Vehicle simulation test method and device, electronic equipment and medium

Abstract

The embodiment of the invention provides a vehicle simulation test method and device, electronic equipment and a medium, which are applied to an automatic driving simulation platform, and the method comprises the following steps: creating a target virtual driving environment and a target virtual vehicle by calling a simulation environment system; the target virtual vehicle is controlled to automatically drive in the target virtual driving environment, virtual vehicle control data in the automatic driving process are converted into CAN bus data, and the CAN bus data are sent to a vehicle domain controller; and receiving automatic driving decision data generated by the vehicle domain controller according to the CAN bus data, the radar sensing data and the environment video data, and controlling the target virtual vehicle to perform automatic driving in the target virtual driving environment according to the automatic driving decision data, so that deep fusion of the virtual driving environment and an automatic driving technology is realized, and the driving efficiency is improved. Dangerous field tests do not need to be carried out on a real road, so that the test cost is reduced, and the test safety and controllability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving simulation testing, and particularly to a method, device, electronic device and medium for vehicle simulation testing. Background Art

[0002] With the rapid development of autonomous driving technology, the demand for testing and verifying autonomous driving systems is increasing day by day. The existing on-site testing methods are not only costly but also difficult to cover all possible driving scenarios. Summary of the Invention

[0003] In view of the above problems, a method, device, electronic device and medium for vehicle simulation testing are provided to overcome or at least partially solve the above problems, including:

[0004] A method for vehicle simulation testing, applied to an autonomous driving simulation platform. The autonomous driving simulation platform includes a simulation environment system, a simulation vehicle control system, a simulation radar system, and a simulation camera system. The autonomous driving simulation platform is deployed on a target device, and the target device is communicatively connected to the vehicle domain controller of a real vehicle. The method includes:

[0005] According to a test task input by a user, call the simulation environment system to create a target virtual driving environment and a target virtual vehicle; wherein, the target virtual vehicle includes a plurality of virtual vehicle-mounted sensors, and the plurality of virtual vehicle-mounted sensors include a virtual radar sensor and a virtual camera sensor;

[0006] Call the simulation vehicle control system to control the target virtual vehicle to perform autonomous driving in the target virtual driving environment, convert the virtual vehicle control data during autonomous driving into CAN bus data, and send the CAN bus data to the vehicle domain controller;

[0007] Call the simulation radar system to generate virtual radar data collected by the virtual radar sensor on the target virtual driving environment during autonomous driving, convert the virtual radar data into radar sensing data, and send the radar sensing data to the vehicle domain controller;

[0008] Call the simulation camera system to generate virtual environment data collected by the virtual camera sensor on the target virtual driving environment during autonomous driving, convert the virtual environment data into environment video data, and send the environment video data to the vehicle domain controller;

[0009] Receive the autonomous driving decision-making data generated by the vehicle domain controller based on the CAN bus data, radar sensing data, and environmental video data, and control the target virtual vehicle to perform autonomous driving in the target virtual driving environment according to the autonomous driving decision-making data.

[0010] Optionally, according to the test task input by the user, call the simulation environment system to create a target virtual driving environment and a target virtual vehicle, including:

[0011] Create multiple virtual driving sub-environments, and determine multiple target virtual driving sub-environments from the multiple virtual driving sub-environments according to the test task input by the user, and combine the multiple target virtual driving sub-environments to generate a target virtual driving environment;

[0012] Create multiple virtual vehicle accessories, and determine multiple target virtual vehicle accessories from the multiple virtual vehicle accessories according to the test task input by the user, and combine the multiple target virtual vehicle accessories to generate a target virtual vehicle.

[0013] Optionally, the autonomous driving simulation platform is also provided with an interactive control interface, and further includes:

[0014] In response to the user's operation on the interactive control interface, generate a user control instruction for the target virtual vehicle, and send the user control instruction to the vehicle domain controller, so that the vehicle domain controller adjusts the autonomous driving decision-making data according to the user control instruction.

[0015] Optionally, it further includes:

[0016] Obtain the driving process data of the target virtual vehicle during autonomous driving;

[0017] Generate a vehicle simulation test result according to the driving process data, and generate an optimization strategy for the autonomous driving function in the vehicle domain controller according to the vehicle simulation test result.

[0018] Optionally, it further includes:

[0019] When detecting abnormal data in the driving process data, mark and alarm the abnormal data, and re-execute the test task.

[0020] Optionally, the vehicle domain controller is connected to the in-vehicle screen of the real vehicle, and further includes:

[0021] Display the radar sensing data and the environmental video data on the in-vehicle screen.

[0022] Optionally, the test task includes a test task for any one or more of the following functions:

[0023] Automatic parking, collision warning, emergency braking, road departure warning, emergency lane keeping, lane centering assist, adaptive cruise control, blind spot monitoring and lane change warning.

[0024] A device for vehicle simulation testing, applied to an autonomous driving simulation platform. The autonomous driving simulation platform includes a simulation environment system, a simulation vehicle control system, a simulation radar system, and a simulation camera system. The autonomous driving simulation platform is deployed on a target device, and the target device is communicatively connected to the vehicle domain controller of a real vehicle. The device is configured to:

[0025] According to a test task input by a user, call the simulation environment system to create a target virtual driving environment and a target virtual vehicle; wherein, the target virtual vehicle includes a plurality of virtual vehicle-mounted sensors, and the plurality of virtual vehicle-mounted sensors include virtual radar sensors and virtual camera sensors;

[0026] Call the simulation vehicle control system to control the target virtual vehicle to perform autonomous driving in the target virtual driving environment, convert virtual vehicle control data during autonomous driving into CAN bus data, and send the CAN bus data to the vehicle domain controller;

[0027] Call the simulation radar system to generate virtual radar data collected by the virtual radar sensor on the target virtual driving environment during autonomous driving, convert the virtual radar data into radar sensing data, and send the radar sensing data to the vehicle domain controller;

[0028] Call the simulation camera system to generate virtual environment data collected by the virtual camera sensor on the target virtual driving environment during autonomous driving, convert the virtual environment data into environmental video data, and send the environmental video data to the vehicle domain controller;

[0029] Receive autonomous driving decision data generated by the vehicle domain controller based on the CAN bus data, radar sensing data, and environmental video data, and control the target virtual vehicle to perform autonomous driving in the target virtual driving environment according to the autonomous driving decision data.

[0030] An electronic device includes a processor, a memory, and a computer program stored on the memory and capable of running on the processor. When the computer program is executed by the processor, the above-mentioned method is implemented.

[0031] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the above-mentioned method is implemented.

[0032] The embodiments of the present invention have the following advantages:

[0033] In the embodiments of the present invention, by invoking the simulation environment system, a target virtual driving environment and a target virtual vehicle are created; the target virtual vehicle is controlled to perform autonomous driving in the target virtual driving environment, and the virtual vehicle control data during the autonomous driving process is converted into CAN bus data, and the CAN bus data is sent to the vehicle domain controller; receiving the autonomous driving decision data generated by the vehicle domain controller according to the CAN bus data, radar sensing data, and environmental video data, and controlling the target virtual vehicle to perform autonomous driving in the target virtual driving environment according to the autonomous driving decision data, realizing the generation of autonomous driving decision data by invoking the simulation environment system and combining with the real vehicle domain controller, enabling the deep integration of the virtual driving environment and autonomous driving technology, and eliminating the need for dangerous on-road field tests, which not only reduces the test cost but also improves the safety and controllability of the test. Description of the Drawings

[0034] To more clearly illustrate the technical solutions of the present invention, the drawings required for the description of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0035] Figure 1 is a flowchart of the steps of a vehicle simulation test method provided by some embodiments of the present invention;

[0036] Figure 2 is a schematic diagram of a vehicle simulation test architecture provided by some embodiments of the present invention. Detailed Embodiments

[0037] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0038] Refer to Figure 1 , which shows a flowchart of the steps of a vehicle simulation test method provided by some embodiments of the present invention, applied to an autonomous driving simulation platform. The autonomous driving simulation platform includes a simulation environment system, a simulation vehicle control system, a simulation radar system, and a simulation camera system. The autonomous driving simulation platform is deployed on a target device, and the target device is communicatively connected to the vehicle domain controller of a real vehicle.

[0039] As some examples, the target device can be a computer or other electronic devices with computing capabilities; these target devices are capable of running an autonomous driving simulation platform to simulate the real-world traffic environment and test and verify the target virtual vehicle.

[0040] In some examples, an autonomous driving simulation platform can be customized in advance based on the Unity simulation platform with the help of its real-time 3D engine, mapping the real scenes of the physical space and some road scenes into the digital world, and constructing a virtual test environment; the autonomous driving simulation platform can also be published in a B / S architecture and support operations on mobile phones, tablets, PCs, etc.

[0041] In practical applications, the simulation environment built by the Unity engine can achieve high-precision virtual world modeling, and at the same time support the simulation of various physical-level sensors such as navigation, ultrasonic, camera, millimeter-wave radar, and lidar, which can effectively improve the authenticity of the test.

[0042] At the same time, an environment perception simulator model can be established through learning (such as Figure 2 the simulation camera system and simulation radar system in

[0043] to achieve the simulation of the output of sensors such as radar and lidar; moreover, a vehicle control model (simulation vehicle control system) is added to achieve the automation test of the automatic parking scenario in the digital world. Through this autonomous driving simulation platform, comprehensive simulation tests can be carried out on the target virtual vehicle, including aspects such as environment perception, vehicle control, radar detection, and image recognition.

[0044] Among them, the simulation environment system can simulate various complex road scenes and traffic conditions, the simulation vehicle control system can simulate the dynamic characteristics and motion laws of real vehicles, and the simulation radar system and simulation camera system can simulate the sensor data relied on by real vehicles.

[0045] During the simulation test process, the autonomous driving simulation platform will transmit the simulation data to the target device in real time, and the target device will then forward the data to the vehicle domain controller of the real vehicle. The vehicle domain controller controls and makes decisions on the autonomous driving vehicle according to the received simulation data, thereby realizing the simulation test of the autonomous driving vehicle. In this way, the simulation test of the autonomous driving vehicle can be carried out efficiently without relying on the real road environment, improving the test efficiency and safety.

[0046] Such as Figure 2A schematic diagram of a vehicle simulation test architecture provided by the present invention may consist of a target device (Personal Computer, PC / computer), a power supply, a vehicle domain controller in a real vehicle, and a vehicle head unit screen; among them, an autonomous driving simulation platform can run in the target device, and the autonomous driving simulation platform includes a simulation environment system, a simulation vehicle control system, a simulation radar system, and a simulation camera system; the vehicle domain controller includes a SOC (System on Chip) and an MCU (Microcontroller Unit); ADB and Peak refer to connection methods, Python is a cross-platform computer programming language, and CASE represents a part of a switch statement.

[0047] Specifically, the following steps may be included:

[0048] Step 101, according to the test task input by the user, call the simulation environment system to create a target virtual driving environment and a target virtual vehicle; wherein, the target virtual vehicle includes a plurality of virtual in-vehicle sensors, and the plurality of virtual in-vehicle sensors include virtual radar sensors and virtual camera sensors.

[0049] As some examples, the target virtual driving environment can be customized according to actual needs, such as including various factors such as garage type, road type, traffic signs, weather conditions, and lighting conditions to simulate various driving scenarios that may occur in the real world. The target virtual vehicle can also be configured according to test requirements, including parameters such as vehicle type, size, weight, and power performance to ensure the accuracy and effectiveness of the simulation test.

[0050] In some examples, the target virtual vehicle includes a plurality of virtual in-vehicle sensors, and the plurality of virtual in-vehicle sensors include virtual radar sensors and virtual camera sensors. These virtual in-vehicle sensors can simulate the functions and performances of the corresponding sensors in a real vehicle, providing comprehensive sensor data support for the simulation test of autonomous driving vehicles; by accurately simulating the sensor data of a real vehicle, the perception, decision-making, and control capabilities of autonomous driving vehicles in complex road scenarios and traffic conditions can be evaluated more accurately, thereby improving the safety and reliability of autonomous driving vehicles.

[0051] In some embodiments of the present invention, the test task includes a test task for any one or more of the following functions: automatic parking, collision warning, emergency braking, road departure warning, emergency lane keeping, lane centering assistance, adaptive cruise control, blind spot monitoring, and lane change warning.

[0052] As some examples, the test task can comprehensively evaluate the performance of autonomous driving vehicles in various typical scenarios.

[0053] For example, in an automatic parking test, the simulation environment system will simulate various parking spaces and the situations of surrounding vehicles to verify the parking accuracy and efficiency of the autonomous driving vehicle.

[0054] In a collision warning test, the simulation vehicle control system will simulate the situation where there is an obstacle ahead or a vehicle suddenly changes lanes to check whether the collision warning system of the autonomous driving vehicle can issue an alarm in a timely manner.

[0055] The emergency braking test evaluates the emergency braking performance and safety of the autonomous driving vehicle by simulating the situation of a sudden obstacle ahead or a vehicle making an emergency stop.

[0056] The road departure warning test simulates the situation where the driver inadvertently deviates from the lane during driving to verify whether the autonomous driving vehicle can issue a warning in a timely manner and assist the driver in correcting the direction.

[0057] The emergency lane keeping test examines the lane keeping ability of the autonomous driving vehicle by simulating the situation where the driver needs to keep the lane in an emergency.

[0058] The lane centering assist test can evaluate whether the autonomous driving vehicle can stably maintain driving in the center of the lane in scenarios such as highways.

[0059] The adaptive cruise control test examines whether the cruise control system of the autonomous driving vehicle can adaptively adjust the vehicle speed and distance by simulating the situation where the vehicle ahead accelerates or decelerates.

[0060] The blind spot monitoring and lane change warning test evaluates the accuracy and reliability of the blind spot monitoring and lane change warning systems of the autonomous driving vehicle by simulating the situation where a vehicle in the adjacent lane approaches or changes lanes.

[0061] In some embodiments of the present invention, according to the test task input by the user, the simulation environment system is called to create a target virtual driving environment and a target virtual vehicle, including: creating a plurality of virtual driving sub - environments, and determining a plurality of target virtual driving sub - environments from the plurality of virtual driving sub - environments according to the test task input by the user, combining the plurality of target virtual driving sub - environments to generate a target virtual driving environment; creating a plurality of virtual vehicle accessories, and determining a plurality of target virtual vehicle accessories from the plurality of virtual vehicle accessories according to the test task input by the user, combining the plurality of target virtual vehicle accessories to generate a target virtual vehicle.

[0062] As some examples, the virtual driving sub-environments may include, but are not limited to, different types of driving environments such as urban roads, highways, rural roads, mountain roads, roads in rainy or snowy weather, and night roads, so as to comprehensively simulate various complex driving scenarios. The virtual vehicle accessories may include, but are not limited to, key components such as the vehicle's power system, braking system, steering system, suspension system, tires, and lighting system, to simulate the performance and reactions of the vehicle under different conditions. By combining different virtual driving sub-environments and virtual vehicle accessories, various complex target virtual driving environments and target virtual vehicles can be generated, thus meeting the needs of users for different test tasks.

[0063] In some examples, according to the test task input by the user, the target virtual driving sub-environments selected from multiple virtual driving sub-environments can be combined together to form a more complex virtual driving environment closer to the actual test needs. Then, according to the requirements of the test task, the target virtual vehicle accessories are selected from multiple virtual vehicle accessories and combined together to form a complete target virtual vehicle.

[0064] Step 102, call the simulation vehicle control system, control the target virtual vehicle to perform autonomous driving in the target virtual driving environment, convert the virtual vehicle control data during the autonomous driving process into CAN bus data, and send the CAN bus data to the vehicle domain controller.

[0065] As some examples, the virtual vehicle control data may be various state information of the target virtual vehicle during the autonomous driving process in the target virtual driving environment, including but not limited to the vehicle's speed, acceleration, steering angle, braking force, suspension system state, tire state, and lighting system state, etc.

[0066] In some examples, such as Figure 2 , the simulation vehicle control system converts the virtual vehicle control data into CAN bus data and sends it to the vehicle domain controller. After receiving the CAN bus data, the vehicle domain controller will perform corresponding control operations on the target virtual vehicle according to the content and format of the data. During the simulation test process, real-time data interaction can be carried out between the simulation vehicle control system and the vehicle domain controller to ensure that the target virtual vehicle can perform autonomous driving in the target virtual driving environment according to the predetermined trajectory and speed.

[0067] Step 103, call the simulation radar system, generate virtual radar data collected by the virtual radar sensor on the target virtual driving environment during the autonomous driving process, convert the virtual radar data into radar sensing data, and send the radar sensing data to the vehicle domain controller.

[0068] As some examples, the virtual radar data can be various information obtained by a virtual radar sensor scanning and perceiving a target virtual driving environment during the autonomous driving process of a target virtual vehicle, including but not limited to the distance, speed, direction, size, shape, and material of the target, etc.

[0069] In some examples, such as Figure 2 , the simulation radar system converts the virtual radar data into radar sensing data through a signal conversion card and sends it to the vehicle domain controller. After receiving the radar sensing data, the vehicle domain controller will combine other sensor data and vehicle status information to comprehensively analyze the environment around the target virtual vehicle, so as to make more accurate and intelligent driving decisions. During the simulation test process, real-time data interaction can also be carried out between the simulation radar system and the vehicle domain controller to ensure that the target virtual vehicle can more realistically simulate the radar perception and response capabilities in the actual driving scenario.

[0070] Step 104, call the simulation camera system to generate virtual environment data collected by the virtual camera sensor for the target virtual driving environment during the autonomous driving process, convert the virtual environment data into environment video data, and send the environment video data to the vehicle domain controller.

[0071] As some examples, the virtual environment data can be image and video information obtained by a virtual camera sensor shooting and capturing a target virtual driving environment during the autonomous driving process of a target virtual vehicle. This information can reflect in detail the environmental conditions around the target virtual vehicle, including but not limited to road conditions, traffic signs, pedestrians, other vehicles, and obstacles, etc.

[0072] In some examples, such as Figure 2 , the simulation camera system converts the virtual environment data into environment video data through a video conversion card and sends it to the vehicle domain controller. After receiving the environment video data, the vehicle domain controller will combine the radar sensing data, other sensor data, and vehicle status information to conduct a more comprehensive and in-depth comprehensive analysis of the environment around the target virtual vehicle to help the vehicle domain controller more accurately judge the environmental changes around the target virtual vehicle, so as to make more intelligent and safe driving decisions. During the simulation test process, real-time data interaction can also be carried out between the simulation camera system and the vehicle domain controller to ensure that the target virtual vehicle can more realistically simulate the visual perception and response capabilities in the actual driving scenario.

[0073] Step 105, receive the autonomous driving decision data generated by the vehicle domain controller based on the CAN bus data, radar sensing data, and environment video data, and control the target virtual vehicle to perform autonomous driving in the target virtual driving environment according to the autonomous driving decision data.

[0074] As some examples, the autonomous driving decision data may include, but are not limited to, driving instructions such as acceleration, braking, and steering of the target virtual vehicle, as well as the recognition results of traffic signs, the predicted trajectories of other vehicles and pedestrians, etc. By controlling the target virtual vehicle to perform autonomous driving according to the autonomous driving decision data, the effectiveness and safety of the autonomous driving function can be further verified. At the same time, various complex situations in the actual driving scenario can also be simulated, providing strong support for the research and development and optimization of autonomous driving technology.

[0075] In addition, during the simulation test process, the parameters of the target virtual vehicle and the virtual driving environment can also be adjusted as needed to achieve comprehensive coverage and testing of different driving scenarios and conditions.

[0076] In some embodiments of the present invention, the autonomous driving simulation platform is further provided with an interactive control interface, and further includes: in response to the user's operation on the interactive control interface, generating a user control instruction for the target virtual vehicle, and sending the user control instruction to the vehicle domain controller, so that the vehicle domain controller adjusts the autonomous driving decision data according to the user control instruction.

[0077] As some examples, the interactive control interface allows users (such as testers) to intuitively monitor and manage the simulation test process. Testers can view the driving state of the target virtual vehicle, the simulation of the virtual driving environment, and the generation and execution effects of the autonomous driving decision data in real time through this interface.

[0078] In some examples, the interactive control interface can also provide a series of operation tools, enabling users to conveniently adjust test parameters, set test scenarios, start and stop tests, etc.

[0079] For example, users can adjust the driving speed, driving direction of the target virtual vehicle in real time through the interactive control interface or simulate specific traffic events, etc., so as to more flexibly test the response and processing capabilities in different situations.

[0080] In some embodiments of the present invention, it further includes: obtaining the driving process data of the target virtual vehicle during autonomous driving; generating a vehicle simulation test result according to the driving process data, and generating an optimization strategy for the autonomous driving function in the vehicle domain controller according to the vehicle simulation test result.

[0081] As some examples, driving process data may include driving trajectories, speed changes, acceleration data, steering angles, sensor input information, etc.; this data can be recorded and stored in real time for subsequent analysis and evaluation; among them, the vehicle simulation test results can reflect in detail the performance of the target virtual vehicle during the autonomous driving process, including its compliance with traffic rules, response ability to emergencies, rationality of the driving path, etc. By analyzing this data, testers can evaluate the performance and safety of the autonomous driving system, and thus optimize and improve it.

[0082] Among them, the optimization strategy is to improve the performance, safety and reliability of the autonomous driving function. For example, if the test results reveal deficiencies in the autonomous driving decision-making in certain specific scenarios, the optimization strategy may include adjusting algorithm parameters, increasing the accuracy of sensor fusion, or improving the environmental perception simulator model, etc. By continuously optimizing the autonomous driving function in the vehicle domain controller, the adaptability of autonomous driving vehicles in various complex environments can be significantly improved, ensuring driving safety.

[0083] In some examples, when simulating the scenario of the target virtual vehicle automatically parking in the target virtual driving environment, the driving process data may also include parameters such as parking space parameters, parking space type, parking time, parking times, completion attitude, angle, etc.

[0084] Among them, these driving process data can not only help testers comprehensively understand the behavioral characteristics of the target virtual vehicle during the automatic parking process, but also be used to evaluate the efficiency and accuracy of the automatic parking system.

[0085] For example, the parking space parameters can describe the specific size and location of the parking space, helping testers understand the performance of the autonomous driving function under different parking space conditions; the parking space type can include different types such as parallel parking and perpendicular parking, reflecting the adaptability of the autonomous driving system to different parking scenarios; the length of the parking time directly reflects the response speed and execution efficiency of the automatic parking system; the number of parking times can indirectly reflect the stability and reliability of the system; and the quality of the completion attitude, such as whether the vehicle stops smoothly in the parking space and the parallelism between the vehicle body and the parking space border, is an important consideration for the accuracy of the automatic parking system and the user experience. By comprehensively analyzing these performance parameters, testers can more accurately locate the problems existing in the autonomous driving function, and then formulate targeted optimization strategies to continuously improve the practicality and user satisfaction of the automatic parking function.

[0086] In some embodiments of the present invention, it further includes: when detecting abnormal data in the driving process data, marking and warning the abnormal data, and re-executing the test task.

[0087] For example, during the automatic parking simulation test, the system can monitor and analyze the driving process data in real time. Once abnormal data is detected, such as an abnormally extended parking time, an abnormally increased number of parking attempts, a significantly poor completion posture, or hitting an obstacle, etc., the system will immediately mark this abnormal data and trigger an alarm mechanism to alert the tester. At the same time, to ensure the accuracy and reliability of the test results, the system will automatically re-execute the test task to exclude abnormalities caused by accidental factors, thereby obtaining more accurate and stable test data.

[0088] In some embodiments of the present invention, the vehicle domain controller is connected to the in-vehicle screen of the real vehicle, and further includes: displaying the radar sensing data and the environmental video data on the in-vehicle screen.

[0089] As some examples, the radar sensing data and the environmental video data can also be displayed and replayed on the in-vehicle screen of the real vehicle to enhance the ability of quick positioning and analysis. For example, it can be replayed by pouring back through zrosbag2, topic_bag, canlog, etc.

[0090] In the embodiments of the present invention, by calling the simulation environment system, a target virtual driving environment and a target virtual vehicle are created; the target virtual vehicle is controlled to perform autonomous driving in the target virtual driving environment, and the virtual vehicle control data during the autonomous driving process is converted into CAN bus data, and the CAN bus data is sent to the vehicle domain controller; the vehicle domain controller generates autonomous driving decision data based on the CAN bus data, the radar sensing data, and the environmental video data, and controls the target virtual vehicle to perform autonomous driving in the target virtual driving environment according to the autonomous driving decision data, realizing the generation of autonomous driving decision data by calling the simulation environment system and combining with the real vehicle domain controller, enabling the deep integration of the virtual driving environment and autonomous driving technology, and eliminating the need for dangerous on-road field tests, which not only reduces the test cost but also improves the safety and controllability of the test.

[0091] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequence, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential for the embodiments of the present invention.

[0092] Some embodiments of the present invention also provide a device for vehicle simulation testing, which is applied to an autonomous driving simulation platform. The autonomous driving simulation platform includes a simulation environment system, a simulation vehicle control system, a simulation radar system, and a simulation camera system. The autonomous driving simulation platform is deployed on a target device, and the target device is communicatively connected to the vehicle domain controller of a real vehicle. The device is configured to:

[0093] According to the test task input by the user, call the simulation environment system to create a target virtual driving environment and a target virtual vehicle; wherein, the target virtual vehicle includes a plurality of virtual vehicle-mounted sensors, and the plurality of virtual vehicle-mounted sensors include virtual radar sensors and virtual camera sensors;

[0094] Call the simulation vehicle control system to control the target virtual vehicle to perform autonomous driving in the target virtual driving environment, convert the virtual vehicle control data during the autonomous driving process into CAN bus data, and send the CAN bus data to the vehicle domain controller;

[0095] Call the simulation radar system to generate virtual radar data collected by the virtual radar sensor on the target virtual driving environment during the autonomous driving process, convert the virtual radar data into radar sensing data, and send the radar sensing data to the vehicle domain controller;

[0096] Call the simulation camera system to generate virtual environment data collected by the virtual camera sensor on the target virtual driving environment during the autonomous driving process, convert the virtual environment data into environmental video data, and send the environmental video data to the vehicle domain controller;

[0097] Receive the autonomous driving decision data generated by the vehicle domain controller based on the CAN bus data, radar sensing data, and environmental video data, and control the target virtual vehicle to perform autonomous driving in the target virtual driving environment according to the autonomous driving decision data.

[0098] In some embodiments of the present invention, according to the test task input by the user, calling the simulation environment system to create a target virtual driving environment and a target virtual vehicle includes:

[0099] Create a plurality of virtual driving sub-environments, and according to the test task input by the user, determine a plurality of target virtual driving sub-environments from the plurality of virtual driving sub-environments, and combine the plurality of target virtual driving sub-environments to generate a target virtual driving environment;

[0100] Create a plurality of virtual vehicle accessories, and according to the test task input by the user, determine a plurality of target virtual vehicle accessories from the plurality of virtual vehicle accessories, and combine the plurality of target virtual vehicle accessories to generate a target virtual vehicle.

[0101] In some embodiments of the present invention, the autonomous driving simulation platform is further provided with an interactive control interface, and the device is further configured to:

[0102] Respond to the operation of the user on the interactive control interface, generate a user control instruction for the target virtual vehicle, and send the user control instruction to the vehicle domain controller, so that the vehicle domain controller adjusts the autonomous driving decision data according to the user control instruction.

[0103] In some embodiments of the present invention, the device is further configured to:

[0104] Obtain the driving process data of the target virtual vehicle during autonomous driving;

[0105] Generate a vehicle simulation test result according to the driving process data, and generate an optimization strategy for the autonomous driving function in the vehicle domain controller according to the vehicle simulation test result.

[0106] In some embodiments of the present invention, the device is further configured to:

[0107] When detecting abnormal data in the driving process data, mark and alarm the abnormal data, and re-execute the test task.

[0108] In some embodiments of the present invention, the vehicle domain controller is connected to the car machine screen of the real vehicle, and the device is further configured to:

[0109] Display the radar sensing data and the environmental video data on the car machine screen.

[0110] In some embodiments of the present invention, the test task includes a test task for any one or more of the following functions:

[0111] Automatic parking, collision warning, emergency braking, road departure warning, emergency lane keeping, lane centering assist, adaptive cruise control, blind spot monitoring and lane change warning.

[0112] Some embodiments of the present invention further provide an electronic device, including a processor, a memory, and a computer program stored on the memory and capable of running on the processor. When the computer program is executed by the processor, the above method is implemented.

[0113] Some embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the above method is implemented.

[0114] Some embodiments of the present invention also provide a computer program product, including a computer program which, when executed by a processor, implements the method as described above.

[0115] For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, please refer to the partial description of the method embodiments.

[0116] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0117] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other.

[0118] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device, or a computer program product. Therefore, the embodiments of the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal devices generate a device for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0120] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 specified in one block or multiple blocks.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operational steps are performed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 specified in one block or multiple blocks.

[0122] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0123] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or terminal device comprising a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the above elements.

[0124] The above has provided a detailed introduction to a method, apparatus, electronic device and medium for vehicle simulation testing. Specific examples are used in this article to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for vehicle simulation testing, characterized in that, Applied to an autonomous driving simulation platform, the autonomous driving simulation platform includes a simulation environment system, a simulation vehicle control system, a simulation radar system, and a simulation camera system. The autonomous driving simulation platform is deployed on a target device, and the target device is communicatively connected to the vehicle domain controller of a real vehicle. The method includes: According to a test task input by a user, call the simulation environment system to create a target virtual driving environment and a target virtual vehicle; wherein, the target virtual vehicle includes a plurality of virtual in-vehicle sensors, and the plurality of virtual in-vehicle sensors include virtual radar sensors and virtual camera sensors; Call the simulation vehicle control system to control the target virtual vehicle to perform autonomous driving in the target virtual driving environment, convert the virtual vehicle control data during autonomous driving into CAN bus data, and send the CAN bus data to the vehicle domain controller; Call the simulation radar system to generate virtual radar data collected by the virtual radar sensor on the target virtual driving environment during autonomous driving, convert the virtual radar data into radar sensing data, and send the radar sensing data to the vehicle domain controller; Call the simulation camera system to generate virtual environment data collected by the virtual camera sensor on the target virtual driving environment during autonomous driving, convert the virtual environment data into environmental video data, and send the environmental video data to the vehicle domain controller; Receive the autonomous driving decision data generated by the vehicle domain controller based on the CAN bus data, radar sensing data, and environmental video data, and control the target virtual vehicle to perform autonomous driving in the target virtual driving environment according to the autonomous driving decision data.

2. The method according to claim 1, wherein According to a test task input by a user, calling the simulation environment system to create a target virtual driving environment and a target virtual vehicle includes: Create a plurality of virtual driving sub-environments, and determine a plurality of target virtual driving sub-environments from the plurality of virtual driving sub-environments according to the test task input by the user, and combine the plurality of target virtual driving sub-environments to generate a target virtual driving environment; Create a plurality of virtual vehicle accessories, and determine a plurality of target virtual vehicle accessories from the plurality of virtual vehicle accessories according to the test task input by the user, and combine the plurality of target virtual vehicle accessories to generate a target virtual vehicle.

3. The method according to claim 1 or 2, characterized in that, The autonomous driving simulation platform is further provided with an interactive control interface, and further includes: In response to an operation of the user on the interactive control interface, generate a user control instruction for the target virtual vehicle, and send the user control instruction to the vehicle domain controller, so that the vehicle domain controller adjusts the autonomous driving decision data according to the user control instruction.

4. The method according to claim 1 or 2, characterized in that, Further includes: Obtain the driving process data of the target virtual vehicle during autonomous driving; Generate a vehicle simulation test result according to the driving process data, and generate an optimization strategy for the autonomous driving function in the vehicle domain controller according to the vehicle simulation test result.

5. The method according to claim 4, wherein Further includes: When abnormal data is detected in the driving process data, the abnormal data is marked and alarmed, and the test task is re-executed.

6. The method according to claim 5, wherein The vehicle domain controller is connected to the car machine screen of the real vehicle, and further includes: Display the radar sensing data and the environmental video data on the car machine screen.

7. The method according to claim 6, wherein The test task includes test tasks for any one or more of the following functions: Automatic parking, collision warning, emergency braking, road departure warning, emergency lane keeping, lane centering assist, adaptive cruise control, blind spot monitoring and lane change warning.

8. A device for vehicle simulation testing, characterized in that, Applied to an autonomous driving simulation platform, the autonomous driving simulation platform includes a simulation environment system, a simulation vehicle control system, a simulation radar system, and a simulation camera system. The autonomous driving simulation platform is deployed on a target device, and the target device is communicatively connected to the vehicle domain controller of the real vehicle. The device is used for: According to the test task input by the user, call the simulation environment system to create a target virtual driving environment and a target virtual vehicle; wherein, the target virtual vehicle includes a plurality of virtual vehicle-mounted sensors, and the plurality of virtual vehicle-mounted sensors include virtual radar sensors and virtual camera sensors; Call the simulation vehicle control system to control the target virtual vehicle to perform autonomous driving in the target virtual driving environment, convert the virtual vehicle control data during the autonomous driving process into CAN bus data, and send the CAN bus data to the vehicle domain controller; Call the simulation radar system to generate virtual radar data collected by the virtual radar sensor for the target virtual driving environment during the autonomous driving process, convert the virtual radar data into radar sensing data, and send the radar sensing data to the vehicle domain controller; Call the simulation camera system to generate virtual environment data collected by the virtual camera sensor for the target virtual driving environment during the autonomous driving process, convert the virtual environment data into environmental video data, and send the environmental video data to the vehicle domain controller; Receive the autonomous driving decision-making data generated by the vehicle domain controller based on the CAN bus data, radar sensing data, and environmental video data, and control the target virtual vehicle to perform autonomous driving in the target virtual driving environment according to the autonomous driving decision-making data.

9. An electronic device, characterized in that, Includes a processor, a memory, and a computer program stored on the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, it implements the method according to any one of claims 1 to 7.

Images