Real-vehicle test method and system, computer device, and storage medium

Abstract

The present application relates to the technical field of intelligent driving vehicles. Disclosed are a real-vehicle test method and system, a computer device, and a storage medium. In the present application, a first path for a test vehicle from a current position to a first test start position and a second path for a target object from a current position to a second test start position are determined in a target test scenario, and then the first path and the second path are sent to the test vehicle and the target object, respectively, so that the test vehicle and the target object automatically travel to the corresponding test start positions without requiring being manually driven to a test site, thereby reducing labor input. Then, by means of control information of the test vehicle in the target test scenario, the test vehicle is controlled to undergo a test without requiring being manually driven, which is conducive to improving the real-vehicle test efficiency and the accuracy of a test result. In addition, after the test is completed, the test vehicle and the target object are controlled to automatically reset without requiring manual operation, thereby saving on labor costs.

Description

Real vehicle testing methods, systems, computer equipment and storage media

[0001] Cross-references to related applications

[0002] This application claims priority to Chinese Patent Application No. 202510126599.1, filed on January 27, 2025, entitled “Real Vehicle Testing Method, System, Computer Equipment and Storage Medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of intelligent driving vehicle technology, specifically to real vehicle testing methods, systems, computer equipment, and storage media. Background Technology

[0004] With the development of intelligent driving, intelligent driving assistance technology has become a key research direction in the field of automotive engineering, with numerous companies and research institutions investing heavily in its development. However, the testing phase of intelligent driving vehicles faces many challenges and difficulties in its development process.

[0005] Traditional closed-course testing of intelligent driving relies heavily on manual operation. This requires a large number of specialized testing personnel who not only drive test vehicles through predetermined scenarios and record data, but also repeatedly set up various scenarios and reset equipment. This results in low testing efficiency and high time costs. Furthermore, the limited working hours of testing personnel make it difficult to guarantee the continuity and stability of testing. In addition, human operation is inherently subjective and subject to unavoidable errors; different testing personnel have different driving habits and judgment standards, which can affect the accuracy and consistency of test results. Summary of the Invention

[0006] In view of this, this application provides a real vehicle testing method, system, computer equipment, and storage medium to solve the problems of low testing efficiency, difficulty in ensuring the continuity and stability of testing, and low accuracy and consistency of test results in traditional manual driving test vehicle testing methods.

[0007] Firstly, this application provides a real-vehicle testing method, which includes:

[0008] Obtain the scenario information of the target test scenario, which includes: the first path of the test vehicle from its current position to its first test starting position, the control information of the test vehicle, and the second path of the target object from its current position to its second test starting position.

[0009] The first path and the second path are sent to the test vehicle and the target object respectively, so that the test vehicle can reach the first test starting position of the test vehicle according to the first path, and the target object can reach the second test starting position of the target object according to the second path.

[0010] Control the test vehicle to conduct real vehicle tests based on the control information of the test vehicle;

[0011] When the test termination conditions are met, the test vehicle and the target object are automatically reset respectively.

[0012] Beneficial Effects: This application first determines the first path of the test vehicle from its current position to the first test starting position in the target test scenario, and the second path of the target object from its current position to the second test starting position. Then, the first and second paths are sent to the test vehicle and the target object respectively, enabling them to automatically travel to their respective test starting positions without manual operation, thus reducing manpower. Next, the test vehicle is controlled via control information within the target test scenario, eliminating the need for manual driving and improving the efficiency and accuracy of real-vehicle testing. Furthermore, after the test, the test vehicle and target object are automatically reset without manual operation, further enhancing testing efficiency.

[0013] In one optional implementation, the first path and the second path are sent to the test vehicle and the target object, respectively, including:

[0014] The pose information of each first path point in the first path and the pose information of each second path point in the second path are sent to the test vehicle and the target object, respectively, so that the test vehicle can reach the first test starting position of the test vehicle according to the pose information of each first path point, and the target object can reach the second test starting position of the target object according to the pose information of each second path point; wherein, the pose information includes position coordinates and orientation angle.

[0015] Beneficial effects: This application precisely sets the starting position of the test vehicle and target object by sending the pose information of each path point, ensuring that the initial conditions of each test are highly consistent, eliminating the interference of position errors on the test results, and improving the repeatability and accuracy of the test. Furthermore, clear path point pose information helps the test vehicle and target object operate more stably, reducing system failures or anomalies caused by uncertain position information or unreasonable path planning, and ensuring the smooth progress of the test process.

[0016] In one optional implementation, the test vehicle and the target object are automatically reset, including:

[0017] Obtain the current positions of the test vehicle and the target object after the test ends;

[0018] Based on the current position of the test vehicle after the test and the starting position of the first test, the first reset path of the test vehicle is obtained through path planning. Based on the current position of the target object after the test and the starting position of the second test, the second reset path of the target object is obtained through path planning.

[0019] The first reset path and the second reset path are sent to the test vehicle and the target object respectively, so that the test vehicle returns to the first test start position of the test vehicle according to the first reset path, and the target object returns to the second test start position of the target object according to the second reset path.

[0020] Beneficial effects: This application performs path planning based on the current positions of the test vehicle and the target object after the test is completed, as well as their respective test start positions, to determine the first reset path of the test vehicle and the second reset path of the target object. It controls the test vehicle and the target object to automatically return to the test start position, so as to facilitate subsequent testing. There is no need for test personnel to operate the equipment to return, which reduces manpower input and thus improves test efficiency.

[0021] In one optional implementation, the control information of the test vehicle includes a first planned path and a first motion command for the test vehicle. Controlling the test vehicle to perform real-vehicle testing based on this control information includes:

[0022] The first planned path and the first motion command of the test vehicle are sent to the test vehicle so that the test vehicle can perform lateral and / or longitudinal movements according to the first motion command and drive in the target test scenario according to the first planned path.

[0023] Beneficial effects: This application sends the first planned path and the first motion command to the test vehicle to control the lateral and longitudinal movement and driving path of the test vehicle during the actual vehicle test process. It does not require frequent manual intervention and adjustment, and can continuously and efficiently complete various test tasks, reduce test time and cost, improve the overall efficiency of test work, and make the test process more standardized and regulated, making it easier for test personnel to operate and monitor.

[0024] In one optional implementation, the control information for the test vehicle includes a first motion command for the test vehicle, and controlling the test vehicle to perform real-vehicle testing based on the control information includes:

[0025] The first motion command of the test vehicle is sent to the test vehicle so that the test vehicle can perform lateral and / or longitudinal movements according to the first motion command and drive in the target test scenario according to its stored memory path.

[0026] Beneficial effects: When the test vehicle of this application is tested for the first time in the target test scenario, the first planned path can be stored. When testing again in the target test scenario, only the first motion command of the test vehicle needs to be sent to the test vehicle. The test vehicle will drive in the target test scenario according to its stored memory path, thereby repeatedly utilizing the control information of the test vehicle, simplifying the sending and receiving of test data in the test process, and improving test efficiency.

[0027] In one optional implementation, the control information for the test vehicle includes emergency control commands. Controlling the test vehicle to conduct real-vehicle testing based on this control information includes:

[0028] The test vehicle is controlled to drive in the target test scenario based on its own advanced driver assistance system;

[0029] When a malfunction is detected in the advanced driver assistance system of the test vehicle, an emergency control command is sent to the test vehicle to control its movement.

[0030] Beneficial effects: After arriving at the test starting position, the test vehicle of this application can rely on its own advanced driver assistance system (ADAS) to drive in the target test scenario to test the ADAS. If the ADAS malfunctions, an emergency control command will be sent to the test vehicle to take over control, thereby avoiding a collision and ensuring the safety of the equipment at the test site.

[0031] In an optional implementation, when the target test scenario is a dynamic test scenario, the scenario information further includes control information of the target object; after the target object reaches its second test starting position according to the second path, the method further includes:

[0032] Controlling the target object based on the target object's control information; wherein, the target object's control information includes the target object's second planned path and second motion command.

[0033] Beneficial effects: After the target object reaches the second test starting position, this application also controls the target object based on the second planned path and the second motion command to construct a dynamic test scenario, simulate various complex situations in real driving scenarios, and thus improve the richness and comprehensiveness of the test results.

[0034] In an alternative implementation, before controlling the target object based on the target object's control information, the method further includes:

[0035] The calling interface of the device calling program is detected. The calling interface of the device calling program is used to communicate with the device interface of the target object.

[0036] After the device calling program passes the call interface test, the control information of the target object is input into the device calling program to control the target object.

[0037] Beneficial effects: This application enables the device to invoke the target object through the device invocation program, which allows for efficient communication and collaborative work with the target object, improves the system's automation level, facilitates centralized management and control of the target object, and enhances the overall operating efficiency and reliability of the system.

[0038] In one optional implementation, before controlling the test vehicle to conduct real-vehicle testing based on the test vehicle's control information, the method further includes:

[0039] The latest positions of the test vehicle and the target test equipment are obtained respectively, and it is determined whether the first error between the latest position of the test vehicle and the first test starting position and the second error between the latest position of the target and the second test starting position meet the error threshold condition.

[0040] If the first error and / or the second error do not meet the error threshold condition, the position of the test vehicle and / or the target object shall be adjusted.

[0041] Beneficial effects: This application ensures that the test vehicle and the target object are in the set test starting position by calibrating the positioning of the test vehicle and the target object, thereby reducing test repetition and adjustment caused by position deviation and improving test efficiency.

[0042] In an optional implementation, before obtaining the scene information of the target test scene, the method further includes:

[0043] Display a visual interface and show drag-and-drop components corresponding to the test vehicle and the target object;

[0044] Obtain the user's configuration information for the drag-and-drop component, and based on the configuration information, obtain the scenario information for the test scenario.

[0045] Beneficial effects: This application makes it easy for users to configure the test scenario information by dragging and dropping components in a visual interface, thus building test scenarios. Compared with the traditional test scenario design through complex code or instructions, this reduces the threshold for use and improves the efficiency of test scenario construction.

[0046] In one alternative implementation, the method further includes:

[0047] Acquire motion status information and / or abnormal event information of the test vehicle and the target object respectively;

[0048] Displays motion status information and / or abnormal event information.

[0049] Beneficial effects: This application enables testers to understand the motion status of the test vehicle and target object in real time by acquiring and displaying their motion status information, so as to intuitively judge whether the test vehicle and target object are running according to the predetermined trajectory and parameters; in addition, the acquisition and display of abnormal event information enables testers to perform timely maintenance and adjustment of the test vehicle and target object, ensuring equipment safety.

[0050] Secondly, this application provides a real vehicle testing system, which includes an automatic scenario building platform, a test vehicle, and a target object, wherein the automatic scenario building platform is used for the real vehicle testing method of the first aspect above or any corresponding embodiment.

[0051] In one optional implementation, the test vehicle includes a test vehicle domain controller, and the target object includes a target object domain controller. The test vehicle domain controller and the target object domain controller establish communication connections with the scene automatic construction platform through a communication base station.

[0052] Thirdly, this application provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle testing method of the first aspect or any corresponding embodiment described above.

[0053] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle testing method described in the first aspect or any corresponding embodiment thereof.

[0054] The beneficial effects of this application are as follows:

[0055] First, the first path from the test vehicle's current position to the first test starting position and the second path from the target object's current position to the second test starting position are determined in the target test scenario. Then, the first and second paths are sent to the test vehicle and the target object respectively, enabling them to automatically travel to their respective test starting positions without manual operation, thus reducing manpower. Next, the test vehicle is controlled via control information from the target test scenario, eliminating the need for manual driving and improving the efficiency and accuracy of real-vehicle testing. Furthermore, after the test, the test vehicle and target object are automatically reset without manual operation, saving labor costs. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0057] Figure 1 is a structural block diagram of a real vehicle testing system according to an embodiment of this application;

[0058] Figure 2 is a schematic diagram of a real vehicle testing system according to an embodiment of this application;

[0059] Figure 3 is a flowchart illustrating the real vehicle testing method according to an embodiment of this application;

[0060] Figure 4 is a flowchart illustrating another real-vehicle testing method according to an embodiment of this application;

[0061] Figure 5 is a structural block diagram of another real vehicle testing system according to an embodiment of this application;

[0062] Figure 6 is a structural block diagram of another real vehicle testing system according to an embodiment of this application;

[0063] Figure 7 is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0065] Traditional closed-course testing of intelligent driving relies heavily on manual operation, which has significant drawbacks. Manual testing requires a large number of specialized test personnel who not only drive test vehicles according to predetermined scenarios and record data, but also repeatedly set up various scenarios and reset equipment, resulting in low testing efficiency and high time costs. For example, in Automatic Emergency Braking (AEB) testing, the process of operating and debugging equipment and setting parameters when switching between different scenarios is complex and prone to errors. Furthermore, prolonged AEB testing can be harmful to the health of test personnel. Moreover, manual testing is relatively inefficient, with limited working hours for test personnel, leading to fatigue and difficulty in ensuring the continuity and stability of testing. In addition, human operation is subject to subjectivity and unavoidable errors; different test personnel have different driving habits and judgment standards, affecting the accuracy and consistency of test results.

[0066] Therefore, this application provides a real vehicle testing method. By constructing an integrated solution of automatic mobile platform and automatic scene construction, it can comprehensively, efficiently and accurately realize scene construction and closed site testing, greatly reducing testing costs and manpower input, and improving testing efficiency, accuracy and comprehensiveness.

[0067] According to an embodiment of this application, a real vehicle testing system is provided, as shown in Figure 1. The real vehicle testing system includes: an automatic scene building platform 101, a test vehicle 102, and a target object 103.

[0068] Specifically, the scene automatic construction platform 101 acquires scene information of the target test scene, including: the first path of the test vehicle 102 from its current position to its first test starting position, the control information of the test vehicle 102, and the second path of the target object 103 from its current position to its second test starting position.

[0069] Furthermore, the scene automatic construction platform 101 sends the first path and the second path to the test vehicle 102 and the target object 103 respectively, so that the test vehicle 102 reaches its first test starting position according to the first path, and the target object 103 reaches its second test starting position according to the second path. The scene automatic construction platform 101 controls the test vehicle 102 to conduct real vehicle testing based on the control information of the test vehicle 102; when the test termination conditions are met, the test vehicle 102 and the target object 103 are automatically reset respectively.

[0070] It should be noted that the embodiment of this application is based on the example of a real vehicle testing system containing one test vehicle 102. In actual applications, the real vehicle testing system may also include two, three or more test vehicles 102. The specific number of test vehicles 102 is related to the testing requirements of the real vehicle testing system, and this application is not limited thereto.

[0071] The vehicle testing system provided in this application embodiment, before the start of the actual vehicle test, the scene automatic construction platform 101 first determines the first path of the test vehicle 102 from its current position to the first test starting position, and the second path of the target object 103 from its current position to the second test starting position in the target test scene. Then, the first and second paths are sent to the test vehicle 102 and the target object 103 respectively, so that the test vehicle 102 and the target object 103 automatically drive to the corresponding test starting positions, eliminating the need for manual operation of the test vehicle and target object to travel to the test site, thus reducing manpower input. Then, the scene automatic construction platform 101 controls the test vehicle 102 to conduct the test using the control information of the test vehicle 102 in the target test scene, eliminating the need for manual driving of the test vehicle, which helps improve the efficiency of actual vehicle testing and the accuracy of test results. Furthermore, after the test, the scene automatic construction platform 101 automatically resets the test vehicle 102 and the target object 103 by controlling them, eliminating the need for manual equipment reset, further improving testing efficiency.

[0072] The specific working principles and processes of the scene automatic construction platform 101, test vehicle 102, and target object 103 are described in the relevant descriptions of the method embodiments below, and will not be repeated here.

[0073] In some optional implementations, the test vehicle 102 includes a test vehicle domain controller, and the target object 103 includes a target object domain controller. The test vehicle domain controller and the target object domain controller establish communication connections with the scene automatic construction platform via a communication base station. For example, the target object 103 can be placed on a target object carrying platform, enabling the movement of the target object 103. The scene automatic construction platform 101 works collaboratively with the test vehicle domain controller and the target object domain controller to control the test vehicle 102 and the target object carrying platform that carries the target object 103.

[0074] Specifically, based on the second path of target object 103, the target object carrying platform automatically travels to the second test starting position corresponding to each test scenario. The test vehicle 102 travels according to the driving or parking path memorized by its own high-precision map. The two work together to traverse and execute closed-scenario real vehicle test cases. After completing each test case, the target object carrying platform and the test vehicle 102 automatically reset, realizing the automatic construction of test scenarios and the automated execution of test processes, thereby improving test efficiency.

[0075] In some optional implementations, as shown in Figure 2, the scene automatic construction platform 101, the test vehicle 102, and the target object 103 all connect to the communication base station of the test site via a wireless network. Both the test vehicle 102 and the target object 103 are equipped with wireless communication and positioning devices, and they transmit location information back to the scene automatic construction platform 101 in real time via the wireless network. The target object 103 can be a target vehicle, a target cyclist, a target pedestrian, a target obstacle, etc., and this application is not limited to these.

[0076] Furthermore, according to the requirements of each test scenario, the scene automatic construction platform 101 transmits the first test starting position of the test vehicle 102, the second test starting position of the target object 103, the first path of the test vehicle 102, and the second path of the target object 103 to the test vehicle 102 and the target object 103 respectively via a wireless network before the start of each test scenario. The test vehicle 102 and the target object 103 move to the test starting position according to their current positions and corresponding paths. The scene automatic construction platform 101 can also use site positioning data to define the boundary restriction information of the test site, ensuring that the movement of the test vehicle 102 and the target object 103 does not exceed the site boundary.

[0077] The real vehicle testing system provided in this application enables the test vehicle 102 and the target object 103 to automatically go to the test start position of each test scenario through the collaborative work between the scenario automatic construction platform 101, the test vehicle 102 and the target object 103, and execute real vehicle test cases in the test scenario to automatically conduct real vehicle testing.

[0078] According to an embodiment of this application, a real vehicle testing method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0079] This embodiment provides a real vehicle testing method, which can be used to automatically build a platform 101 for the scenario shown in Figure 1, such as a computer device. Figure 3 is a flowchart of the real vehicle testing method according to an embodiment of this application. As shown in Figure 3, the process includes the following steps:

[0080] Step S301: Obtain scene information of the target test scenario. The scene information includes: the first path of the test vehicle from its current position to its first test starting position, the control information of the test vehicle, and the second path of the target object from its current position to its second test starting position.

[0081] In some optional implementations, a visualization interface is displayed, showing draggable components corresponding to the test vehicle and the target object. By obtaining the user's configuration information for the draggable components, and based on this configuration information, scenario information for the test scenario is obtained.

[0082] Specifically, users can drag and drop components representing different test devices in the visual interface and configure information such as device type, number of devices, starting position in the test scenario, planned path, movement commands, and boundary restrictions of the test site. After the user clicks the submit button, the front end sends the user's configuration information to the back end. The back end generates scenario information for the test scenario based on the configuration information, thereby constructing various test scenarios and storing them in the scenario library of the scenario building platform.

[0083] For example, an AEB field test scenario library can be built using drag-and-drop components corresponding to targets such as vehicles, children, pedestrians, cyclists, and tricycles. This AEB field test scenario library covers standard scenarios such as crossing, going straight, and turning of the target in various scenarios.

[0084] For example, a standard scenario library for parking site testing can be constructed, including marked perpendicular parking spaces, marked parallel parking spaces, marked angled parking spaces, spatial perpendicular parking spaces, spatial parallel parking spaces, spatial angled parking spaces, and combinations of lines, spaces, and various obstacles. Obstacles include pillars, suspended obstacles, cones, water-filled barriers, pedestrians, parking locks, curbs, etc., but this application is not limited to these.

[0085] It should be noted that for each test scenario in the scenario library, the scenario information must include at least the following items: the first path of the test vehicle from its current position to its first test starting position, the control information of the test vehicle, and the second path of the target object from its current position to its second test starting position. For each test scenario, based on the site conditions, the test starting positions of the test vehicle and the target object can be fixed and memorized using the site-end positioning equipment.

[0086] In some alternative implementations, the first path of the test vehicle and the second path of the target object can be planned based on the relative positions between the current position and the test starting position, following the principle of the shortest route, and on-site personnel are required to confirm that there are no obstacles within the path outline. If the test vehicle or the target object experiences equipment malfunction due to a collision while traveling to the test starting position, the test personnel should be alerted.

[0087] This embodiment displays drag-and-drop components in a visual interface, making it easy for users to configure test scenario information by dragging and dropping to build test scenarios. Compared with the traditional method of designing test scenarios through complex code or instructions, this reduces the barrier to entry and improves the efficiency of test scenario construction.

[0088] In step S302, the first path and the second path are sent to the test vehicle and the target object respectively, so that the test vehicle reaches the first test starting position of the test vehicle according to the first path, and the target object reaches the second test starting position of the target object according to the second path.

[0089] Specifically, the pose information of each first path point in the first path and the pose information of each second path point in the second path are sent to the test vehicle and the target object, respectively, so that the test vehicle can reach the first test starting position of the test vehicle according to the pose information of each first path point, and the target object can reach the second test starting position of the target object according to the pose information of each second path point; wherein, the pose information includes position coordinates and orientation angle.

[0090] This embodiment precisely sets the starting positions of the test vehicle and target object by sending the pose information of each path point, ensuring that the initial conditions are highly consistent for each test, eliminating the interference of position errors on the test results, and improving the repeatability and accuracy of the test. Furthermore, clear path point pose information helps the test vehicle and target object operate more stably, reducing system failures or anomalies caused by uncertain position information or unreasonable path planning, and ensuring the smooth progress of the test process.

[0091] In some optional implementations, when the target test scenario is a dynamic test scenario, the scenario information also includes the control information of the target object. After the target object arrives at the second test scenario, the target object can be controlled based on the control information of the target object. The control information of the target object includes the second planned path and the second movement command of the target object.

[0092] Specifically, dynamic test scenarios are relative to static test scenarios. In a static test scenario, the target object will not move after reaching the second test starting position; while in a dynamic test scenario, the target object will move according to the second planned path and the second movement command to simulate various complex situations in real driving scenarios, thereby improving the richness and comprehensiveness of the test results.

[0093] In some optional implementations, before controlling the target object based on its control information, the calling interface of the device calling program is checked. This calling interface is used to communicate with the device interface of the target object. After the calling interface of the device calling program passes the check, the control information of the target object is input to the device calling program to control the target object.

[0094] Specifically, a device interface corresponding to the target object should be provided so that the target object can be invoked through the calling interface of the device invocation program. For target objects that cannot provide a device interface, a control program can be built through icon self-learning to invoke the device.

[0095] For example, when testing the calling interface of the device calling program, you can try to connect to the IP address and port specified by the target device interface to check whether the target device's network connection is normal; you can also send test data to the target device to check whether the data can be sent successfully and check whether the target device's response data can be received. If no response is received or a communication error occurs, give the corresponding prompt.

[0096] This embodiment invokes the target object through a device invocation program, enabling efficient communication and collaborative work with the target object, improving the system's automation level, facilitating centralized management and control of the target object, and enhancing the overall system's operating efficiency and reliability.

[0097] In some optional implementations, before executing step S303, the latest positions of the test vehicle and the target testing equipment can be obtained respectively, and it can be determined whether the first error between the latest position of the test vehicle and the first test starting position, and the second error between the latest position of the target and the second test starting position, meet the error threshold condition. If the first error and / or the second error do not meet the error threshold condition, the positions of the test vehicle and / or the target are adjusted.

[0098] For example, the aforementioned device invocation procedure may also include a device positioning calibration procedure. The device positioning link needs to be manually debugged and confirmed to be complete in order to facilitate device positioning calibration and device invocation self-test. During device positioning calibration, the test vehicle and target object can automatically check whether the signal search and detection accuracy meets the requirements, and can also upload the relevant location information to the scene automatic construction platform for analysis. If the requirements are not met, the test personnel will be prompted to perform the next step, such as adjusting the device position.

[0099] This application calibrates the positioning of the test vehicle and the target object to ensure that they are in the set starting position for testing, thereby reducing test repetitions and adjustments caused by positional deviations and improving testing efficiency.

[0100] Step S303: Control the test vehicle to conduct real vehicle testing based on the control information of the test vehicle.

[0101] Specifically, the control information of the test vehicle includes a first planned path and / or a first motion command for the test vehicle. Based on the actual test requirements, the corresponding control information of the test vehicle is sent to the test vehicle to control the test vehicle to carry out the test.

[0102] Furthermore, the system can acquire and display motion status information and / or abnormal event information of the test vehicle and target object, allowing test personnel to monitor the speed, acceleration, position, and other motion status of the test vehicle and target object in real time. This enables them to intuitively determine whether the test vehicle and target object are operating according to the predetermined trajectory and parameters. Moreover, the acquisition and display of abnormal event information allows test personnel to promptly perform maintenance and adjustments on the test vehicle and target object, ensuring equipment safety.

[0103] In some optional implementations, the displayed visual interface can also show information such as the scenario library and selection interface, the planned paths of the test vehicle and target objects, the test site area, equipment type, real-time positioning and motion status, equipment fault prompts, and test progress display of the test scenario library, making it convenient for testers to view. In addition, operation buttons such as start, end, and pause can be provided to facilitate testers to control the test process.

[0104] Step S304: When the test end conditions are met, the test vehicle and the target object are automatically reset respectively.

[0105] Specifically, the reset paths for the test vehicle and target object can be planned based on their current positions after the test and their starting positions in the test scenario, following the principle of the shortest route. If a malfunction occurs during the reset of the test vehicle or target object, the operator should be notified promptly. For equipment malfunctions caused by collisions, the operator should be given appropriate instructions.

[0106] It should be noted that the test termination condition can be set according to the actual scenario, such as receiving a termination instruction from the tester, but this application is not limited to this.

[0107] The real-vehicle testing method provided in this embodiment first determines the first path of the test vehicle from its current position to the first test starting position, and the second path of the target object from its current position to the second test starting position in the target test scenario. Then, the first and second paths are sent to the test vehicle and the target object respectively, enabling them to automatically travel to their respective test starting positions without manual operation, thus reducing manpower. Next, the test vehicle is controlled via control information from the target test scenario, eliminating the need for manual driving and improving the efficiency and accuracy of real-vehicle testing. Furthermore, after the test, the test vehicle and the target object are automatically reset without manual operation, saving labor costs.

[0108] This embodiment provides a real vehicle testing method, which can be used to automatically build a platform 101 for the scenario shown in Figure 1, such as a computer device. Figure 4 is a flowchart of the real vehicle testing method according to an embodiment of this application. As shown in Figure 4, the process includes the following steps:

[0109] Step S401: Obtain scene information of the target test scenario. Scene information includes: the first path of the test vehicle from its current position to its first test starting position, the control information of the test vehicle, and the second path of the target object from its current position to its second test starting position. For details, please refer to the specific description of step S401 in the embodiment shown in Figure 3, which will not be repeated here.

[0110] In step S402, the first path and the second path are sent to the test vehicle and the target object, respectively, so that the test vehicle reaches its first test starting position according to the first path, and the target object reaches its second test starting position according to the second path. For details, please refer to the specific description of step S402 in the embodiment shown in Figure 3, which will not be repeated here.

[0111] Step S403: Control the test vehicle to conduct real vehicle testing based on the control information of the test vehicle.

[0112] In some optional implementations, the control information of the test vehicle includes a first planned path and a first motion command of the test vehicle. The first planned path and the first motion command of the test vehicle are sent to the test vehicle so that the test vehicle can perform lateral and / or longitudinal movements according to the first motion command and drive in the target test scenario according to the first planned path.

[0113] This application sends the first planned path and the first motion command to the test vehicle to control the lateral and longitudinal movement and driving path of the test vehicle during the actual vehicle test. It does not require frequent manual intervention and adjustment, and can continuously and efficiently complete various test tasks, reduce test time and cost, improve the overall efficiency of test work, and make the test process more standardized and regulated, making it easier for test personnel to operate and monitor.

[0114] In some optional implementations, the control information of the test vehicle includes a first motion command for the test vehicle. The first motion command is sent to the test vehicle so that the test vehicle can perform lateral and / or longitudinal movements according to the first motion command and travel in the target test scenario according to its stored memory path.

[0115] In this embodiment, when the test vehicle is tested for the first time in the corresponding test scenario, it can use its own high-precision map and positioning equipment to memorize and store the first planned path, forming a memorized path. Subsequent tests in the same test scenario only require sending the test vehicle's first motion command. The test vehicle will then travel according to its stored memorized path, repeatedly utilizing the test vehicle's control information, simplifying the data transmission and reception process, and improving testing efficiency.

[0116] In some alternative implementations, the control information for the test vehicle includes emergency control commands to control the test vehicle to drive in the target test scenario based on its own advanced driver assistance system; when a malfunction of the test vehicle's advanced driver assistance system is detected, emergency control commands are sent to the test vehicle to control the test vehicle's driving.

[0117] Specifically, there are no restrictions on the movement or travel path of the test vehicle. After arriving at the test starting position, the test vehicle can rely on its own advanced driver assistance system (ADAS) to drive in the target test scenario to test the ADAS. If the ADAS malfunctions, an emergency control command is sent to the test vehicle to take over control, thereby avoiding a collision and ensuring the safety of the equipment at the test site.

[0118] Step S404: When the test end conditions are met, the test vehicle and the target object are automatically reset respectively.

[0119] Specifically, step S404 includes:

[0120] Step S4041: Obtain the current positions of the test vehicle and the target object after the test ends.

[0121] Step S4042: Based on the current position of the test vehicle after the test and the first test start position, a path is planned to obtain the first reset path of the test vehicle; and based on the current position of the target object after the test and the second test start position, a path is planned to obtain the second reset path of the target object.

[0122] Specifically, based on the current positions of the test vehicle and the target object after the test and their respective test start positions, the shortest path can be planned to determine the reset path of the test vehicle and the target object.

[0123] In step S4043, the first reset path and the second reset path are sent to the test vehicle and the target object respectively, so that the test vehicle returns to the first test start position of the test vehicle according to the first reset path, and the target object returns to the second test start position of the target object according to the second reset path.

[0124] Specifically, the first reset path and the second reset path are sent to the test vehicle and the target object respectively, so that the test vehicle and the target object can automatically return to the test start position to facilitate subsequent testing. This eliminates the need for test personnel to operate the equipment to return, reducing manpower input and thus improving testing efficiency.

[0125] The following section provides a detailed explanation of the real-vehicle testing method of this application, using a specific application example.

[0126] As shown in Figure 5, the scene automatic setup platform, test vehicle, target object, and communication base station of the test site constitute the overall real vehicle test system. The scene automatic setup platform includes a data receiving module, a scene setup module, and a data sending module. The test vehicle domain controller and the target object domain controller establish communication connections with the scene automatic setup platform through the communication base station.

[0127] The data receiving module is used to receive high-precision positioning information, motion status information, and abnormal event information of the test vehicle, as well as high-precision positioning information, motion status information, and abnormal event information of the target object.

[0128] The scenario setup module is used to process the data input from the data receiving module, including test scenario orchestration, selection of the test start position of the test scenario, calculation of the test vehicle / target position, test vehicle / target path planning, reset path calculation, and boundary control of the test site.

[0129] The data transmission module is used to send the planned path and motion commands of the test vehicle output by the scene building module to the test vehicle domain controller through the communication base station, and to send the planned path and motion commands of the target object to the target object domain controller through the communication base station.

[0130] The test vehicle domain controller includes a wireless communication module, a motion control module, and a high-precision positioning module. The wireless communication module sends the planned path and motion commands received from the test vehicle to the motion control module. The motion control module executes the planned path and motion commands to control the test vehicle's lateral and longitudinal movements and feeds back the test vehicle's motion status information to the wireless communication module. The high-precision positioning module acquires the test vehicle's high-precision positioning information and feeds it back to the wireless communication module. The wireless communication module then sends the test vehicle's high-precision positioning information, motion status information, and abnormal event information to the scene automation platform.

[0131] The target object domain controller also includes a wireless communication module, a motion control module, and a high-precision positioning module. Its specific working principle is similar to that of the test vehicle domain controller, and will not be described in detail here.

[0132] The aforementioned real-vehicle testing system utilizes an automatic scenario building platform to receive information from the test vehicle and target objects. After processing, the information is imported into the scenario building module for position calculation, scenario start point selection, reset path calculation, path planning, and other functions to complete the test scenario arrangement. The system then outputs the planned path and motion commands to the test vehicle and target objects. A communication base station acts as an information relay to ensure network communication. The test vehicle domain controller provides positioning information through its built-in high-precision positioning module, executes motion commands through its motion control module, and sends positioning information, motion status information, and receives planned path and motion command information through its wireless communication module. The target object domain controller also provides positioning information through its built-in high-precision positioning module, executes motion commands through its motion control module, and sends positioning information, motion status information, and receives planned path and motion command information through its wireless communication module.

[0133] As shown in Figure 6, the vehicle system includes the vehicle under test, the domain control system, and equipment such as cameras / millimeter-wave radar.

[0134] The vehicle under test, serving as a platform for advanced driver assistance systems (ADAS), must possess excellent mechanical performance and electrical compatibility to ensure the stable operation of the ADAS. Key components such as the vehicle's powertrain, braking system, and steering system must accurately respond to control commands issued by the external domain controller, enabling operations such as acceleration, deceleration, and steering.

[0135] The domain control system stores fixed planned paths in parking or driving test scenarios using high-precision maps, and automatically traverses and executes these paths according to the test scenario library and the scenario-based platform. An external domain controller can be deployed in the trunk of the vehicle under test, responsible for sending real-time vehicle control commands to the vehicle's actuators. It enables control of the vehicle's driving status. The external domain controller adapts to the vehicle's communication protocol, controlling the vehicle under test to repeatedly execute tests during advanced driver assistance system (ADAS) testing. Simultaneously, in the event of a malfunction or anomaly in the ADAS, the domain controller promptly takes over vehicle control to ensure safe driving and monitors and records the ADAS's operational status in real time, providing additional data support for test result analysis and ensuring the safety and reliability of unmanned testing.

[0136] Furthermore, a high-precision integrated navigation system can be installed in the trunk of the vehicle under test, providing centimeter-level high-precision positioning data for the entire real-vehicle testing system. During unmanned testing, this high-precision positioning data is crucial for the cloud to accurately grasp the vehicle's location, make precise scheduling arrangements, and generate reasonable pre-control commands.

[0137] Referring again to Figure 6, the roadside system may include equipment such as cameras, millimeter-wave radar, traffic lights, multi-access edge computing (MEC) devices, positioning base stations, local area networks, and global positioning satellite systems. The positioning base stations are fixed at the test site and primarily receive location signals from relevant equipment. Based on high-precision maps and local area networks, they locate and memorize information such as the parking test path and the starting position. Using global positioning satellite systems such as GPS and BeiDou, they provide precise location services for the tested vehicle on the road, employing a combination of multi-satellite positioning technology and ground augmentation technology to achieve centimeter-level or even millimeter-level positioning accuracy.

[0138] The equipment system includes a mobile platform carrying the target object, various obstacles in the test scenario, positioning devices, and positioning base stations. The target object receives calls from the equipment's invocation program, moves from its current location to the test start position in the test scenario according to the corresponding path, and automatically resets. Based on the scenario, the platform automatically builds a communication protocol with MQTT, relying on a local real-time network to send control commands to the target object's external domain controller for control and invocation. The target object's platform control system may include a scheduling control platform, a control box, an integrated antenna, the target platform, and base stations. The scheduling control platform sends start / stop control commands to the control box (communication interface is open), and the control box relays relevant commands to the target platform in real time via the integrated antenna. The base station receives the test platform's location data in real time and sends it to the target platform.

[0139] In addition, a coordinate transformation system can be provided, with a fixed coordinate origin. This coordinate origin is used as the reference point for the test scenario. All test scenario setup data is derived from this reference point. The coordinate origin, base station location, and target object mounted platform control system have a fixed geometric relationship, allowing for coordinate system transformation to adapt to various closed sites.

[0140] This application example also provides a real-vehicle testing process, which mainly includes the following steps:

[0141] Step 1: Equipment Assembly and Self-Test. The positioning base station, vehicle-mounted positioning equipment, and target object on the target object carrying platform need to be manually assembled to ensure normal and uninterrupted communication of all equipment. Set up the base station, install the positioning equipment on the vehicle, and complete the communication self-test and equipment self-test and preparation through the equipment program. The self-test includes search status, signal strength, positioning accuracy and the response of each device, whether the field signal is unobstructed, and whether the target address is accurate, etc.

[0142] Step 2: Select the test scenario and the starting positions for the test vehicle and target within that scenario. Based on the test requirements, select the scenario to be tested within the platform, and determine the test reference point, base station fixed point, test vehicle, and target's starting positions. For fixed scenarios, the corresponding positions and equipment movement trajectories must be saved in advance using a high-precision map. The platform calls the device to the test starting position via the device interface or other methods (buttons within the device software). Simultaneously, it controls the vehicle to follow the planned path to the saved test starting position by matching the vehicle's protocol with an external domain controller. Path planning can be based on the shortest travel distance between the current position and the target position, and the vehicle's posture should be adjusted to maintain consistency with the original saved posture. During this process, the test personnel must confirm that there are no obstacles within the path outline.

[0143] Step 3, repeat the test. Using the automated scenario-based platform, iterate through each test scenario according to the scenario library. After each scenario test is completed, the vehicle returns to the test starting position along the memorized route, and the target object carrying platform also automatically resets to the test starting position.

[0144] Step 4, Anomaly Handling. When a target object or vehicle collides with another vehicle, or when a remote termination command is received, the vehicle and related equipment will automatically stop, awaiting manual inspection and recovery.

[0145] Step 5, Test End. When the test scenario traversal is complete, the vehicle and equipment automatically return to the test starting position; or upon receiving a remote emergency stop command, the vehicle immediately and safely stops, and the equipment ceases movement.

[0146] This application embodiment also provides a computer device having the scene automatic building platform 101 shown in FIG1 above.

[0147] Please refer to Figure 7, which is a schematic diagram of the structure of a computer device provided in an optional embodiment of this application. As shown in Figure 7, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be installed on a common motherboard or otherwise as needed. The processor can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 7 uses one processor 10 as an example.

[0148] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0149] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0150] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0151] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0152] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means; Figure 7 shows an example of a connection via a bus.

[0153] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0154] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0155] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0156] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A real-vehicle testing method, characterized in that, The method includes: Obtain scene information of the target test scenario, including: the first path of the test vehicle from its current position to its first test starting position, the control information of the test vehicle, and the second path of the target object from its current position to its second test starting position. The first path and the second path are sent to the test vehicle and the target object respectively, so that the test vehicle reaches the first test starting position of the test vehicle according to the first path, and the target object reaches the second test starting position of the target object according to the second path. Control the test vehicle to conduct real vehicle tests based on the control information of the test vehicle; When the test termination conditions are met, the test vehicle and the target object are automatically reset respectively.

2. The method according to claim 1, characterized in that, The step of sending the first path and the second path to the test vehicle and the target object, respectively, includes: The pose information of each first path point in the first path and the pose information of each second path point in the second path are sent to the test vehicle and the target object, respectively, so that the test vehicle can reach the first test starting position of the test vehicle according to the pose information of each first path point, and the target object can reach the second test starting position of the target object according to the pose information of each second path point; wherein, the pose information includes position coordinates and orientation angle.

3. The method according to claim 2, characterized in that, The automatic reset of the test vehicle and the target object includes: Obtain the current positions of the test vehicle and the target object after the test ends; Based on the current position of the test vehicle after the test and the starting position of the first test, the first reset path of the test vehicle is obtained through path planning. Based on the current position of the target object after the test and the starting position of the second test, the second reset path of the target object is obtained through path planning. The first reset path and the second reset path are sent to the test vehicle and the target object respectively, so that the test vehicle returns to the first test start position of the test vehicle according to the first reset path, and the target object returns to the second test start position of the target object according to the second reset path.

4. The method according to claim 1, characterized in that, The control information for the test vehicle includes the test vehicle's first planned path and first motion command. Controlling the test vehicle to conduct real-vehicle testing based on this control information includes: The first planned path and the first motion command of the test vehicle are sent to the test vehicle so that the test vehicle can perform lateral and / or longitudinal movements according to the first motion command and drive in the target test scenario according to the first planned path.

5. The method according to claim 1, characterized in that, The control information for the test vehicle includes the test vehicle's first motion command. Controlling the test vehicle to conduct real-vehicle testing based on this control information includes: The test vehicle is given a first motion command, which enables it to move laterally and / or longitudinally according to the first motion command and to travel in the target test scenario according to its stored memory path.

6. The method according to claim 1, characterized in that, The control information for the test vehicle includes emergency control commands. Controlling the test vehicle to conduct real-vehicle tests based on this control information includes: The test vehicle was controlled to drive in the target test scenario based on its own advanced driver assistance system. When a malfunction is detected in the advanced driver assistance system of the test vehicle, the emergency control command is sent to the test vehicle to control its movement.

7. The method according to claim 1, characterized in that, When the target test scenario is a dynamic test scenario, the scenario information also includes control information of the target object; after the target object reaches its second test starting position according to the second path, the method further includes: Controlling the target object based on the target object's control information; wherein, the target object's control information includes the target object's second planned path and second motion command.

8. The method according to claim 7, characterized in that, Before controlling the target object based on the target object's control information, the method further includes: The calling interface of the device calling program is detected. The calling interface of the device calling program is used to communicate with the device interface of the target object. After the device calling program's calling interface passes the test, the control information of the target object is input into the device calling program to control the target object.

9. The method according to any one of claims 1-8, characterized in that, Before controlling the test vehicle to conduct real-vehicle testing based on the control information of the test vehicle, the method further includes: The latest positions of the test vehicle and the target test equipment are obtained respectively, and it is determined whether the first error between the latest position of the test vehicle and the first test starting position and the second error between the latest position of the target and the second test starting position meet the error threshold condition. If the first error and / or the second error do not meet the error threshold condition, the position of the test vehicle and / or the target object shall be adjusted.

10. The method according to any one of claims 1-8, characterized in that, Before obtaining the scenario information of the target test scenario, the method further includes: Display a visual interface and show drag-and-drop components corresponding to the test vehicle and the target object on the visual interface; Obtain the user's configuration information for the drag-and-drop component, and based on the configuration information, obtain the scenario information for the test scenario.

11. The method according to any one of claims 1-8, characterized in that, The method further includes: Acquire motion status information and / or abnormal event information of the test vehicle and the target object respectively; Display the motion status information and / or the abnormal event information.

12. A real vehicle testing system, characterized in that, The system includes an automatic scenario building platform, a test vehicle, and a target object, wherein the automatic scenario building platform is used to execute any one of the real vehicle testing methods described in 1 to 11.

13. The system according to claim 12, characterized in that, The test vehicle includes a test vehicle domain controller, and the target object includes a target object domain controller. The test vehicle domain controller and the target object domain controller respectively establish communication connections with the scene automatic construction platform through a communication base station.

14. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the real vehicle testing method according to any one of claims 1 to 11 by executing the computer instructions.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the real vehicle testing method according to any one of claims 1 to 11.

Images