Multi-domain control interactive automatic driving test method, system and device and storage medium

Abstract

The embodiment of the invention provides a multi-domain control interactive automatic driving test method, system and device and a storage medium, and the method comprises the steps: building a plurality of virtual vehicles and virtual maps in vehicle simulation software; each virtual vehicle in the plurality of virtual vehicles corresponds to one real domain controller, and each virtual vehicle is used for simulating one real vehicle to execute corresponding automatic driving operation according to an automatic driving algorithm configured on the corresponding domain controller; simulating a plurality of virtual vehicles on the virtual map to execute corresponding automatic driving operation according to an automatic driving algorithm configured on the corresponding domain controller; determining an interaction result among the plurality of virtual vehicles according to the automatic driving operation executed by the plurality of virtual vehicles; and according to an interaction result among the plurality of virtual vehicles, determining a test result of the automatic driving algorithm configured on the domain controller corresponding to the plurality of virtual vehicles. The problem that an existing test means cannot meet the complex automatic driving test requirement is solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of autonomous driving simulation technology, and specifically, to a multi-domain control interactive autonomous driving test method, system, device and storage medium. Background Art

[0002] Self-driving cars integrate advanced perception, decision-making and control technologies, involving multiple sensors (such as lidar, cameras, millimeter-wave radar, etc.), complex algorithms and control systems. The integration and collaborative work of these systems need to be verified under various complex and extreme conditions to ensure the safety and reliability of self-driving cars. In the development process of self-driving cars, test verification is an indispensable part, and hardware-in-the-loop simulation technology came into being. It simulates the real vehicle to be tested and the system operating environment, connects the real controller to the simulation system, and realizes the simulation test of the entire system.

[0003] Traditional autonomous driving hardware-in-the-loop simulation only simulates the sensors and vehicle dynamics information of an autonomous driving domain controller, and the surrounding traffic participants are completely set according to the rule logic, including the time of cutting in and out, etc. Interactive, game-like high-level autonomous driving that can face complex working conditions has strong interactivity and game-like nature with traffic flow. The current testing methods cannot meet the testing needs. Testing on public roads is not only time-consuming and labor-intensive, but also prone to collision accidents. Summary of the invention

[0004] The embodiments of the present application provide a multi-domain control interactive autonomous driving test method, system, device and storage medium to at least solve the problem that existing testing methods cannot meet the complex and high-level autonomous driving test requirements.

[0005] According to one aspect of an embodiment of the present application, a multi-domain control interactive autonomous driving test method is provided, comprising: establishing multiple virtual vehicles and virtual maps in vehicle simulation software; the multiple virtual vehicles are randomly distributed on the virtual map, each of the multiple virtual vehicles corresponds to a real domain controller, and the domain controller corresponding to each virtual vehicle is configured with an autonomous driving algorithm to be tested; each virtual vehicle is used to simulate a real vehicle to perform a corresponding autonomous driving operation according to the autonomous driving algorithm configured on the corresponding domain controller; in the vehicle simulation software, the multiple virtual vehicles are simulated on the virtual map to perform the corresponding autonomous driving operation according to the autonomous driving algorithm configured on the corresponding domain controller; according to the autonomous driving operations performed by the multiple virtual vehicles, the interaction results between the multiple virtual vehicles are determined; the interaction results between the multiple virtual vehicles are used to characterize the interaction behaviors between the multiple virtual vehicles; according to the interaction results between the multiple virtual vehicles, the test results of the autonomous driving algorithms configured on the domain controllers corresponding to the multiple virtual vehicles are determined.

[0006] According to another aspect of an embodiment of the present application, a multi-domain control interactive autonomous driving test system is provided, the system comprising: a terminal device, used to implement the steps of the method; a bus simulation board, used to transmit the sensor information of each virtual vehicle detected by the terminal device and the vehicle status information of each virtual vehicle to the domain controller corresponding to each virtual vehicle; the domain controllers corresponding to the multiple virtual vehicles are used to perform driving behavior analysis on the received sensor information and vehicle status information, obtain control instructions corresponding to each virtual vehicle, and feed back the control instructions corresponding to each virtual vehicle to the corresponding virtual vehicle, so that each virtual vehicle performs corresponding autonomous driving operations.

[0007] According to another aspect of an embodiment of the present application, a multi-domain control interactive autonomous driving test device is provided, comprising: a scenario simulation module, used to establish multiple virtual vehicles and virtual maps in vehicle simulation software; the multiple virtual vehicles are randomly distributed on the virtual map, each of the multiple virtual vehicles corresponds to a real domain controller, and the domain controller corresponding to each virtual vehicle is configured with an autonomous driving algorithm to be tested; each virtual vehicle is used to simulate a real vehicle to perform a corresponding autonomous driving operation according to the autonomous driving algorithm configured on the corresponding domain controller; an interactive simulation module, used to simulate, in the vehicle simulation software, the multiple virtual vehicles on the virtual map to perform the corresponding autonomous driving operation according to the autonomous driving algorithm configured on the corresponding domain controller; an analysis module, used to determine the interaction results between the multiple virtual vehicles according to the autonomous driving operations performed by the multiple virtual vehicles; the interaction results between the multiple virtual vehicles are used to characterize the interactive behaviors between the multiple virtual vehicles; a testing module, used to determine the test results of the autonomous driving algorithms configured on the domain controllers corresponding to the multiple virtual vehicles according to the interaction results between the multiple virtual vehicles.

[0008] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned multi-domain control interactive autonomous driving test method when running.

[0009] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the multi-domain control interactive autonomous driving test method through the computer program.

[0010] According to another aspect of an embodiment of the present application, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the steps in any of the above-mentioned multi-domain control interactive autonomous driving test method embodiments.

[0011] Through the embodiment of the present application, each virtual vehicle is set to correspond to a real domain controller, and the domain controller is configured with the autonomous driving algorithm to be tested, which improves the authenticity of the test environment, so that the performance of the autonomous driving algorithm in the virtual vehicle can more accurately reflect its behavior in the real vehicle; by simulating multiple virtual vehicles in the vehicle simulation software to perform corresponding autonomous driving operations on the virtual map according to the autonomous driving algorithm configured on the corresponding domain controller, the complex scenes in the real traffic environment are simulated; after each virtual vehicle performs the corresponding autonomous driving operation according to the autonomous driving algorithm configured on the corresponding domain controller, the interaction results between the multiple virtual vehicles are analyzed according to the autonomous driving operations performed by the multiple virtual vehicles, wherein the interaction results between the multiple virtual vehicles are used to characterize the interactive behaviors between the multiple virtual vehicles. Compared with the traditional rule-based testing scheme, it simulates the competition for road rights among multiple autonomous driving vehicles on the road in the future, and can test the impact of interactive traffic flows close to reality on the autonomous driving algorithms configured on the real domain controllers. According to the interaction results of the simulated multiple domain controllers under complex traffic flows, the test results of the autonomous driving algorithms configured on the domain controllers corresponding to the multiple virtual vehicles can be quickly determined, solving the problem that the existing testing methods cannot meet the complex and high-level autonomous driving testing requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a hardware structure block diagram of an optional multi-domain control interactive autonomous driving test method of an embodiment of the present application;

[0013] Figure 2 is a flowchart of an optional multi-domain control interactive autonomous driving test method according to an embodiment of the present application;

[0014] Figure 3 is a structural diagram of an optional multi-domain control interactive autonomous driving test according to an embodiment of the present application;

[0015] Figure 4 is a schematic diagram of an optional multi-vehicle domain control in-loop test according to an embodiment of the present application;

[0016] Figure 5 is a schematic diagram of another optional multi-vehicle domain control in-loop test according to an embodiment of the present application;

[0017] Figure 6 is a schematic diagram of another optional multi-vehicle domain control in-loop test according to an embodiment of the present application;

[0018] Figure 7 is a structural diagram of an optional multi-domain control interactive autonomous driving test device according to an embodiment of the present application;

[0019] Figure 8It is a structural block diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] According to one aspect of an embodiment of the present application, a multi-domain control interactive autonomous driving test method is provided. Optionally, in this embodiment, the multi-domain control interactive autonomous driving test method can be applied to Figure 1 The hardware environment shown in FIG. 1 is composed of a terminal device 102, a bus simulation board 104, and a plurality of domain controllers 106 of real vehicles. Figure 1 As shown, the terminal device 102 is used to simulate the interactive operation of multiple virtual vehicles on the virtual map; the bus simulation board 104 is used to transmit the sensor information of each virtual vehicle detected by the terminal device 102 and the vehicle status information of each virtual vehicle to the domain controller 106 corresponding to each virtual vehicle. The domain controller 106 corresponding to each virtual vehicle is used to perform driving behavior analysis on the received sensor information and vehicle status information, obtain the control instructions corresponding to each virtual vehicle, and feed back the control instructions corresponding to each virtual vehicle to the corresponding virtual vehicle, so that each virtual vehicle performs the corresponding automatic driving operation.

[0023] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI, Bluetooth. The terminal device 102 may not be limited to a PC, a mobile phone, a tablet computer, or other devices.

[0024] The multi-domain control interactive autonomous driving testing method of the embodiment of the present application can be executed by the terminal device 102. Figure 2 is a flow chart of an optional multi-domain control interactive autonomous driving test method according to an embodiment of the present application, such as Figure 2 As shown, the process of the method may include the following steps:

[0025] Step S202, establishing multiple virtual vehicles and virtual maps in the vehicle simulation software; the multiple virtual vehicles are randomly distributed on the virtual map, each of the multiple virtual vehicles corresponds to a real domain controller, and the domain controller corresponding to each virtual vehicle is configured with an autonomous driving algorithm to be tested; each virtual vehicle is used to simulate a real vehicle to perform corresponding autonomous driving operations according to the autonomous driving algorithm configured on the corresponding domain controller.

[0026] Among them, vehicle simulation software is a computer program specifically used to simulate the operating environment and behavior of a real vehicle.

[0027] Virtual vehicles are digital models created in vehicle simulation software that represent real vehicles. These models have similar physical characteristics and behavior patterns to real vehicles, but run entirely in a computer environment.

[0028] A virtual map is a digital model used in vehicle simulation software to represent the real-world geographical environment. It contains detailed information such as road networks, traffic signs, obstacles, buildings, etc., and can simulate different weather and lighting conditions.

[0029] The domain controller is a key hardware component in self-driving cars, responsible for managing and coordinating the operation of various systems inside the real vehicle. The domain controller usually integrates high-performance computing units, sensor interfaces and communication modules, and can process data from different sensors and execute complex algorithms and control strategies based on these data.

[0030] Autonomous driving algorithms are software programs used in autonomous vehicles to achieve autonomous navigation and decision-making. Autonomous driving algorithms are usually based on technologies such as deep learning, machine learning, computer vision, and sensor fusion, and can analyze the environmental information around the vehicle in real time and make correct driving decisions based on it.

[0031] Autonomous driving operations refer to the various driving actions and decisions made by an autonomous vehicle based on the autonomous driving algorithm during driving. Autonomous driving operations include but are not limited to acceleration, deceleration, steering, lane changing, parking, etc.

[0032] Optionally, the terminal device establishes multiple virtual vehicles and virtual maps in the vehicle simulation software, randomly distributes the multiple virtual vehicles on the virtual map, and sets each of the multiple virtual vehicles to correspond to a real domain controller, so as to simulate a real vehicle to perform corresponding autonomous driving operations according to the autonomous driving algorithm configured on the corresponding domain controller.

[0033] Step S204, in the vehicle simulation software, multiple virtual vehicles are simulated on the virtual map to perform corresponding autonomous driving operations according to the autonomous driving algorithms configured on the corresponding domain controllers.

[0034] Optionally, the terminal device sets the initial conditions for each virtual vehicle (such as start time, starting point, end point, speed and direction, etc.), and starts the virtual vehicle that meets the initial conditions in the vehicle simulation software. The started virtual vehicle will begin to perform autonomous driving operations (such as keeping lanes, accelerating, decelerating, avoiding obstacles, changing lanes, etc.) according to the corresponding autonomous driving algorithms on the virtual map. The vehicle simulation software records the motion status, sensor data and control instructions of the virtual vehicle in real time, and updates the position and status of the virtual vehicle on the virtual map.

[0035] Step S206, determining the interaction results between the multiple virtual vehicles according to the automatic driving operations performed by the multiple virtual vehicles; the interaction results between the multiple virtual vehicles are used to characterize the interaction behaviors between the multiple virtual vehicles.

[0036] The interaction results refer to the specific consequences or state changes caused by the mutual influence between multiple virtual vehicles when they perform autonomous driving operations in the simulation environment. For example, the interaction results include the relative position change, speed adjustment, obstacle avoidance behavior, lane change decision, etc. of the vehicles.

[0037] Interactive behavior refers to the process of information transmission, decision making and action execution among multiple virtual vehicles in a simulation environment based on their respective autonomous driving algorithms and current traffic conditions.

[0038] Optionally, after multiple virtual vehicles perform autonomous driving operations in the vehicle simulation software, the terminal device records the interaction results such as relative position changes, speed adjustments, obstacle avoidance behaviors, etc. between the multiple virtual vehicles, and performs quantitative analysis on the interaction results, such as calculating the relative distance between vehicles, speed difference, obstacle avoidance success rate and other indicators to obtain quantified interaction results.

[0039] Step S208, determining the test results of the autonomous driving algorithms configured on the domain controllers corresponding to the multiple virtual vehicles based on the interaction results between the multiple virtual vehicles.

[0040] Optionally, the terminal device compares the quantified interaction results with preset test standards to evaluate the performance (such as safety, stability, efficiency, etc.) of the autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle in a complex traffic environment, and determines the test results of the autonomous driving algorithms configured on the domain controllers corresponding to multiple virtual vehicles based on the performance of each virtual vehicle in the complex traffic environment.

[0041] Through the above steps S202 to S206, each virtual vehicle is set to correspond to a real domain controller, and the domain controller is configured with the autonomous driving algorithm to be tested, so as to improve the authenticity of the test environment, so that the performance of the autonomous driving algorithm in the virtual vehicle can more accurately reflect its behavior in the real vehicle; by simulating multiple virtual vehicles in the vehicle simulation software to perform corresponding autonomous driving operations on the virtual map according to the autonomous driving algorithm configured on the corresponding domain controller, the complex scenes in the real traffic environment are simulated; after each virtual vehicle performs the corresponding autonomous driving operation according to the autonomous driving algorithm configured on the corresponding domain controller, the interaction results between the multiple virtual vehicles are analyzed according to the autonomous driving operations performed by the multiple virtual vehicles, wherein the interaction results between the multiple virtual vehicles are used to characterize the interactive behaviors between the multiple virtual vehicles. Compared with the traditional rule-based test scheme, the competition for road rights among multiple autonomous driving vehicles on the road in the future is simulated, and the impact of interactive traffic flows close to reality on the autonomous driving algorithms configured on the real domain controllers can be tested. According to the interaction results of the simulated multiple domain controllers under complex traffic flows, the test results of the autonomous driving algorithms configured on the domain controllers corresponding to the multiple virtual vehicles can be quickly determined, solving the problem that the existing testing methods cannot meet the complex and high-level autonomous driving test requirements.

[0042] In an exemplary embodiment, in the vehicle simulation software, multiple virtual vehicles are simulated on a virtual map to perform corresponding autonomous driving operations according to the autonomous driving algorithms configured on the corresponding domain controllers, including:

[0043] 1. Detect the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle through the vehicle simulation software, and transmit the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle to the corresponding domain controller through the vehicle simulation software.

[0044] Sensor information refers to the information generated by the virtual vehicle collected in real time by the sensor network simulated in the vehicle simulation software. Sensor information usually covers the location, speed, distance, type (such as pedestrians, vehicles, bicycles, etc.) of obstacles around the vehicle, road signs, traffic light status, and weather and road conditions.

[0045] The vehicle status information refers to the dynamic attribute data of the virtual vehicle itself, wherein the dynamic attribute data includes the current speed, acceleration, steering angle, wheel speed, brake status, etc. of the virtual vehicle, reflecting the current motion state of the virtual vehicle.

[0046] Optionally, Figure 3 FIG. 1 is a structural diagram of a multi-domain control interactive autonomous driving test in one embodiment. Figure 3 As shown in the figure, vehicle simulation software includes scenario simulation software and vehicle dynamics software. Scenario simulation software provides a highly simulated virtual scene that can restore the real driving road conditions, including road layout, traffic signs, weather conditions, and the behavior of other traffic participants (such as vehicles, pedestrians, etc.). Vehicle dynamics software is used to simulate and analyze the movement and control of vehicles. Figure 3 As shown, virtual vehicles 1 to 5 are set in the scene simulation software, and regular or random traffic vehicles can also be added, such as Figure 3 "Other vehicles" in.

[0047] In some embodiments, a corresponding virtual sensor is set on each virtual vehicle according to the real sensor on the real vehicle corresponding to each virtual vehicle. The virtual sensor includes but is not limited to a camera, a millimeter wave radar and a laser radar, and the virtual sensor is installed in the scene simulation software according to the installation position angle and other information corresponding to the real sensor.

[0048] In some embodiments, detecting the sensor information of each virtual vehicle and the vehicle state information of each virtual vehicle by vehicle simulation software includes:

[0049] Through the scene simulation software, the sensor information collected by the virtual sensors on multiple virtual vehicles is obtained, and the sensor information is sent to the domain controller corresponding to each virtual vehicle through video darkroom, video injection, radar simulator or bus simulation; the dynamic model of each virtual vehicle is established through the vehicle dynamics software; the spatial state parameters of each virtual vehicle are transmitted to the dynamic model of each virtual vehicle through the scene simulation software; the spatial state parameters of each virtual vehicle are used to characterize the spatial distribution information of each virtual vehicle in the virtual map, such as the position information, height information and other contents of the virtual vehicle; through the dynamic model of each virtual vehicle, the vehicle state information corresponding to each virtual vehicle under the corresponding spatial state parameters is simulated.

[0050] For example, Figure 3 As shown, in the scene simulation software, the sensor information of virtual vehicles 1 to 5 is collected through virtual sensors on multiple virtual vehicles, and the sensor information is sent to the domain controllers corresponding to virtual vehicles 1 to 5 respectively through video dark box, video injection, radar simulator or bus simulation. In the vehicle dynamics software, the corresponding virtual vehicles 1 to 5 are established, and the parameters are adjusted according to the real vehicles where the domain controllers are located. The scene simulation software transmits the spatial state parameters of virtual vehicles 1 to 5 to the dynamics model corresponding to each virtual vehicle.

[0051] 2. The autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle performs driving behavior analysis on the received sensor information and vehicle status information, obtains control instructions corresponding to each virtual vehicle, and feeds back the control instructions corresponding to each virtual vehicle to the corresponding virtual vehicle, so that each virtual vehicle performs corresponding autonomous driving operations on the virtual map.

[0052] Optionally, after receiving the corresponding sensor information and vehicle status information, the domain controller corresponding to each virtual vehicle uses the autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle to analyze and identify road features, obstacle locations, etc., and generates driving decisions based on the identified information. According to the driving decisions, control instructions corresponding to each virtual vehicle are generated, such as acceleration, deceleration, steering, braking, etc., and the generated control instructions are fed back to the corresponding virtual vehicle through a communication protocol (such as CAN bus, Ethernet, etc.). After receiving the control instructions, the control system of the virtual vehicle performs corresponding autonomous driving operations, such as adjusting engine output, changing braking force, adjusting steering angle, etc.

[0053] Through this embodiment, the sensor information and vehicle status information of the virtual vehicle in various scenarios are accurately simulated using vehicle simulation software, so that the accuracy and reliability of the test results can be ensured; through real-time communication between the vehicle simulation software and the domain controller, the processing results of the autonomous driving algorithm on the sensor information and vehicle status information, as well as the control instructions generated by the domain controller can be obtained in real time. The above-mentioned multi-domain controller autonomous driving hardware-in-the-loop test uses the real control instructions of the domain controller in different driving environments to evaluate the reliability of the corresponding autonomous driving algorithm and improve the test accuracy of the autonomous driving algorithm.

[0054] In an exemplary embodiment, the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle are transmitted to the corresponding domain controller through the vehicle simulation software, including:

[0055] Through the vehicle simulation software, the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle are transmitted to the bus simulation board, so that the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle are fed back to the corresponding domain controller through the bus simulation board; the bus simulation board is used to simulate the bus communication behavior of the domain controllers corresponding to the multiple virtual vehicles; the bus simulation board is rigidly connected to the domain controllers corresponding to the multiple virtual vehicles.

[0056] Among them, the bus simulation board is a hardware device used to simulate and test the bus communication behavior of domain controllers corresponding to multiple virtual vehicles to ensure that the test environment is as close to the real situation as possible.

[0057] Alternatively, if Figure 3 As shown, the scenario simulation software sends the sensor information of virtual vehicles 1 to 5; the dynamic models corresponding to virtual vehicles 1 to 5 in the vehicle dynamics software send the vehicle status information of each virtual vehicle to the bus simulation board; the bus simulation board simulates the bus communication behavior of virtual vehicles 1 to 5, and sends the sensor information of virtual vehicles 1 to 5 to the corresponding domain controllers, and sends the vehicle status information of virtual vehicles 1 to 5 to the corresponding domain controllers. The domain controllers corresponding to virtual vehicles 1 to 5 perform driving behavior analysis on the received sensor information and vehicle status information, issue corresponding control commands to the bus simulation board, and transmit them back to the dynamic models corresponding to virtual vehicles 1 to 5 in the vehicle dynamics software through the bus simulation board to perform corresponding automatic driving operations, such as acceleration, deceleration, lane change, etc., and complete the closed-loop simulation by feeding back the vehicle status information to the scenario simulation software.

[0058] Through this embodiment, the sensor information and vehicle status information of the virtual vehicle generated by the vehicle simulation software are transmitted to the corresponding domain controller in real time through the bus simulation board, ensuring that this information is transmitted from the simulation software to the domain controller in real time, thereby simulating a real real-time communication environment and ensuring that the test environment is as close to the actual situation as possible.

[0059] In an exemplary embodiment, each virtual vehicle is provided with a corresponding start time, a starting point and an end point. Among multiple virtual vehicles, the start times and starting points corresponding to different virtual vehicles are at least partially different, and the end points corresponding to the multiple virtual vehicles are the same.

[0060] The start time refers to the time point when the vehicle starts to travel. The starting point refers to the location where the vehicle starts to travel. The end point refers to the location where the vehicle ends or the target location. In the case of multiple virtual vehicles, the start time and the starting point of the multiple virtual vehicles are not exactly the same, that is, at least some of the virtual vehicles have different start times or starting points from other vehicles. In other words, not all vehicles start from the same location at the same time.

[0061] In some embodiments, determining the interaction results between the multiple virtual vehicles according to the autonomous driving operations performed by the multiple virtual vehicles includes:

[0062] A designated virtual vehicle among the multiple virtual vehicles is used as a test vehicle, and the remaining virtual vehicles except the designated virtual vehicle are used as traffic vehicles. The interaction results among the multiple virtual vehicles are determined according to the automatic driving operations performed by the test vehicle after the traffic vehicle performs the corresponding automatic driving operations.

[0063] Optionally, the terminal device sets the start time and starting point corresponding to different virtual vehicles to be at least partially different, and the end points corresponding to multiple virtual vehicles are the same, and designates a virtual vehicle from multiple virtual vehicles as the vehicle to be tested, and uses the remaining virtual vehicles except the designated virtual vehicle as traffic vehicles, so that the traffic vehicles perform the corresponding automatic driving operation according to their respective automatic driving strategies, and record the position, speed, acceleration and other state information of the traffic vehicles during the automatic driving operation. After the traffic vehicle completes the automatic driving operation, the terminal device allows the vehicle to be tested to perform the corresponding automatic driving operation according to the current environment (including the state of the traffic vehicle), and records the position, speed, acceleration and other state information of the vehicle to be tested during the automatic driving operation. The terminal device analyzes the interaction between them based on the recorded state information of the traffic vehicle and the vehicle to be tested, specifically including evaluating whether the vehicle to be tested can safely avoid the traffic vehicle, whether it follows the traffic rules, whether it effectively handles the emergency, etc.; based on the above analysis, the terminal device determines the interaction results between multiple virtual vehicles, such as a qualitative evaluation (such as "successful avoidance", "minor collision", etc.), or a quantitative score (such as a score based on indicators such as safe distance and driving efficiency).

[0064] For example, Figure 4 FIG. 1 is a schematic diagram of a multiple-vehicle domain control in-loop test in one embodiment. Figure 4As shown, virtual vehicle 5 is used as the vehicle to be tested, and the remaining virtual vehicles are used as traffic vehicles. The vehicle to be tested and the traffic vehicle have different start times and starting points, which result in different states of the vehicle to be tested and the traffic vehicle at corresponding times, but have the same end point. Therefore, the vehicle to be tested and the traffic vehicle will interactively change lanes, overtake, and other behaviors under the control of the corresponding automatic driving algorithm. At this time, the driving performance of the vehicle to be tested can be tested.

[0065] Through this embodiment, each virtual vehicle is set with a corresponding start time, a starting point and an end point, and the start time and the starting point corresponding to different virtual vehicles are at least partially different, so as to achieve diversity in the real traffic environment, and the end points corresponding to multiple virtual vehicles are set to be the same, so as to generate interactive lane changing, overtaking and other behaviors, and by using a designated virtual vehicle among the multiple virtual vehicles as a test vehicle, and using the remaining virtual vehicles except the designated virtual vehicle as traffic vehicles, according to the interactive behavior between the test vehicle and the traffic vehicles, it can be verified whether the automatic driving algorithm of the test vehicle can effectively handle the interaction with other vehicles.

[0066] In an exemplary embodiment, each virtual vehicle is provided with a corresponding start time, a starting point and an end point, the start times corresponding to multiple virtual vehicles are the same, and among the multiple virtual vehicles, the starting points and end points corresponding to different virtual vehicles are at least partially different.

[0067] The starting points and ending points corresponding to different virtual vehicles are at least partially different, including the following situations: different virtual vehicles have different starting points and the same ending points; different virtual vehicles have the same starting points and different ending points; different virtual vehicles have different starting points and ending points. By setting the corresponding start time, starting point and ending point for each virtual vehicle, the diversity and complexity of vehicle driving in the real world can be simulated.

[0068] In some embodiments, determining the interaction results between the multiple virtual vehicles according to the autonomous driving operations performed by the multiple virtual vehicles includes:

[0069] Multiple virtual vehicles are started simultaneously, and the interaction results between the multiple virtual vehicles are determined based on the autonomous driving operations performed by each virtual vehicle.

[0070] Among them, the autonomous driving algorithms configured on the domain controllers corresponding to the multiple virtual vehicles are the same algorithm. By setting the startup time corresponding to the multiple virtual vehicles to be the same, and the starting points and ending points corresponding to different virtual vehicles in the multiple virtual vehicles to be at least partially different, a variety of test scenarios are generated. The test performance of the same autonomous driving algorithm in different traffic scenarios can be determined, thereby improving test efficiency and saving test time.

[0071] Optionally, the terminal device sets the same start time for multiple virtual vehicles, and the starting points and ending points corresponding to different virtual vehicles in the multiple virtual vehicles are at least partially different, and multiple virtual vehicles are used as test vehicles, and the multiple test vehicles are set at different starting points in the virtual map, and the multiple test vehicles are started at the same time, so that the multiple test vehicles perform the corresponding automatic driving operation according to their respective automatic driving strategies, and record the position, speed, acceleration and other state information of the multiple test vehicles during the automatic driving operation. The terminal device analyzes the interaction between them according to the recorded state information of the multiple test vehicles, specifically including evaluating whether the multiple test vehicles can safely avoid traffic vehicles, whether they follow traffic rules, whether they effectively handle emergencies, etc.; based on the above analysis, the terminal device determines the interaction results between the multiple virtual vehicles, such as a qualitative evaluation (such as "successful avoidance", "minor collision", etc.), or a quantitative score (such as a score based on indicators such as safe distance and driving efficiency).

[0072] For example, Figure 5 FIG. 1 is a schematic diagram of a multiple-vehicle domain control in-loop test in another embodiment. Figure 5 As shown, the autonomous driving algorithms configured on the domain controllers corresponding to virtual vehicles 1 to 5 are the same algorithm. Virtual vehicles 1 to 5 are used as multiple vehicles to be tested. Multiple vehicles to be tested are placed at different positions on the comprehensive virtual map, and starting points and end points are set. Regular live and random traffic flows are set around the multiple vehicles to be tested. When the test starts, multiple vehicles to be tested will travel at the same time for testing, which greatly improves the test efficiency and saves test time.

[0073] Through this embodiment, the start time corresponding to multiple virtual vehicles is set to be the same, and the starting points and ending points corresponding to different virtual vehicles in the multiple virtual vehicles are at least partially different, thereby generating a variety of test scenarios. By starting multiple virtual vehicles at the same time, the test performance of the same autonomous driving algorithm in different traffic scenarios can be determined, thereby improving test efficiency and saving test time.

[0074] In an exemplary embodiment, the current driving mode of each virtual vehicle is at least partially the same; the autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle is the same algorithm or a different algorithm;

[0075] In some embodiments, determining the interaction results between the multiple virtual vehicles according to the autonomous driving operations performed by the multiple virtual vehicles includes:

[0076] When the autonomous driving algorithms configured on the domain controllers corresponding to the virtual vehicles are the same algorithm and the current driving mode of each virtual vehicle is at least partially the same, or when the autonomous driving algorithms configured on the domain controllers corresponding to the virtual vehicles are different algorithms and the current driving mode of each virtual vehicle is the same, the interaction results between the multiple virtual vehicles are determined based on the automatic switching operation of the driving simulation of each virtual vehicle in the current driving mode.

[0077] Among them, if the autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle is the same algorithm, and the current driving mode of each virtual vehicle is at least partially the same, then the interaction result between multiple virtual vehicles refers to the test performance of the same autonomous driving algorithm (or the same domain controller) in different driving modes. If the autonomous driving algorithms configured on the domain controller corresponding to each virtual vehicle are different algorithms, and the current driving mode of each virtual vehicle is the same, then the interaction result between multiple virtual vehicles refers to the test performance of different autonomous driving algorithms (or different domain controllers) in the same driving mode.

[0078] Optionally, the terminal device sets the autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle to the same algorithm, and the current driving mode of each virtual vehicle is at least partially the same, starts each virtual vehicle to make each virtual vehicle travel according to the current driving mode, and records the driving mode changes of each virtual vehicle after at least one virtual vehicle performs the automatic switching operation of the driving simulation, and determines the interaction results between the multiple virtual vehicles based on the driving mode changes of each virtual vehicle.

[0079] For example, Figure 6 FIG. 1 is a schematic diagram of a multiple-vehicle domain control in-loop test in another embodiment of an embodiment, such as Figure 6 As shown, if the autonomous driving algorithms configured on the domain controllers corresponding to virtual vehicles 1 to 5 are the same algorithm, virtual vehicles 1 to 5 are used as multiple vehicles to be tested, where the driving modes include normal mode, conservative mode and aggressive mode. The current driving modes of virtual vehicles 1 to 5 are as follows: Figure 6 As shown, when virtual vehicle 1 (aggressive mode) intends to change lanes, whether virtual vehicle 2 (conservative mode) in front chooses to give way, and whether virtual vehicle 5 (conservative mode) chooses to give way to the vehicles on the left and right, the autonomous driving algorithm can be adjusted and iterated according to the test performance of the same autonomous driving algorithm (or the same domain controller) in different driving modes.

[0080] Through this embodiment, by setting the current driving mode of each virtual vehicle to be at least partially the same, it is easier to control the test variables and simulate the interaction of different driving modes with traffic flows on real roads, so as to quickly identify the performance differences of different autonomous driving algorithms or the same algorithm in different scenarios, and allow multiple test cases to be run simultaneously, significantly improving the test efficiency.

[0081] According to another aspect of the embodiment of the present application, Figure 1 As shown, a multi-domain control interactive autonomous driving test system is also provided, including:

[0082] A terminal device is used to implement any step of the above-mentioned multi-domain control interactive autonomous driving test method.

[0083] The bus simulation board is used to transmit the sensing information of each virtual vehicle detected by the terminal device and the vehicle status information of each virtual vehicle to the domain controller corresponding to each virtual vehicle.

[0084] The domain controller corresponding to each virtual vehicle is used to perform driving behavior analysis on the received sensor information and vehicle status information, obtain control instructions corresponding to each virtual vehicle, and feed back the control instructions corresponding to each virtual vehicle to the corresponding virtual vehicle, so that each virtual vehicle performs corresponding autonomous driving operations.

[0085] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware server, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0087] According to another aspect of the embodiments of the present application, a multi-domain control interactive autonomous driving test device is also provided, which is used to implement the multi-domain control interactive autonomous driving test method provided in the above embodiments, and will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0088] Figure 7 is a structural block diagram of an optional multi-domain control interactive autonomous driving test device according to an embodiment of the present application, such as Figure 7 As shown, the device may include:

[0089] The scenario simulation module 701 is used to establish multiple virtual vehicles and virtual maps in the vehicle simulation software; the multiple virtual vehicles are randomly distributed on the virtual map, each of the multiple virtual vehicles corresponds to a real domain controller, and the domain controller corresponding to each virtual vehicle is configured with an autonomous driving algorithm to be tested; each virtual vehicle is used to simulate a real vehicle to perform corresponding autonomous driving operations according to the autonomous driving algorithm configured on the corresponding domain controller;

[0090] The interactive simulation module 702 is used to simulate multiple virtual vehicles on a virtual map in the vehicle simulation software to perform corresponding autonomous driving operations according to the autonomous driving algorithms configured on the corresponding domain controllers;

[0091] The analysis module 703 is used to determine the interaction results between the multiple virtual vehicles according to the automatic driving operations performed by the multiple virtual vehicles; the interaction results between the multiple virtual vehicles are used to characterize the interaction behaviors between the multiple virtual vehicles;

[0092] The testing module 704 is used to determine the test results of the autonomous driving algorithm configured on the domain controllers corresponding to the multiple virtual vehicles based on the interaction results between the multiple virtual vehicles.

[0093] In an exemplary embodiment, the interactive simulation module 702 is also used to detect the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle through the vehicle simulation software, and transmit the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle to the corresponding domain controller through the vehicle simulation software; perform driving behavior analysis on the received sensor information and vehicle status information through the autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle, obtain control instructions corresponding to each virtual vehicle, and feed back the control instructions corresponding to each virtual vehicle to the corresponding virtual vehicle, so that each virtual vehicle performs corresponding autonomous driving operations on the virtual map.

[0094] In an exemplary embodiment, the interactive simulation module 702 is also used to transmit the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle to the bus simulation board through the vehicle simulation software, so as to feed back the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle to the corresponding domain controller through the bus simulation board; the bus simulation board is used to simulate the bus communication behavior of the domain controllers corresponding to the multiple virtual vehicles; the bus simulation board is rigidly connected to the domain controllers corresponding to the multiple virtual vehicles.

[0095] In an exemplary embodiment, each virtual vehicle is provided with a corresponding start time, a starting point and an end point. Among the multiple virtual vehicles, the start times and starting points corresponding to different virtual vehicles are at least partially different, and the end points corresponding to the multiple virtual vehicles are the same; the analysis module 703 is also used to use a designated virtual vehicle among the multiple virtual vehicles as a test vehicle, and use the remaining virtual vehicles except the designated virtual vehicle as traffic vehicles, and determine the interaction results between the multiple virtual vehicles according to the automatic driving operations performed by the test vehicle after the traffic vehicle performs the corresponding automatic driving operations.

[0096] In an exemplary embodiment, each virtual vehicle is provided with a corresponding start time, a starting point and an end point, the start times corresponding to a plurality of virtual vehicles are the same, and among the plurality of virtual vehicles, the starting points and the end points corresponding to different virtual vehicles are at least partially different; the analysis module 703 is also used to start a plurality of virtual vehicles at the same time, and determine the interaction results between the plurality of virtual vehicles according to the automatic driving operation performed by each virtual vehicle.

[0097] In an exemplary embodiment, the current driving mode of each virtual vehicle is at least partially the same; the autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle is the same algorithm or different algorithms; the analysis module 703 is also used to determine the interaction results between multiple virtual vehicles according to the automatic switching operation of the driving simulation under the current driving mode of each virtual vehicle when the autonomous driving algorithm configured on the domain controller corresponding to the virtual vehicle is the same algorithm and the current driving mode of each virtual vehicle is at least partially the same, or when the autonomous driving algorithm configured on the domain controller corresponding to the virtual vehicle is different algorithm and the current driving mode of each virtual vehicle is the same.

[0098] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0099] According to another aspect of the embodiments of the present application, a storage medium is further provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the multi-domain control interactive autonomous driving test methods in the embodiments of the present application.

[0100] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0101] Optionally, in this embodiment, the storage medium is configured to store program code for executing any of the above-mentioned multi-domain control interactive autonomous driving testing methods.

[0102] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0103] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disk.

[0104] According to another aspect of an embodiment of the present application, an electronic device for implementing the above-mentioned multi-domain control interactive autonomous driving testing method is also provided. The electronic device may be a smart device, a server, a terminal, or a combination thereof.

[0105] Figure 8 is a structural block diagram of an optional electronic device according to an embodiment of the present application, such as Figure 8 As shown, it includes a processor 802, a communication interface 804, a memory 806 and a communication bus 808, wherein the processor 802, the communication interface 804 and the memory 806 communicate with each other through the communication bus 808, wherein,

[0106] Memory 806, used for storing computer programs;

[0107] The processor 802 is used to implement the program code of any of the above-mentioned multi-domain control interactive autonomous driving testing methods when executing the computer program stored in the memory 806.

[0108] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8The communication interface is used for communication between the above electronic device and other devices.

[0109] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0110] As an example, the memory 806 may include, but is not limited to, each module in the multi-domain control interactive autonomous driving test device. In addition, it may also include, but is not limited to, other module units in the multi-domain control interactive autonomous driving test device, which will not be described in detail in this example.

[0111] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0112] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0113] It can be understood by those skilled in the art that Figure 8 The structure shown is for illustration only. The device for implementing the above-mentioned multi-domain control interactive autonomous driving test method may be a terminal device, which may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 8 The structure of the electronic device is not limited. Figure 8 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 8 Different configurations shown.

[0114] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0115] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0116] The embodiments of the present application also provide a computer program, which includes computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in any one of the above method embodiments.

[0117] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0118] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0119] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0120] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0123] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist physically separately, or at least two units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A multi-domain control interactive autonomous driving test method, characterized in that: include: Establish multiple virtual vehicles and virtual maps in the vehicle simulation software; the multiple virtual vehicles are randomly distributed on the virtual map, each of the multiple virtual vehicles corresponds to a real domain controller, and the domain controller corresponding to each virtual vehicle is configured with an autonomous driving algorithm to be tested; each virtual vehicle is used to simulate a real vehicle to perform corresponding autonomous driving operations according to the autonomous driving algorithm configured on the corresponding domain controller; In the vehicle simulation software, the plurality of virtual vehicles are simulated on the virtual map to perform corresponding autonomous driving operations according to the autonomous driving algorithms configured on the corresponding domain controllers; Determining, according to the autonomous driving operations performed by the multiple virtual vehicles, interaction results between the multiple virtual vehicles; the interaction results between the multiple virtual vehicles are used to characterize the interaction behaviors between the multiple virtual vehicles; According to the interaction results between the multiple virtual vehicles, the test results of the automatic driving algorithm configured on the domain controllers corresponding to the multiple virtual vehicles are determined.

2. The method according to claim 1, characterized in that In the vehicle simulation software, simulating the plurality of virtual vehicles on the virtual map to perform corresponding autonomous driving operations according to the autonomous driving algorithms configured on the corresponding domain controllers includes: Detecting the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle through the vehicle simulation software, and transmitting the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle to the corresponding domain controller through the vehicle simulation software; The autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle performs driving behavior analysis on the received sensor information and vehicle status information to obtain control instructions corresponding to each virtual vehicle, and feeds back the control instructions corresponding to each virtual vehicle to the corresponding virtual vehicle, so that each virtual vehicle performs corresponding autonomous driving operations on the virtual map.

3. The method according to claim 2, characterized in that The transmitting the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle to the corresponding domain controller through the vehicle simulation software includes: Through the vehicle simulation software, the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle are transmitted to the bus simulation board, so that the sensor information of each virtual vehicle and the vehicle status information of each virtual vehicle are fed back to the corresponding domain controller through the bus simulation board; the bus simulation board is used to simulate the bus communication behavior of the domain controllers corresponding to the multiple virtual vehicles; the bus simulation board is rigidly connected to the domain controllers corresponding to the multiple virtual vehicles.

4. The method according to claim 1, characterized in that: Each of the virtual vehicles is provided with a corresponding start time, a starting point and an end point, among the multiple virtual vehicles, the start times and starting points corresponding to different virtual vehicles are at least partially different, and the end points corresponding to the multiple virtual vehicles are all the same; The step of determining the interaction results between the multiple virtual vehicles according to the autonomous driving operations performed by the multiple virtual vehicles includes: A designated virtual vehicle among the multiple virtual vehicles is used as a test vehicle, and the remaining virtual vehicles except the designated virtual vehicle are used as traffic vehicles. The interaction results between the multiple virtual vehicles are determined according to the autonomous driving operations performed by the test vehicle after the traffic vehicle performs the corresponding autonomous driving operations.

5. The method according to claim 1, characterized in that Each of the virtual vehicles is provided with a corresponding start time, a starting point and an end point, the start times corresponding to the multiple virtual vehicles are the same, and the start points and end points corresponding to different virtual vehicles among the multiple virtual vehicles are at least partially different; The step of determining the interaction results between the multiple virtual vehicles according to the autonomous driving operations performed by the multiple virtual vehicles includes: The multiple virtual vehicles are started simultaneously, and the interaction results between the multiple virtual vehicles are determined according to the automatic driving operation performed by each virtual vehicle.

6. The method according to claim 1, characterized in that The current driving mode of each virtual vehicle is at least partially the same; the autonomous driving algorithm configured on the domain controller corresponding to each virtual vehicle is the same algorithm or a different algorithm; The step of determining the interaction results between the multiple virtual vehicles according to the autonomous driving operations performed by the multiple virtual vehicles includes: In the case where the autonomous driving algorithms configured on the domain controllers corresponding to the virtual vehicles are the same algorithm and the current driving mode of each virtual vehicle is at least partially the same, or in the case where the autonomous driving algorithms configured on the domain controllers corresponding to the virtual vehicles are different algorithms and the current driving mode of each virtual vehicle is the same, the interaction results between the multiple virtual vehicles are determined according to the automatic switching operation of the driving simulation of each virtual vehicle under the current driving mode.

7. A multi-domain control interactive autonomous driving test system, characterized in that: The system comprises: Terminal device, used to implement the steps of any one of the methods of claims 1 to 6; A bus simulation board, used for transmitting the sensing information of each virtual vehicle detected by the terminal device and the vehicle status information of each virtual vehicle to a domain controller corresponding to each virtual vehicle; The domain controller corresponding to each virtual vehicle is used to perform driving behavior analysis on the received sensor information and vehicle status information, obtain control instructions corresponding to each virtual vehicle, and feed back the control instructions corresponding to each virtual vehicle to the corresponding virtual vehicle, so that each virtual vehicle performs corresponding automatic driving operations.

8. A multi-domain control interactive autonomous driving test device, characterized in that: include: A scenario simulation module is used to create multiple virtual vehicles and virtual maps in the vehicle simulation software; The multiple virtual vehicles are randomly distributed on the virtual map, each of the multiple virtual vehicles corresponds to a real domain controller, and the domain controller corresponding to each virtual vehicle is configured with an autonomous driving algorithm to be tested; each virtual vehicle is used to simulate a real vehicle to perform a corresponding autonomous driving operation according to the autonomous driving algorithm configured on the corresponding domain controller; An interactive simulation module, used for simulating, in the vehicle simulation software, on the virtual map, the plurality of virtual vehicles to perform corresponding autonomous driving operations according to the autonomous driving algorithms configured on the corresponding domain controllers; An analysis module, configured to determine, according to the autonomous driving operations performed by the multiple virtual vehicles, interaction results between the multiple virtual vehicles; the interaction results between the multiple virtual vehicles are used to characterize interaction behaviors between the multiple virtual vehicles; The test module is used to determine the test results of the automatic driving algorithm configured on the domain controller corresponding to the multiple virtual vehicles according to the interaction results between the multiple virtual vehicles.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of any one of the methods of claims 1 to 6 when executed by a processor.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images