A complete vehicle testing system and method for autonomous driving vehicle
Through the automotive wireless communication system, map and positioning simulation system, the problem that the existing autonomous vehicle bench test methods cannot truly simulate traffic scenarios is solved, and efficient and reliable vehicle testing of autonomous vehicles is achieved. Save time and space costs.
Patent Information
- Application Number
- CN202310949320.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-28
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2043-07-28
AI Technical Summary
The existing self-driving car bench test methods are mainly system-level and cannot truly simulate traffic scenarios, resulting in insufficient reliability of test results, and problems are prone to occur after the vehicle is integrated, and the existing methods cannot effectively save time and space. cost.
The four-in-one closed-loop system consisting of a vehicle wireless communication system, a map, positioning simulation system and a bench test system, replicate the environmental signals of the actual traffic scene through a signal generator, and combines the map system to simulate the relative position relationship between vehicles and roads. Realize vehicle testing of autonomous vehicles and ensure the reliability of test results.
The vehicle function test of autonomous vehicles is realized in limited space and time, which improves the reliability of test results and the safety of system operation and saves test costs.
Smart Images

Figure CN117007333B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of autonomous driving vehicles, and in particular to a whole vehicle testing system and method for autonomous driving vehicles. Background Art
[0002] Fully autonomous driving is the ultimate goal of autonomous driving technology, but it currently remains at the L3 level; the application of vehicle-to-everything (V2X) wireless communication technology and high-precision map technology will accelerate the realization of fully autonomous driving.
[0003] However, at present, vehicle wireless communication technology and high-precision map technology have not yet been fully applied to autonomous vehicles. The stable application of these two technologies requires a large number of road tests, but road tests consume a lot of time and manpower.
[0004] Bench testing has the advantage of saving time and effort. However, the current bench testing methods for autonomous vehicles are mainly oriented towards the system level. When multiple systems are integrated into the entire vehicle, various problems will arise.
[0005] Vehicle bench testing offers the advantages of saving time and effort while avoiding problems that may arise after system integration into the vehicle. However, there is currently no reasonable solution. Moreover, existing bench testing relies on videos or images, which cannot realistically simulate traffic scenarios and make it difficult to guarantee the reliability of test results. Summary of the Invention
[0006] The purpose of the present invention is to provide a whole-vehicle testing system and method for autonomous driving vehicles, which can test the functions of the whole-vehicle autonomous driving vehicle in a limited space. Moreover, the reliability of the test results is ensured by adopting a method of calculating the relative position relationship between the vehicle and the road, extracting environmental signals based on actual traffic scenarios, and reproducing them.
[0007] In order to solve the above technical problems, the present invention provides a self-driving car whole vehicle testing system, comprising:
[0008] The vehicle wireless communication system is used to transmit environmental signals extracted from actual traffic scenarios to vehicles after being reproduced using a signal generator;
[0009] A map and positioning simulation system receives motion state parameters, obtains the vehicle's position coordinates through a vehicle positioning simulator, and combines this with a map system to obtain the relative position relationship between the vehicle and the road. This information is then sent to the vehicle, allowing the vehicle's autonomous driving system to plan its motion trajectory based on the reproduced traffic scenario.
[0010] The bench test system is used to simulate the motion conditions of the vehicle and collect the vehicle's motion state parameters.
[0011] Furthermore, the vehicle wireless communication system is further configured to uniformly arrange the reproduced environmental signals through a signal format converter, and transmit the reproduced environmental signals to the vehicle in chronological order.
[0012] Furthermore, it also includes a host computer system;
[0013] The host computer system is used to control the bench test system.
[0014] Furthermore, the host computer system is also used to display the target trajectory, the traffic scene and the motion trajectory in the order of the time axis.
[0015] Furthermore, the environmental signals include pedestrian signals, vehicle signals, infrastructure signals and road signals.
[0016] Furthermore, the pedestrian signal includes the pedestrian's position, travel direction and speed;
[0017] Alternatively, the vehicle signal includes the position, velocity, acceleration and heading angle of the environment vehicle;
[0018] Alternatively, the infrastructure signals include traffic signs, traffic markings and traffic lights;
[0019] Alternatively, the road signal includes road curvature and road slope.
[0020] Furthermore, the priorities of the pedestrian signal, vehicle signal, infrastructure signal and road signal decrease in sequence.
[0021] Furthermore, the map system is a map constructed based on actual traffic scenarios, the coverage of the map is the area where the actual traffic scenarios are located, and the physical objects in the map are represented by coordinates.
[0022] In order to solve the above technical problems, the present invention also provides a method for testing a whole vehicle of an autonomous driving vehicle, comprising:
[0023] The environmental signals extracted from the actual traffic scene are reproduced using a signal generator and then sent to the vehicle;
[0024] The vehicle's position coordinates are obtained through a vehicle positioning simulator. Combined with a map system, the relative position relationship between the vehicle and the road is obtained and sent to the vehicle, allowing the vehicle's autonomous driving system to plan its motion trajectory based on the reproduced traffic scenario.
[0025] Start the test system to simulate the vehicle's motion conditions and collect the vehicle's motion state parameters.
[0026] Furthermore, it also includes displaying the target trajectory, the traffic scene and the motion trajectory in the order of the time axis.
[0027] Compared with the prior art, the present invention has the following beneficial effects:
[0028] The present invention simulates motion conditions through a bench test system, simulates the relative positional relationship between the vehicle and the road through a map and positioning simulation system, and reproduces the environmental signals of actual traffic scenes through a vehicle wireless communication system, thereby realizing whole-vehicle testing of the vehicle. Moreover, compared with the existing bench test method using video and images, the method of calculating the relative positional relationship between the vehicle and the road, extracting the environmental signals based on the actual traffic scene and reproducing them can better ensure the reliability of the test results.
[0029] The present invention can position the test vehicle on the test bench, saving test space and time costs.
[0030] The present invention provides a four-in-one closed-loop system consisting of a perception simulation system, a vehicle automatic driving system, a bench test system, and a host computer system, which can realize communication, monitoring, and control among the four, thereby improving the safety of the entire system operation and the reliability of the test results. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] The drawings in the specification, which constitute a part of this application, are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.
[0032] Figure 1 This is a logical relationship diagram of a full-vehicle testing system for an autonomous driving vehicle according to the first embodiment of the present invention;
[0033] Figure 2 This is a physical isometric diagram of an autonomous driving vehicle full vehicle testing system according to the first embodiment of the present invention;
[0034] Figure 3 This is a flowchart of a method for testing a whole autonomous vehicle according to the second embodiment of the present invention. DETAILED DESCRIPTION
[0035] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.
[0036] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.
[0037] To further clarify the objectives, technical solutions, and advantages of the embodiments of the present invention, the following will provide a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments are only a portion of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.
[0038] Example 1
[0039] One of the objectives of the present invention is to provide a full-vehicle testing system for autonomous vehicles, comprising a vehicle wireless communication system 121, a map and positioning simulation system 111, a bench test system 107, a host computer system 110, and a projection display device. This system is capable of performing full-vehicle testing of high-level autonomous vehicles.
[0040] This embodiment provides an autonomous driving vehicle whole vehicle testing system, which provides a method and system for simulating test vehicle positioning and simulating test vehicle perception signals, thereby enabling the positioning of the test vehicle on a test bench and saving testing space and time costs.
[0041] This embodiment provides an autonomous vehicle whole-vehicle testing system, which provides a four-in-one closed-loop system consisting of a perception simulation system, a vehicle autonomous driving system, a bench test system, and a host computer system. The system can realize communication, monitoring, and control among the four, thereby improving the safety of the entire system operation and the reliability of the test results.
[0042] like Figure 2As shown, the map and positioning simulation system 111 and the vehicle wireless communication equipment 112 are respectively installed on the ground 104 on one side of the bench test system 107, and communicate with the vehicle using hard lines; the host computer system 110 is installed on the ground 104 on one side of the bench test system 107, and communicates with the vehicle, the bench test system 107 and the projection display device using hard lines; the bench test system 107 is installed in a pit, with its upper end surface at the same horizontal plane as the ground 104, and communicates with the host computer system 110 using hard lines; the projector 102 of the projection display device is installed on the projector bracket 101, and the screen 103 is installed directly in front of the vehicle, maintaining a fixed distance from the vehicle; the test vehicle 106 is fixed to the bench test system 107 by the vehicle front wheel holder 105 and the vehicle rear wheel holder 109.
[0043] The vehicle wireless communication system 121 is used to reproduce the environmental signals extracted according to the actual traffic scene using a signal generator, uniformly arrange the reproduced environmental signals according to the time sequence through a signal format converter, and send the reproduced environmental signals at the same time in chronological order to the vehicle's automatic driving system to enable the vehicle's automatic driving system to plan the motion trajectory.
[0044] like Figure 1 As shown, the vehicle wireless communication system 121 divides the sensed signals into four categories: pedestrian side signals, vehicle side signals, infrastructure side signals, and road side signals. The system then simulates and transmits the signals through four signal generators: pedestrian side signals, vehicle side signals, infrastructure side signals, and road side signals.
[0045] The vehicle wireless communication system 121 primarily includes a signal generator, a signal format converter, and vehicle wireless communication equipment, enabling communication between environmental signals and the test vehicle. The signal generator generates vehicle perception signals in a timed sequence based on target signals extracted from typical scenarios. These include pedestrian signal generators, vehicle signal generators, infrastructure signal generators, and road signal generators.
[0046] like Figure 1 and Figure 2 As shown, the vehicle wireless communication system 121 mainly includes a pedestrian signal generator 116, a vehicle signal generator 117, an infrastructure signal generator 118, a road signal generator 119, a signal format converter 113, and a vehicle wireless communication device 112. The signal format converter can convert the signal from the signal generator into the CAN communication format used by the test vehicle.
[0047] The pedestrian side refers to people walking or riding bicycles. It has the function of sending pedestrian signals and can share information with the vehicle side through mobile phones or vehicles, including pedestrian location, travel direction, and speed.
[0048] On the pedestrian side, the source of pedestrian information is the actual traffic scene that has been collected, and then pedestrian features are extracted, then the pedestrian features are encoded and stored, and the signal is reproduced using the pedestrian signal generator 116, and finally communicated through the signal format converter and the vehicle wireless communication equipment; when there are a large number of pedestrians around, pedestrians who are closer to the vehicle have a higher communication priority.
[0049] The vehicle side, including the vehicle side and the surrounding vehicle side, can realize communication between the vehicle and the surrounding vehicles (environmental vehicles). In the present invention, the vehicle side only receives signals, and the surrounding vehicle side sends signals. When there are a large number of surrounding vehicles, vehicles with closer distances between vehicles enjoy higher communication priority.
[0050] The test vehicle 106 is equipped with a receiving terminal, and the signals of surrounding vehicles are generated using the vehicle signal generator 117 .
[0051] By collecting actual traffic scenes, extracting surrounding vehicle signals, and then extracting vehicle features including: vehicle position, speed, acceleration, heading angle, etc., the vehicle features are encoded and stored, and then generated and sent using the vehicle signal generator 117.
[0052] like Figure 1 and Figure 2 As shown, the infrastructure end refers to the signal of the infrastructure in the traffic environment; through the actual traffic scene that has been collected, the infrastructure signal is extracted, and then the infrastructure features including: traffic signs, traffic markings, and traffic lights are extracted, the infrastructure features are encoded and stored, and then generated and sent using the infrastructure signal generator 118.
[0053] like Figure 1 and Figure 2 As shown, the road end refers to the signal of the road in the traffic environment; through the actual traffic scene that has been collected, the road signal characteristics are extracted, including road curvature and road slope, the road characteristics are encoded and stored, and then generated and sent using the road signal generator 119.
[0054] After the four signal generators are uniformly sent to the signal format converter 113, the signal format converter will uniformly arrange the reproduced environmental signals according to the time sequence, and send the signals of different ports at the same time to the vehicle's automatic driving system 115 in chronological order.
[0055] The vehicle wireless communication device includes a signal transmitting end and a signal receiving end. The signal transmitting end is installed outside the vehicle and is connected to the signal format converter for transmitting pedestrian, vehicle, infrastructure, and road signals; the signal receiving end is installed inside the vehicle and is connected to the automatic driving system 115 for receiving signals sent by the signal transmitting end.
[0056] In the vehicle wireless communication system 121 , the signals of the four signal generators and the test vehicle communication should follow the priority: pedestrian side > vehicle side > infrastructure side > road side.
[0057] The pedestrian signal generator is used to replace pedestrians in actual scenes. It has the function of generating and sending pedestrian signals. The pedestrian signal characteristics are derived from actual traffic scenes, including pedestrian position, movement direction, speed, etc. The pedestrian signals extracted from the actual scene are arranged in time sequence and then sent to the signal format converter in time sequence.
[0058] The vehicle signal generator is used to replace the vehicles around the vehicle in the actual scene. It has the function of generating and sending signals of vehicles around the vehicle. The characteristics of the surrounding vehicle signals are derived from the actual traffic scene, including vehicle number, position, movement direction, speed, etc. The vehicle signals around the vehicle extracted from the actual scene are arranged in time sequence and then sent to the signal format converter in time sequence.
[0059] The infrastructure signal generator is used to replace the infrastructure slogan signal in the actual scene. It has the function of generating and sending infrastructure equipment signals. The characteristics of the infrastructure equipment signal are derived from the actual traffic scene, including traffic signs, traffic markings, and traffic lights. The infrastructure equipment signals extracted from the actual scene are arranged in time sequence and then sent to the signal format converter in time sequence.
[0060] The road signal generator replaces the road signal in the actual scene and has the function of generating and sending road signals. The road signal characteristics are derived from the actual traffic scene, including road curvature and road slope. The road signals extracted from the actual scene are arranged in time sequence and then sent to the signal format converter in time sequence.
[0061] The signal format converter is used to receive signals from four signal generators. After receiving the signals from the signal generators, the signal format converter will convert the signal format according to the timing, and send the signals from different ports at the same time to the vehicle's automatic driving system through the vehicle wireless communication device according to the timing.
[0062] The map and positioning simulation system 111 is used to receive motion state parameters, obtain the vehicle's position coordinates through the vehicle positioning simulator, and combine with the map system to obtain the relative position relationship between the vehicle and the road, and send it to the vehicle's automatic driving system to enable the vehicle's automatic driving system to plan the motion trajectory.
[0063] like Figure 1 and Figure 2As shown, mapping and positioning simulation system 111 includes a vehicle positioning simulator 114 and a mapping system 120. Vehicle positioning simulator 114 includes hardware and internal programs, while mapping system 120 is software installed within mapping and positioning simulation system 111. Vehicle positioning simulator 114 calculates the vehicle's coordinates by collecting the test vehicle's heading angle, velocity, and acceleration signals. Mapping and positioning simulation system 111 accurately locates the vehicle within the mapping system through coordinate query and replacement techniques.
[0064] like Figure 1 and Figure 2 As shown, the vehicle positioning simulator 114 is connected to the bench test system 107 through a data acquisition line to receive signals sent by the bench test system 107, including vehicle heading angle signals, speed signals, and acceleration signals. The vehicle positioning simulator 114 calculates the longitudinal and lateral positions of the vehicle through resampling, calculus and other methods to obtain the position coordinates of the vehicle at all times, and adds velocity, acceleration, and heading angle information to each position coordinate.
[0065] like Figure 1 and Figure 2 As shown, the data output end of the vehicle positioning simulator 114 is connected to the map and positioning simulation system 111, and the vehicle positioning simulator 114 sends the vehicle coordinates, speed, acceleration, and heading angle information to the map and positioning simulation system 111 through the data line.
[0066] like Figure 1 and Figure 2 As shown, the map system 120 is a local map constructed based on the collected scenes. The map mainly covers the area where the scenes are located (the area where the vehicle intends to travel). The physical objects in the map include roads, buildings, trees, etc., all of which are represented by coordinates. The roads in the map system 120 only have coordinate attributes, and signals such as lane lines and traffic lights are sent through the vehicle wireless communication system 121.
[0067] The positioning technology of the vehicle positioning simulator 114 in the map system 120, when the vehicle positioning simulator 114 sends the vehicle position coordinates to the map system 120, the map and positioning simulation system 111 automatically queries the target coordinates through the coordinates, and then replaces the original coordinates with the new vehicle coordinates, and marks and stores the completed positioning coordinates.
[0068] like Figure 1 and Figure 2As shown, mapping and positioning simulation system 111 uses coordinate query and positioning technology to accurately locate vehicle coordinates on the map, transmits the vehicle positioning information to autonomous driving control system 115, and updates the data in real time. Specifically, mapping and positioning simulation system 111 compares the vehicle coordinates with the road coordinates, calculates the relative position, and transmits the relative position relationship between the vehicle and the road to autonomous driving system 115. Autonomous driving system 115 then makes decisions and plans to control the vehicle's trajectory based on the vehicle's position information.
[0069] like Figure 1 and Figure 2 As shown, the test bench system 107 consists of a control system, a longitudinal motion simulation system, a lateral motion simulation system, and a test bench signal acquisition system. It can communicate with the host computer system in real time and accurately simulate the longitudinal and lateral test conditions of the test vehicle. It can also collect vehicle motion parameters such as speed and acceleration in real time and transmit them to the host computer system.
[0070] like Figure 2 As shown, the test bench system 107 is installed in the pit, with the upper end of the test bench system 107 at the same level as the ground 104. The system can adjust its working state in real time according to the instructions of the host computer system 110 and the actual situation of the vehicle's movement. While accurately simulating the vehicle's motion conditions, it also collects the vehicle's motion state parameters. The function of the test bench system 107 is to replace the road surface. For example, when a vehicle is accelerating in a straight line, the test bench system 107 can simulate the resistance of the vehicle's straight-line acceleration, achieving the effect that the wheels are rotating while the body position does not move. The data collected by the test bench system 107 is used to plan the vehicle's motion trajectory through a map and positioning simulation system.
[0071] The test bench control system includes an industrial computer 108, a signal receiving / transmitting board, and a test bench control program, which can receive signals from a host computer, feedback control the test bench to simulate the longitudinal motion condition of the vehicle, and feedback control the test bench to simulate the lateral motion condition of the vehicle.
[0072] The longitudinal motion simulation system can simulate the longitudinal motion resistance of the vehicle and provide the vehicle with close to real longitudinal driving conditions by using the wheel speed and torque as feedback signals.
[0073] The lateral motion simulation system can simulate the lateral motion conditions of the vehicle. It uses the wheel angle and the lateral motion simulation system angle as feedback signals to provide the vehicle with a lateral driving condition close to the real one.
[0074] The test bench signal acquisition system can collect vehicle speed, acceleration, heading angle and other signals, and send the signals to the vehicle positioning simulator in real time.
[0075] like Figure 1 and Figure 2As shown, after receiving the signal from the host computer, the bench test system 107, the industrial computer 108 controls the longitudinal motion simulation system and the lateral motion simulation system respectively to provide the vehicle with a longitudinal and lateral driving condition close to the real one; at the same time, the speed, acceleration, and heading angle signals of the test vehicle 106 are collected in real time and sent to the vehicle positioning simulator 114.
[0076] The autonomous driving control system 115 includes a vehicle decision-making system. This system plans a target trajectory based on the vehicle's own state information, the map, and signals from the positioning simulation system 111 and the vehicle wireless communication system 121. This system then uploads the target trajectory to the host computer system and controls the vehicle chassis based on the target trajectory.
[0077] The host computer system is used to control the bench test system and to display the traffic scene, motion trajectory, and target trajectory in a timeline sequence.
[0078] like Figure 1 and Figure 2 As shown, the host computer system 110 controls the test bench system, collects and processes signals from the map and positioning simulation system, collects and processes signals from the vehicle wireless communication system, and collects and processes test result data. It includes a control program, a signal acquisition program, a data processing program, and a scene restoration program. It can control the test bench system, collect and process test scene data, collect vehicle positioning signals, collect and process test vehicle target and actual trajectory data, evaluate the driving performance of the autonomous driving system, and generate animations of the spatial relationships between the map, scene, obstacles, and the vehicle, and transmit them to a projection display device in a timed sequence.
[0079] like Figure 1 and Figure 2 As shown, the control program is used by the upper computer to control the bench test system. According to the requirements of the test conditions, the bench test system 107 is controlled and monitored in real time through the time axis and the feedback information of the bench test system 107; then, the signal acquisition program collects scene data and the target trajectory of the vehicle, and associates the vehicle positioning data, target obstacle data, and vehicle target trajectory data in the order of the time axis; the signal data processing program calculates the actual motion trajectory of the vehicle and associates the actual trajectory data with the data in the above-mentioned control program; at the same time, the overlap between the actual trajectory and the target trajectory is calculated to confirm whether the vehicle is traveling according to the target trajectory; the signal data processing program calculates the distance between the actual estimate and the target obstacle to confirm whether the vehicle collides with the obstacle; finally, the scene restoration program displays the calculation results including the obstacle, target trajectory, and actual trajectory in the order of the time axis and projects them on the screen 103.
[0080] The test bench system 107 collects the current test bench longitudinal state value and uploads it to the host computer system 110. The automatic driving control system 115 uploads the target motion trajectory (including the vehicle speed at the next moment) to the host computer system 110. The host computer system 110 calculates the longitudinal simulation control compensation of the test bench system 107 based on the current longitudinal simulation state value of the test bench system 107 and the vehicle speed value at the next moment.
[0081] The test bench system 107 collects the current test bench lateral state value and uploads it to the host computer system 110. The automatic driving control system 115 uploads the target motion trajectory (including the vehicle's wheel yaw angle at the next moment) to the host computer system 110. The host computer system 110 calculates the test bench system's lateral simulation control compensation based on the test bench system 107's current lateral simulation state value and the vehicle's wheel yaw angle at the next moment.
[0082] At the next moment, the host computer system 110 sends the longitudinal and lateral simulation control compensation values to the bench test system 107. After receiving the signal, the bench test system 107 adjusts the working state of the actuator, thereby achieving accurate simulation of the vehicle motion condition.
[0083] like Figure 1 and Figure 2 As shown, the projection display device includes a projector bracket 101, a projector 102, and a screen 103. The screen displays animations and evaluation results generated by the host computer system in real time. Projector 102 is bolted to the ground 104 and fixed to the center of the crossbeam of projector bracket 101. The data input cable of projector 102 is connected to the host computer system 110. Screen 103 is installed directly in front of the test vehicle 106 to display the test data results.
[0084] This embodiment provides a full-vehicle autonomous vehicle testing system consisting of a map and positioning simulation system, a vehicle wireless communication system, a test bench system, a host computer system, and a projection display device. This system establishes a four-in-one closed-loop system consisting of a perception simulation system, an autonomous vehicle system, a test bench system, and a host computer system. This system enables high-level full-vehicle autonomous vehicle bench testing with high test accuracy, effectively addressing challenges inherent in real-world vehicle testing, including spatial limitations, omnidirectional environmental perception, and vehicle dynamics.
[0085] This embodiment provides a whole-vehicle testing system for autonomous vehicles. This system simulates motion conditions through a bench testing system, simulates the relative positional relationship between the vehicle and the road through a map and positioning simulation system, and reproduces environmental signals of actual traffic scenes through a vehicle wireless communication system, thereby achieving whole-vehicle testing of the vehicle. Moreover, compared with existing bench testing methods using videos and images, the method of calculating the relative positional relationship between the vehicle and the road, extracting environmental signals based on actual traffic scenes, and reproducing them can better ensure the reliability of test results.
[0086] Example 2
[0087] A second object of the present invention is to provide a method for testing a whole vehicle of an autonomous driving vehicle.
[0088] This embodiment provides a method for testing an autonomous vehicle, comprising: reproducing environmental signals extracted from actual traffic scenarios using a signal generator and transmitting the signals to the vehicle; obtaining the vehicle's position coordinates using a vehicle positioning simulator, and combining this with a map system to obtain the relative position relationship between the vehicle and the road, and transmitting the obtained coordinates to the vehicle, so that the vehicle's autonomous driving system plans a motion trajectory based on the reproduced traffic scenario information; and starting a test system to simulate motion conditions for the vehicle and collect the vehicle's motion state parameters.
[0089] like Figure 3 As shown, this embodiment provides a method for testing an autonomous vehicle, which specifically includes the following steps:
[0090] Step 1: Test preparation, including selection and editing of target test scenarios, startup and warm-up of the bench test system 107, accurate positioning of the vehicle, and vehicle fixing;
[0091] Step 2: Start the test system equipment, power on and initialize the host computer system 110, vehicle positioning simulator 114, map and positioning simulation system 111, and signal generator one by one;
[0092] Step 3: Start the test. The positioning signal and scene signal begin to communicate with the test vehicle, and the test vehicle enters the autonomous driving system.
[0093] Specifically, the test begins with the signal generator generating a signal that communicates via the format converter to the vehicle wireless communication device 112 . The map and positioning simulation system 111 transmits the vehicle positioning information to the automatic driving system 115 of the test vehicle 106 . The test vehicle 106 enters the automatic driving mode and begins the automatic driving function test.
[0094] Step 4: During the test process, the console test system and the test vehicle 106 automatically adjust the driving state while the host computer system 110 collects and processes the test data and evaluates and displays the test results;
[0095] Step 5: After the test is completed, the vehicle exits the autonomous driving system 115, the test data is saved, and all devices are restored to their initial states.
[0096] Step 1 includes the following steps:
[0097] Step 11: Collect scenes, select and process typical scenes;
[0098] Specifically, the test scene is captured by a video recording device, and then the ideal test scene is selected and the scene video is cropped;
[0099] Step 12: Extract scene targets and eliminate useless targets, and sort the targets by time;
[0100] Specifically, the targets in the target scene are screened, including pedestrians, vehicles, infrastructure, and roads, and useless targets such as manhole covers and garbage on the road are eliminated. The targets are numbered and different signals are sorted in chronological order.
[0101] Step 13: The bench test system 107 is powered on, initialized, preheated before the test bench experiment, and checked whether the feedback data of the test bench is correct;
[0102] Step 14: The test vehicle arrives at the designated location, adjusts its posture and fixes itself;
[0103] Specifically, the test vehicle 106 is driven onto the test bench system 107 , the vehicle direction and body are adjusted so that the axle and the axis of the test bench system 107 are in the same vertical plane, and then the gear is switched to neutral and the idling state is maintained.
[0104] Step 2 includes the following steps:
[0105] Step 21: Initialize the host computer system 110, power on the host computer system 110, and initialize the four internal subroutines (control program, data acquisition program, data processing program, and scene restoration program);
[0106] Step 22: Initializing the vehicle positioning simulator 114. After the vehicle positioning simulator 114 is powered on, the initial speed, acceleration, and heading angle of the test vehicle 106 are defined, and the initial position coordinates of the initial test vehicle 106 are given;
[0107] Step 23: After the map and positioning simulation system 111 is initialized, the vehicle positioning simulator 114 sends the vehicle's initial position coordinates to the map system 120. The map and positioning simulation system 111 finds the vehicle's position on the map and sends a signal to the autonomous driving system 115.
[0108] Step 24: Signal generator initialization: the pedestrian signal generator 116 , vehicle signal generator 117 , infrastructure signal generator 118 , and road signal generator 119 are powered on one by one, and the signal chain is paused at time 0 (initial state).
[0109] Step 3 includes the following steps:
[0110] Step 31: Send the target signals to the signal format converter one by one, following the relative distance priority and two-level priority, and then the format converter converts the target signal format into the CAN communication format;
[0111] Step 32: The vehicle wireless communication system 121 starts communicating, and the four port signals are communicated with the vehicle side one by one simultaneously, realizing the information exchange between pedestrian signals, surrounding vehicles, roads, infrastructure and the autonomous driving system 115;
[0112] Step 33: The map and positioning simulation system 111 collects the test bench feedback signals (test vehicle motion data), including the heading angle, velocity, and acceleration of the test vehicle 106. The vehicle positioning simulator 114 calculates the vehicle coordinates and positions them on the map. The vehicle position coordinates are packaged together with the velocity, acceleration, and heading angle signals and sent to the autonomous driving system 115.
[0113] Step 34 : The test vehicle 106 turns on the automatic driving function, enters the initial driving state, and starts automatic driving on the bench test system 107 .
[0114] Step 4 includes the following tasks, which are carried out simultaneously:
[0115] 1. The test vehicle 106 automatically adjusts its driving state to avoid collisions by steering, accelerating, decelerating, and other actions based on the scene and obstacle location;
[0116] 2. The host computer system 110 receives feedback signals from the test bench system 107, the vehicle's target trajectory status, and the vehicle's target traffic environment signal. Based on these three signals, the host computer controls the test bench system 107 through a control program and collects scene data, positioning data, target trajectory, and actual trajectory through a data acquisition program.
[0117] 3. The data processing program constructs a new dataset by chronologically combining the scene data, positioning data, and target trajectory data. The actual trajectory is compared with the target trajectory to evaluate the accuracy of trajectory tracking. The actual trajectory is compared with the positions of pedestrians and vehicles in the scene to assess the likelihood of collision.
[0118] 4. The scene restoration program automatically generates an animation in chronological order based on the data processing results (scene data, positioning data, target trajectory data, actual trajectory data) and displays it on the screen 103 through a projection display device, while also displaying the trajectory tracking reliability assessment results and the collision possibility assessment results.
[0119] Step 5 includes the following steps:
[0120] Step 51: The test vehicle 106 exits the automatic driving system 115 and switches to an idle state.
[0121] Step 52: The bench test system 107 stops working and returns to an initial state;
[0122] Step 53: Save the test data, and shut down the vehicle wireless communication system 121, the map and positioning simulation system 111, and the host computer system 110;
[0123] Step 54: The vehicle leaves the test bench system 107, and all devices in the test system return to their initial states.
[0124] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.
Claims
1. A self-driving car whole vehicle testing system, characterized in that: include: The vehicle wireless communication system is used to reproduce the environmental signals extracted from the actual traffic scene using a signal generator and send them to the vehicle so that the vehicle's automatic driving system can plan the movement trajectory; A map and positioning simulation system is used to receive motion state parameters, obtain the position coordinates of the vehicle through a vehicle positioning simulator, and combine with the map system to obtain the relative position relationship between the vehicle and the road, and send it to the vehicle so that the vehicle's automatic driving system can plan the motion trajectory; The bench test system is used to simulate the motion conditions of the vehicle and collect the vehicle's motion state parameters; The vehicle wireless communication system is used to uniformly arrange the reproduced environmental signals through a signal format converter, and send the reproduced environmental signals to the vehicle in chronological order; divide the sensed signals into four categories: pedestrian-side signals, vehicle-side signals, infrastructure-side signals, and road-side signals, and simulate and generate signals through four signal generators at the pedestrian-side, vehicle-side, infrastructure-side, and road-side ends and send the signals; The priority of pedestrian signals, vehicle signals, infrastructure signals and road signals decreases in order; The map and positioning simulation system compares the vehicle coordinates and the road coordinates, calculates the relative position, obtains the relative position relationship between the vehicle and the road, and sends it to the automatic driving system. The automatic driving system will make decisions and plan the movement trajectory of the vehicle according to the vehicle's position information; The signal data processing program calculates the actual motion trajectory of the vehicle and associates the actual trajectory data with the data in the control program; at the same time, it calculates the overlap between the actual trajectory and the target trajectory to confirm whether the vehicle is moving along the target trajectory; The bench test system collects the current bench longitudinal state value and uploads it to the host computer system; The automatic driving control system uploads the target motion trajectory to the host computer system, including the vehicle speed at the next moment; the host computer system calculates the longitudinal simulation control compensation amount of the bench test system according to the longitudinal simulation state value of the bench test system at the current moment and the speed value of the vehicle at the next moment; The bench test system collects the lateral state value of the bench test system at the current moment and uploads it to the host computer system; the automatic driving control system uploads the target motion trajectory to the host computer system, including the wheel yaw angle of the vehicle at the next moment; the host computer system calculates the lateral simulation control compensation amount of the bench test system based on the lateral simulation state value of the bench test system at the current moment and the wheel yaw angle of the vehicle at the next moment.
2. The automatic driving vehicle whole vehicle testing system as claimed in claim 1, characterized in that: It also includes the host computer system; The host computer system is used to control the bench test system.
3. The automatic driving vehicle whole vehicle testing system as claimed in claim 2, characterized in that: The host computer system is also used to display the target trajectory, the traffic scene and the motion trajectory in the order of the time axis.
4. The automatic driving vehicle whole vehicle testing system as claimed in claim 1, characterized in that: The pedestrian signal includes the pedestrian's position, travel direction and speed; Alternatively, the vehicle signal includes the position, speed, acceleration and heading angle of the environment vehicle; Alternatively, the infrastructure signals include traffic signs, traffic markings and traffic lights; Alternatively, the road signal includes road curvature and road slope.
5. The automatic driving vehicle whole vehicle testing system as claimed in claim 1, characterized in that: The map system is a map constructed based on actual traffic scenarios. The coverage of the map is the area where the actual traffic scenarios are located, and the physical objects in the map are represented by coordinates.
6. A method for testing a whole vehicle of an autonomous driving vehicle, characterized in that: include: The environmental signals extracted from the actual traffic scene are reproduced using a signal generator and then sent to the vehicle; The vehicle location coordinates are obtained through the vehicle positioning simulator, and combined with the map system, the relative position relationship between the vehicle and the road is obtained and sent to the vehicle so that the vehicle's automatic driving system can plan the movement trajectory in combination with the reproduced traffic scene; Start the test system to simulate the motion condition of the vehicle and collect the motion state parameters of the vehicle; The vehicle wireless communication system is used to uniformly arrange the reproduced environmental signals through a signal format converter and send the reproduced environmental signals to the vehicle in chronological order; the perception signals are divided into four categories: pedestrian-side signals, vehicle-side signals, infrastructure-side signals, and road-side signals, and the signals are simulated and sent through four signal generators at the pedestrian-side, vehicle-side, infrastructure-side, and road-side ends; The priority of pedestrian signals, vehicle signals, infrastructure signals and road signals decreases in order; The map and positioning simulation system compares the vehicle coordinates with the road coordinates, calculates the relative position, obtains the relative position relationship between the vehicle and the road, and sends it to the autonomous driving system. The autonomous driving system will make decisions and plan the vehicle's movement trajectory based on the vehicle's position information. The signal data processing program calculates the actual motion trajectory of the vehicle and associates the actual trajectory data with the data in the control program; at the same time, it calculates the overlap between the actual trajectory and the target trajectory to confirm whether the vehicle is moving along the target trajectory; The bench test system collects the current bench longitudinal state value and uploads it to the host computer system; The automatic driving control system uploads the target motion trajectory to the host computer system, including the vehicle speed at the next moment; the host computer system calculates the longitudinal simulation control compensation amount of the bench test system according to the longitudinal simulation state value of the bench test system at the current moment and the speed value of the vehicle at the next moment; The bench test system collects the lateral state value of the bench test system at the current moment and uploads it to the host computer system; the automatic driving control system uploads the target motion trajectory to the host computer system, including the wheel yaw angle of the vehicle at the next moment; the host computer system calculates the lateral simulation control compensation amount of the bench test system based on the lateral simulation state value of the bench test system at the current moment and the wheel yaw angle of the vehicle at the next moment.
Citation Information
Patent Citations
Automatic driving performance testing method and automatic driving performance testing device
CN109187048A
Test method, device and system for automatic driving vehicle
CN110160804A
Device and method for testing emergency braking function of autonomous vehicle
CN112649208A
Automatic driving test system and method, electronic equipment and storage medium
CN115203062A
Simulation test method for autonomous driving vehicle, computer equipment and medium
US20210394787A1
