controller under test controls the virtual vehicle to perform the target test task in the target simulation environment based on the environmental data.

[0041] In step S103, test data of the virtual vehicle performing the target test task is obtained, and test results of the autonomous driving system are generated based on the processing and analysis results of the test data.

[0042] Specifically, the detailed process of the testing method of the intelligent driving test platform in this application includes the following steps:

[0043] 1) Configure sensor equipment: Based on the requirements, set up the appropriate sensor type and configure its placement.

[0044] 2) Building a simulation environment: Using simulation software to build a virtual environment for vehicle driving, including roads, traffic signs, obstacles, etc.

[0045] 3) Set test tasks: Based on the test objectives, set specific driving tasks that the vehicle needs to perform, such as driving to the destination and avoiding obstacles.

[0046] 4) Execute test tasks: Start the test platform, let the vehicle perform the set driving tasks in the simulation environment, and collect data in real time.

[0047] 5) Data analysis and evaluation: Analyze the collected data and evaluate the performance indicators of the intelligent driving system, such as recognition accuracy and path planning effectiveness.

[0048] 6) Generate test report: Generate a test report based on the evaluation results, including the testing process, result analysis, and improvement suggestions.

[0049] In summary, the testing method of the intelligent driving test platform of this application embodiment has been described. Based on the simulation environment provided by the intelligent driving test platform, diverse and safe tests are carried out, which effectively reduces testing costs and risks. It can quickly and accurately evaluate the performance of autonomous driving systems, identify problems and propose improvement suggestions, which helps to accelerate the commercial application of autonomous driving technology.

[0050] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the testing method of the intelligent driving test platform described above.

[0051] This application also provides a computer program or instruction, which, when executed, is used to implement the testing method of the intelligent driving test platform described above.

[0052] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0053] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0054] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0055] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0056] Those skilled in the art will understand that all or part of the steps of the methods implementing the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0057] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. An intelligent driving test platform, characterized in that, include: The controller under test; Real-time machine, used to generate target simulation environment based on the target test task of autonomous driving system; Sensor components are used to collect environmental data of the virtual vehicle in the target simulation environment; A switch is used to send the target simulation environment to the sensor component and send the environmental data collected by the sensor component to the controller under test. The controller under test controls the virtual vehicle to perform the target test task in the target simulation environment according to the environmental data. The host computer is used to send the target test task to the real-time computer and generate the test results of the autonomous driving system based on the test data of the virtual vehicle executing the target test task; The sensor assembly includes at least one of a camera, a lidar, and a millimeter-wave radar; The switch includes an Ethernet converter and a video converter, wherein the Ethernet converter is used to send the sensing data of the LiDAR and the millimeter-wave radar to the controller under test, and the video converter is used to send the sensing data of the camera to the controller under test. The sensor components are placed at two map stations. The host computer, the real-time machine, the two map stations, and the controller under test are connected through the switch, which not only enables data sharing and interconnection but also time synchronization. The industrial Ethernet sensor data of the lidar is converted into vehicle Ethernet through an Ethernet converter and transmitted to the controller under test. The two map stations transmit camera video data to the controller under test through a video board.

2. The intelligent driving test platform according to claim 1, characterized in that, The camera, the lidar, and the millimeter-wave radar are positioned at the target location on the platform.

3. The intelligent driving test platform according to claim 1, characterized in that, The host computer includes a data processing and analysis module and a user interface module. The data processing and analysis module is used to process and analyze the test data of the virtual vehicle performing the target test task. The user interface module is used to set the target test task of the autonomous driving system, display the test accuracy, and display at least one of the test results.

4. The intelligent driving test platform according to claim 1, characterized in that, The target simulation environment includes at least one of the following: urban road environment, highway environment, intersection environment, and weather environment.

5. The intelligent driving test platform according to claim 1, characterized in that, The target test task includes at least one of the following tasks: lane keeping, following other vehicles, and lane changing.

6. A testing method for an intelligent driving test platform, characterized in that, The method is based on the intelligent driving test platform according to any one of claims 1-5, wherein the method includes the following steps: Set target test tasks for the autonomous driving system; The target test task is sent to the real-time machine, wherein the real-time machine is used to generate a target simulation environment according to the target test task of the autonomous driving system, the sensor component is used to collect environmental data of the virtual vehicle in the target simulation environment, the switch is used to send the target simulation environment to the sensor component, and send the environmental data collected by the sensor component to the controller under test, and the controller under test controls the virtual vehicle to perform the target test task in the target simulation environment according to the environmental data. The test data of the virtual vehicle performing the target test task is obtained, and the test results of the autonomous driving system are generated based on the processing and analysis results of the test data.

7. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed, they implement the testing method of the intelligent driving test platform as described in claim 6.

8. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed, they implement the testing method of the intelligent driving test platform as described in claim 6.

Images