A method, system and device for automating driving simulation test

Abstract

The present invention provides an automatic driving simulation test method, system and equipment, comprising the following steps: obtaining traffic participant information, wherein the traffic participant information includes the trajectory points of the traffic participants; deleting the parking trajectory points of the vehicle in the trajectory points of the traffic participants; supplementing the regular new trajectory points to replace the parking trajectory points of the vehicle according to the continuous driving point supplement algorithm to obtain new traffic participant information; and performing automatic driving simulation test according to the new traffic participant information. The present application can reproduce real, continuous and complex test scenarios, can automatically and quickly process scenario data, improve the efficiency of scenario reproduction, can well deal with the problem of scenario truncation, and improve the safety factor of personnel and property; in the simulation, the traffic participants at the current moment are output and screened according to the scene playback time to improve the simulation efficiency; the present application can modify and simplify the model according to the usage requirements to improve the simulation efficiency while ensuring good visualization effects.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving simulation test method, system and equipment. Background Art

[0002] In recent years, autonomous driving technology has been widely used in various types of vehicles, so the maturity of related functions has also become a focus of user attention. This demand mainly depends on extensive and large-scale testing and verification of the driving safety of autonomous driving vehicles.

[0003] At present, the testing methods for autonomous driving vehicles are divided into simulation testing and real vehicle testing. The test scenarios used in both are derived from standardized scenarios designed by laws and regulations, which are somewhat different from actual driving scenarios. At present, in order to meet the needs of real, efficient and safe autonomous driving testing, a virtual-real combination testing method has been proposed. This method uses a technical solution for autonomous driving simulation testing based on virtual scenarios reproduced by real vehicle data, which can greatly enrich the scenario library while improving test efficiency and safety factors.

[0004] At present, scene reproduction data mostly comes from vehicle-side and road-side sensors or is completely dependent on vehicle-side sensors. On the one hand, this data sampling method significantly increases equipment costs while failing to guarantee the accuracy of reproduction. On the other hand, it also causes too many traffic participants to participate in the scene, increases non-critical factors, and causes a sharp increase in computing costs, which is not conducive to autonomous driving simulation testing.

[0005] In low-cost scene reproduction methods, regulatory scenarios are often used as test cases, and actual scenarios are artificially built and then virtualized for reproduction. Although this method solves the problem of over-idealization of traffic participant motion data to a certain extent, it only reproduces the scene in a fragmented manner, and then obtains the conditions required for vehicle driving in non-continuous scenarios through autonomous driving simulation tests, without considering the problem of scene truncation, such as halfway parking scenarios; parking scenarios will cause the vehicle posture sensor to output irregular posture points, resulting in frequent switching of the heading angle or parking position of the vehicle at the parking point during autonomous driving, and the safety factor of people and property in this process is low. Summary of the invention

[0006] The present application provides an autonomous driving simulation test method, system and equipment that can address scene truncation problems and improve the safety factor of personnel and property.

[0007] The first aspect of the present application provides an autonomous driving simulation test method;

[0008] An automatic driving simulation test method comprises the following steps:

[0009] Acquiring traffic participant information, wherein the traffic participant information includes trajectory points of the traffic participant;

[0010] Deleting the parking trajectory point of the vehicle from the trajectory points of the traffic participants;

[0011] According to the continuous driving point supplement algorithm, new regular trajectory points are added to replace the parking trajectory points of the vehicle to obtain new traffic participant information;

[0012] Conduct autonomous driving simulation tests based on new traffic participant information.

[0013] The above scheme solves the problem of irregular output posture points caused by parking by deleting the parking trajectory points of the vehicle and supplementing new trajectory points with regular patterns. It corrects the automatic driving path, makes frequent switching of heading angles or parking positions less likely to occur, and improves the safety factor of people and property during the automatic driving process.

[0014] Preferably, the continuous driving point supplement algorithm is:

[0015]

[0016] Traffic participant information includes: Respectively represent the sampling time before the vehicle stops and the sampling time after the vehicle starts, T C represents the time of the new trajectory point, X A , Y A , Yaw A 、V A Represents T A The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time. B , Y B , Yaw B 、V B Represents T B The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time. C , Y C , Yaw C 、V C Represents T C The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time, Vx A , Vy A Represents T A The two component velocities of the vehicle on the X-axis and Y-axis on the horizontal plane.

[0017] Preferably, before deleting the parking trajectory point of the vehicle in the trajectory points of the traffic participants, the method includes:

[0018] The vehicle motion trajectory points in the traffic participant information are filtered.

[0019] Preferably, after obtaining the new traffic participant information, the following steps are included:

[0020] Identify static traffic participant information and dynamic traffic participant information in new traffic participant information;

[0021] According to the dynamic algorithm, the static traffic participant information is dynamically processed to obtain the static traffic participant trajectory;

[0022] Interpolating the dynamic traffic participant trajectory points in the dynamic traffic participant information to obtain the dynamic traffic participant trajectory;

[0023] According to the static traffic participant trajectory and the dynamic traffic participant trajectory, a traffic participant trajectory file is obtained for autonomous driving simulation testing.

[0024] Preferably, the dynamic algorithm is:

[0025]

[0026] Among them, static traffic participant information includes X D , Y D , Yaw D 、V D , X E , Y E , Yaw E 、V E , X D , Y D , Yaw D 、V D Represents the X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the static traffic participant when entering the collected range. E , Y E , Yaw E 、V E Represents the X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the static traffic participant when it leaves the collected range, Vx D , Vy D Represents the velocity component of a static traffic participant when entering the scene, and Δt1 is the sampling step.

[0027] Preferably, the new traffic participant information includes traffic participant outline information, and the traffic participant outline information includes several attribute objects. Before performing the autonomous driving simulation test based on the new traffic participant information, the following steps are included:

[0028] Delete specific attribute objects in the traffic participant outline information and modify the content of the attribute objects according to preset modification rules.

[0029] Preferably, an autonomous driving simulation test is performed based on the new traffic participant information, including:

[0030] Establish a time-stamped reference traffic participant list based on the new traffic participant information;

[0031] The timestamp reference traffic participant list, the preset system simulation time, and the preset scenario model are input into the preset simulation test system to obtain an autonomous driving simulation scenario. The autonomous driving simulation scenario has several traffic participants, and the coordinates of the traffic participants in the autonomous driving simulation scenario are converted into world coordinates for autonomous driving simulation testing.

[0032] Preferably, after inputting the timestamp reference traffic participant list, system simulation time, and preset scenario model into a preset simulation test system to obtain an autonomous driving simulation scenario, the following steps are included:

[0033] Filter out traffic participants outside the preset driving focus area in the autonomous driving simulation scenario.

[0034] In a second aspect of the present application, an autonomous driving simulation test system is provided.

[0035] An automatic driving simulation test system, comprising:

[0036] A traffic participant information acquisition module, used to acquire traffic participant information, wherein the traffic participant information includes trajectory points of the traffic participants;

[0037] A self-parking trajectory point deletion module, used to delete the self-parking trajectory point in the trajectory points of traffic participants;

[0038] A point supplement module is used to supplement regular new trajectory points to replace the parking trajectory points of the vehicle according to the continuous driving point supplement algorithm to obtain new traffic participant information;

[0039] In a third aspect of the present application, an electronic device is provided.

[0040] An electronic device includes a processor, a memory and a transceiver, wherein the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs an autonomous driving simulation test method.

[0041] In summary, this application includes the following beneficial technical effects:

[0042] 1. This application can reproduce real, continuous, and complex test scenarios, can automatically and quickly process scenario data, improve the efficiency of scenario reproduction, and can well deal with the problem of scenario truncation, thereby improving the safety factor of personnel and property;

[0043] 2. This application can output and filter the current traffic participants according to the scene playback time in the simulation to improve the simulation efficiency;

[0044] 3. This application can create, modify and simplify the 3D obstacle model according to usage requirements, thereby improving simulation efficiency while ensuring good visualization effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flowchart of an automatic driving simulation test method according to an embodiment of the present application;

[0046] Figure 2 is a schematic diagram of the parking trajectory points of the vehicle after the parking trajectory points of the vehicle are replaced by new trajectory points with regularity according to the continuous driving point supplementation algorithm in an embodiment of the present application;

[0047] Figure 3 This is a schematic diagram of the classification of static traffic participant information and dynamic traffic participant information in an embodiment of the present application;

[0048] Figure 4 It is a schematic diagram of the trajectory points of the dynamic processing of static traffic participants in an embodiment of the present application.

[0049] Figure 5 It is a schematic diagram of processing dynamic traffic participant trajectory points in an embodiment of the present application.

[0050] Figure 6 is a top view schematic diagram of the 3D outline of a traffic participant before and after the content of the attribute object is modified in an embodiment of the present application;

[0051] Figure 7 It is a schematic diagram of the autonomous driving simulation test of an embodiment of the present application.

[0052] Figure 8 It is a schematic diagram of the driving attention area according to an embodiment of the present application.

[0053] Fig. 9 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0055] In the description of the embodiments of the present application, words such as "illustrative", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "illustrative", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "illustrative", "for example" or "for example" is intended to present related concepts in a concrete way.

[0056] In the description of the embodiments of the present application, the term "and / or" is only a kind of association relationship describing the associated objects, indicating that there may be three kinds of relationships, for example, A and / or B, which can represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" can explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0057] Scenario:

[0058] The existing Chinese invention application "Road environment scene simulation method, electronic equipment and medium integrating vehicle, road and cloud" (Announcement No.: CN116244902A) provides a road environment scene simulation method integrating vehicle, road and cloud. The scene data of this invention comes from road-side and vehicle-side sensors, which are transmitted and loaded into the server via cloud communication tools. This method can generate a real-time simulation scene model for autonomous driving simulation testing.

[0059] The Chinese invention patent "Simulation scene moving obstacle control method, system, medium and equipment" (Announcement No.: CN116224833A) provides a simulation scene moving obstacle control method. The scene reproduction data in this invention comes from vehicle-mounted sensors, road-end traffic lights, etc. When the reproduced scene does not match the actual scene, the invention adopts simulation control to solve possible traffic accidents.

[0060] The Chinese invention application "A method for assisting autonomous driving simulation testing through data mining" (Announcement No.: CN116256985A) provides a method for building an autonomous driving simulation library through data classification, interception and combination, three-dimensional dynamic visualization and other means. The focus of this invention is to obtain high-frequency simulation data through simulation testing in the scene library to improve the efficiency of information mining.

[0061] The Chinese invention application "Scene reconstruction method and device for road test data" (Announcement No.: CN115984788A) proposes a scene reproduction method based on the data collected by the vehicle-mounted sensor and the lane line perception results as a reference to finally obtain the obstacle position information. This method is mainly used for scenes built in closed test sites and is highly dependent on the perception performance of the sensor.

[0062] The above-mentioned patents have certain shortcomings, specifically high cost, low scene complexity, lack of continuity and low efficiency.

[0063] Therefore, the present application provides an autonomous driving simulation test method based on real vehicle environment data, which aims to carry out autonomous driving simulation testing based on real vehicle data with low cost, high efficiency, high reliability and wide application, and meet the technical requirements of high authenticity and good reliability of autonomous driving simulation testing.

[0064] Glossary:

[0065] Gaussian smoothing: A smoothing technique commonly used in image processing and signal processing. It reduces noise in an image or signal while preserving edge information by applying a Gaussian function as a weight coefficient to the data.

[0066] Pose sensor: A device that measures and reports the position and orientation of an object in space. These sensors are widely used in robotics, augmented reality, virtual reality, drones, navigation systems, medical devices, motion tracking, and industrial automation.

[0067] Scene building scripts: Commonly used in movies, games, virtual reality (VR) and augmented reality (AR) to create virtual or physical environments. These scripts define the layout, appearance, behavior, and interaction of the scene.

[0068] Simulation Model: A mathematical or computational model used to simulate a real-world system or process. They are widely used in engineering, science, business, and many other fields to predict system behavior, test hypotheses, optimize designs, conduct risk assessments, and support decision making. Simulation models can be either quantitative or qualitative, depending on the complexity of the system they represent and the accuracy required.

[0069] Interpolation algorithm: A mathematical method used to estimate unknown data points between known data points. Interpolation algorithms are very important in signal processing, image processing, computer graphics, numerical analysis, and other scientific computing fields.

[0070] Perception algorithms: Perception algorithms are algorithms used to simulate or enhance a machine’s ability to perceive its environment, particularly in the fields of artificial intelligence, robotics, computer vision, and self-driving cars. These algorithms are designed to enable machines to understand the environment they are in and react accordingly.

[0071] Reference Figure 1 , an automatic driving simulation test method, comprising the following steps:

[0072] S1: Real vehicle environment data collection and preprocessing: Obtain smooth traffic participant motion information through filtering and position supplementation;

[0073] Specifically: real vehicle environment data refers to the real driving scene data collected by the vehicle-mounted sensor, which is processed by the perception algorithm and stored in the host computer. Traffic participant information is included in the real vehicle environment data, and the real vehicle environment data includes the movement information of the vehicle and at least one traffic participant; the traffic participant information is extracted by the intelligent terminal after being collected; then the intelligent terminal filters the movement trajectory points of the vehicle among the traffic participants to solve the positioning error problem caused by temporary parking of the vehicle or low speed. The vehicle movement data includes the X-axis coordinate position, Y-axis coordinate position, speed and heading angle of the traffic participant's vehicle, and the filtering method includes but is not limited to Gaussian smoothing.

[0074] In order to solve the scene truncation problem such as trajectory lag caused by temporary parking of the vehicle, this application takes the following steps:

[0075] S11: deleting the parking trajectory point of the vehicle from the trajectory points of the traffic participants; wherein the traffic participant information includes the trajectory points of the traffic participants;

[0076] Specifically: by slicing the scene, taking the parking state of the vehicle as a reference, the entire scene is sliced ​​and processed, the parking process is extracted and deleted, it can be understood that the trajectory points of traffic participants are points that appear continuously in the real vehicle environment scene, the real vehicle environment scene can be regarded as a video, the trajectory points of traffic participants can be understood as a number of points representing traffic participants that appear in each video frame, and the parking process is based on the parking state of the vehicle, deleting the trajectory points of traffic participants within 0.1 seconds before parking and 0.1 seconds after starting; it should be noted that because the posture sensor in the car will swing due to inertia when parking, resulting in confusion of trajectory points, the purpose of this operation is to remove these confused trajectory points.

[0077] S12: According to the continuous driving point supplement algorithm, new regular trajectory points are supplemented to replace the parking trajectory points of the vehicle, and new traffic participant information is obtained;

[0078] Specific: Refer to Figure 1 and Figure 2, using the method of filling in points, new trajectory points are added in the real vehicle environment scene where the trajectory points of traffic participants are deleted;

[0079] The algorithm for filling in points during continuous driving is:

[0080]

[0081] Among them, traffic participant information includes X A , Y A , Yaw A 、V A , X B , Y B , Yaw B 、V B , T A , T B , T A , T B The time of the first undeleted track point before the vehicle stops and the time of the first undeleted track point after the vehicle starts, T C represents the time of the new trajectory point, X A , Y A , Yaw A 、V A Represents T A The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time. B , Y B , Yaw B 、V B In order of arrangement, they represent T B The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time. C , Y C , Yaw C 、V C In order of arrangement, they represent T C The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time, Vx A , Vy A Represents T A The two component velocities of the vehicle on the X-axis and Y-axis on the horizontal plane. A , T B The actual time is 0.1 second before the vehicle stops and 0.1 second after the vehicle starts.

[0082] The new trajectory point is based on the vehicle position at the end and the beginning of the two adjacent scenes. The relative heading angle, relative speed, position and scene duration of the vehicle between the two positions are calculated. The scene duration is calculated by adding and subtracting 0.1s from the end and the beginning of the two adjacent scenes. After the deleted parking trajectory point of the vehicle is replaced by the new trajectory point, the new traffic participant information is obtained.

[0083] S2: Traffic participant information sorting: Automatically process scene data to obtain the attributes and trajectory files of all traffic participants to ensure high efficiency, complete scenes, and normal attributes;

[0084] Reference Figure 1 and Figure 3 , specifically including:

[0085] S21: Identify static traffic participant information and dynamic traffic participant information in the new traffic participant information; it should be noted that the classification principle of the attributes of the traffic participant is to compare the motion attribute of the traffic participant with the target historical tracking data length. The target historical tracking data length can be understood as the number of frames of the traffic scene screen in which the traffic participant appears. If the motion attribute is static and the target historical tracking data length is less than the data length threshold, the traffic participant is static; if the motion attribute is dynamic and the target historical tracking data length is not less than the data length threshold, the traffic participant is dynamic; traffic participants other than the above two cases are also processed as dynamic;

[0086] S22: According to the dynamic algorithm, the static traffic participant information is dynamically processed to obtain the static traffic participant trajectory;

[0087] Reference Figure 1 and Figure 4 , where the dynamic algorithm is:

[0088]

[0089] Among them, static traffic participant information includes X D , Y D , Yaw D 、V D , X E , Y E , Yaw E 、V E ;X D , Y D , Yaw D 、V D In order of arrangement, they represent the X-axis coordinate position, Y-axis coordinate position, heading angle and speed when the static traffic participant appears. E , Y E , YawE 、V E In order of arrangement, they represent the X-axis coordinate position, Y-axis coordinate position, heading angle and speed when the static traffic participant disappears. D , Vy D represents the velocity component of the static traffic participant when entering the scene, Δt1 is the sampling step, and the time when the static traffic participant appears is T D , the time when the static traffic participant disappears is T E .

[0090] It should be noted that the purpose of this step is to sense the same static traffic participant on the roadside during the driving process of the vehicle. Because of the image acquisition method used, when the orientation of both parties changes, the position of the sensed same static traffic participant will also change frequently, resulting in a large number of calculation examples being wasted during calculation, which is inconsistent with the actual scene. Therefore, a dynamic algorithm is set up so that T D -T E During the scene, the heading angle of the same static traffic participant is kept unchanged. There is no need to calculate the heading angle of the static traffic participant again. It is only necessary to calculate the relative position of the static traffic participant and the vehicle, which saves computing power.

[0091] S23: interpolating the dynamic traffic participant trajectory points in the dynamic traffic participant information to obtain the dynamic traffic participant trajectory;

[0092] Reference Figure 1 and Figure 5 Specifically, considering that the ego vehicle will exist as a reference object for judging the scene position after the scene is reproduced, the processing of the trajectory points of dynamic traffic participants can be divided into the processing of the trajectory points of the ego vehicle and the processing of the trajectory points of other dynamic traffic participants. Among them, the purpose of interpolation processing is to output the trajectory points of dynamic traffic participants at a fixed sampling time to obtain new dynamic traffic participant trajectories. This method effectively solves the problem of dynamic traffic participant delay caused by uneven sampling of the original scene data and the mismatch between the true value time of the scene and the simulation time. The interpolation algorithms of interpolation processing include but are not limited to nearest neighbor interpolation, linear interpolation, bilinear interpolation, high-order interpolation, etc.;

[0093] S24: obtaining a traffic participant trajectory file according to the static traffic participant trajectory and the dynamic traffic participant trajectory for use as an autonomous driving simulation test;

[0094] Specifically, the static and dynamic traffic participant trajectories are processed to obtain complete static and dynamic traffic participant trajectory files. Furthermore, by connecting the saved dynamic and static data groups with the same attributes, the trajectory file names can be modified in sequence according to the principle of dynamic data first and static data later, and finally a complete, unique, and continuous traffic participant trajectory file can be generated, which can be added to the new traffic participant information.

[0095] Among them, in actual operation, the entire S2 traffic participant information sorting process can obtain the dynamic traffic participant list DyObs and the static traffic participant list StaObs with information such as traffic participant category, outline size, scene time, trajectory, heading angle, etc. The static traffic participant list StaObs after dynamic processing is saved in the format of StaObsTraj_i.csv file, where i represents the i-th static traffic participant. The DyObs list after dynamic traffic participant processing is saved as DyObsTraj_i.csv and egoTraj.csv files, where the egoTraj.csv file has been interpolated. Finally, according to the type of all obstacles, they can be stored in four trajectory folders, namely non-motor vehicles, pedestrians, passenger cars and commercial vehicles, and the traffic participants in the folder are arranged in the principle of dynamic data first and static data later, and finally generate four complete, unique and continuous traffic participant trajectory folders: BicycleCSV, PedestrianCSV, VehicleCSV, TruckCSV.

[0096] S3: Traffic participant appearance design: Build and simplify various types of traffic participant appearance models, enrich the scene building model library;

[0097] Specifically, the new traffic participant information includes traffic participant outline information, and the traffic participant outline information includes a number of attribute objects. The specific attribute objects in the traffic participant outline information are deleted, and the content of the attribute objects is modified according to the preset modification rules to further modify the new traffic participant information. Specifically, the following steps are included:

[0098] S31: Design and simplify the networking of various traffic participants to reduce simulation complexity;

[0099] Furthermore, simplifying various types of traffic participants is a method of reducing the number of contour attributes of various types of traffic obstacles to reduce the simulation complexity and improve the scene playback rate. Among them, the material attributes of traffic participants include but are not limited to the coordinates of traffic participant contour points and surface structure matrices, and the types of traffic participants that can be processed include but are not limited to non-motor vehicles, pedestrians, commercial vehicles and passenger cars.

[0100] S32: Design and simplify 3D models of various motor vehicles and non-motor vehicles, enrich the scene model library, and reduce rendering costs;

[0101] Furthermore, by simplifying and modifying the 3D outline models of various types of motor vehicles and non-motor vehicles, the purpose of enriching the types of 3D outline models and reducing scene rendering is achieved. Among them, the simplified 3D outline model object is the specific attribute object deleted in the outline information of the traffic participant, including but not limited to material, internal structure and density, and the modified 3D outline model object is the content of the attribute object, including but not limited to external structure and color. The preset modification rules can be to binarize the color content in the content of the attribute object, delete the external structure of the traffic participant that has no effect on the vehicle or replace it with a simple shape, etc.

[0102] Reference Figure 6 The traffic participant is a certain city bus, and the 3D outline of the traffic participant before and after the modification of the attribute object is shown in the top view. The top is the bus shape before the modification, including the air-conditioning shell, the top escape door, the front shape and other structures. The bottom of the figure is the bus shape after the modification, which removes the air-conditioning shell, the top escape door, the front shape and other structures. At the same time, the outline color can be randomly defined, and the coverage area is shown as the grid shadow in the figure.

[0103] Reference Figure 1 and Figure 7 , based on the new traffic participant information, an autonomous driving simulation test is conducted. This step includes:

[0104] S4: Scenario construction: Design all traffic participants to enter and exit the scenario in sequence according to the simulation time, and design the attributes of traffic participants;

[0105] Specifically include:

[0106] S41: extracting and saving the time and outline dimensions of all traffic participants entering and exiting the scene from the traffic participant information, and defining 3D model categories corresponding to different outline dimensions;

[0107] It should be noted that the purpose of defining the 3D model categories corresponding to different outline sizes mentioned in this step is to restore the appearance of some traffic participants in the real scene as much as possible, and these traffic participants include but are not limited to commercial vehicles and passenger cars;

[0108] S42: Generate scene building script;

[0109] It should be noted that the scene building script contains the attributes of all traffic participants, including but not limited to the ID, name, traffic participant trajectory file path, 3D model category, etc. of each traffic participant. The attributes of traffic participants can be obtained through the new traffic participant information;

[0110] In addition, the scene building script can also automatically and randomly modify the color, name and other information of traffic participants according to needs, and ultimately achieve the automatic generation of scenes with large data volume, high complexity and good visual effects.

[0111] Afterwards, the map of the road test area and the scene building script corresponding to the map of the road test area are loaded, and finally saved as a scene file that can be used in the autonomous driving simulation platform;

[0112] Among them, in the actual operation process, the scene building first extracts the time of entering and exiting the scene and the outline size from the dynamic traffic participant list DyObs and the static traffic participant list StaObs and saves them, and then assigns different 3D outline models to traffic participants according to different sizes. For example, passenger cars can be divided into small cars, medium-sized cars, large cars, mini vans, etc., commercial vehicles can be divided into semi-trailers, buses, ambulances, road vehicles, etc., and pedestrians can be divided into adults, children, etc. The scene building script needs to define the ID, name, trajectory file path, 3D model, etc. of each traffic participant, where the trajectory file refers to BicycleCSV, PedestrianCSV, VehicleCSV, TruckCSV, and the 3D model refers to the simplified and modified 3D outline model. After running the script, the traffic participant command statement that can be used in the RoadRunner Scenario Build API is generated. The map required in the scene is a high-precision map designed by the mapping software RoadRunner. Finally, loading the traffic participant command statement into the software can automatically load all traffic participant movement data, and save the file as a scene file XX.Scenario in the OpenScenario format. The map of the road test area is selected by selecting the perception scene data of a certain place within a certain time period in the vehicle-mounted industrial computer. The scene is usually a normal driving scene, including parking avoidance, emergency braking and other working conditions.

[0113] S5: Conduct autonomous driving simulation tests;

[0114] Specifically, a time-stamp reference traffic participant list is established in the simulation model according to the new traffic participant information, wherein the time-stamp reference traffic participant list includes but is not limited to the traffic participant ID, type, scene entry time and scene exit time, and the time-stamp reference traffic participant list can reflect the traffic participants appearing at each moment;

[0115] The timestamp reference traffic participant list, the preset system simulation time, and the preset scenario model are input into the preset simulation test system to obtain the autonomous driving simulation scenario, which includes the movement information of several traffic participants at the current simulation moment.

[0116] Furthermore, in actual operation, the autonomous driving simulation will simultaneously load the scenario file XX.Scenario, the system simulation time module, and the traffic participant list ObsList, where ObsList includes the ID, type, material, scene entry time, and scene exit time of all traffic participants.

[0117] Reference Figure 8 , filter out the traffic participants outside the preset driving attention area in the autonomous driving simulation scene, and remove the traffic participants outside the driving attention area, where the driving attention area is: extending L from the center of the vehicle forward F Distance, extending from the center of the vehicle to the rear R Distance, extending from the center of the vehicle to both sides L S The area obtained by distance; where L F , L R and L S The value of is set according to the actual situation. For example, in this embodiment, L F =200m, L R =30m, L S =15m, and finally convert the coordinates of traffic participants in the driving focus area into world coordinates for autonomous driving simulation testing. The conversion reference point of the world coordinate conversion is the origin of the high-precision map, and finally packaged and saved in csv file format.

[0118] It should also be noted that the application scenarios of this application include but are not limited to open roads, closed parks, test roads, etc.; the types of vehicle-mounted sensors include but are not limited to laser radar, millimeter wave radar, ultrasonic radar, monocular camera, binocular camera, etc.; the self-driving cars mentioned in this application include but are not limited to passenger cars, commercial vehicles, engineering vehicles, unmanned vehicles, etc. The high-precision map formats used in this application include but are not limited to OpenDrive, OpenStreetMap, HERE HD Live Map, etc.; the scene file formats include but are not limited to OpenScenario; the scene design or simulation software includes but is not limited to CARLA, PreScan, RoadRunner, Matlab / Simulink, etc.; the 3D outline modification software includes but is not limited to Solidworks, ProE / Creo, SketchUp, AutoCAD, etc.

[0119] The present application also provides an autonomous driving simulation test system.

[0120] An automatic driving simulation test system comprises:

[0121] A traffic participant information acquisition module, used to acquire traffic participant information, wherein the traffic participant information includes trajectory points of the traffic participants;

[0122] A self-parking trajectory point deletion module, used to delete the self-parking trajectory point in the trajectory points of traffic participants;

[0123] A point supplement module is used to supplement regular new trajectory points to replace the parking trajectory points of the vehicle according to the continuous driving point supplement algorithm to obtain new traffic participant information;

[0124] The simulation test module is used to conduct autonomous driving simulation tests based on new traffic participant information.

[0125] Reference Fig. 9 , provides a schematic diagram of the structure of an electronic device for an embodiment of the present application. The electronic device may include: at least one processor, at least one network interface, a user interface, a memory, and at least one communication bus.

[0126] The communication bus is used to realize the connection and communication between these components.

[0127] The user interface may include a display screen (Display) and a camera (Camera), and the optional user interface may also include a standard wired interface and a wireless interface.

[0128] The network interface may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0129] Among them, the processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts within the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor, but implemented separately through a chip.

[0130] Among them, the memory may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory includes a non-transitory computer-readable storage medium. The memory can be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory may also be optionally at least one storage device located away from the aforementioned processor. The memory as a computer storage medium may include an operating system, a network communication module, a user interface module, and an automatic driving simulation test method application.

[0131] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0132] In an electronic device, the user interface is mainly used to provide an input interface for the user and obtain data input by the user; and the processor can be used to call an application stored in the memory that has an autonomous driving simulation test method. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0133] The "unit" and "module" in this specification refer to software and / or hardware that can independently complete a specific function or cooperate with other components to complete a specific function, where the hardware may be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0134] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0135] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program code.

[0140] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0141] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An automatic driving simulation test method, characterized in that: The following steps are involved: Acquiring traffic participant information, wherein the traffic participant information includes trajectory points of the traffic participant; Deleting the parking trajectory point of the vehicle from the trajectory points of the traffic participants; According to the continuous driving point supplement algorithm, new regular trajectory points are added to replace the parking trajectory points of the vehicle to obtain new traffic participant information; Conduct autonomous driving simulation tests based on new traffic participant information; The new track points supplemented according to the continuous driving point supplement algorithm replace the parking track points of the vehicle, and the new traffic participant information is obtained, including: By using the method of filling in points, new trajectory points are added in the real vehicle environment scene where the trajectory points of traffic participants are deleted; The continuous driving point filling algorithm is: Traffic participant information includes: X A , Y A , Yaw A 、V A , X B , Y B , Yaw B 、V B , T A , T B , T A , T B They represent the time of the first undeleted track point before the ego vehicle stops and the time of the first undeleted track point after the ego vehicle starts, respectively. C represents the time of the new trajectory point, X A , Y A , Yaw A 、V A Represents T A The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time. B , Y B , Yaw B 、V B Represents T B The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time. C , Y C , Yaw C 、V C Represents T C The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time, Vx A , Vy A Represents T A The two component velocities of the vehicle on the X-axis and Y-axis on the horizontal plane; The new trajectory point is based on the vehicle position at the end and the beginning of the two adjacent scenes. The relative heading angle, relative speed, position and scene duration of the vehicle between the two positions are calculated. The scene duration is calculated by adding and subtracting 0.1s from the end and the beginning of the two adjacent scenes. After the deleted parking trajectory point of the vehicle is replaced by the new trajectory point, the new traffic participant information is obtained. The autonomous driving simulation test is performed according to the new traffic participant information, including: Establish a time-stamped reference traffic participant list based on the new traffic participant information; The timestamp reference traffic participant list, the preset system simulation time, and the preset scenario model are input into the preset simulation test system to obtain an autonomous driving simulation scenario. The autonomous driving simulation scenario has several traffic participants, and the coordinates of the traffic participants in the autonomous driving simulation scenario are converted into world coordinates for autonomous driving simulation testing.

2. The automatic driving simulation test method according to claim 1, characterized in that: Before deleting the own vehicle's parking trajectory points from the traffic participant's trajectory points, include: The vehicle motion trajectory points in the traffic participant information are filtered.

3. The automatic driving simulation test method according to claim 1, characterized in that: After obtaining the information of new traffic participants, including: Identify static traffic participant information and dynamic traffic participant information in new traffic participant information; According to the dynamic algorithm, the static traffic participant information is dynamically processed to obtain the static traffic participant trajectory; Interpolating the dynamic traffic participant trajectory points in the dynamic traffic participant information to obtain the dynamic traffic participant trajectory; According to the static traffic participant trajectory and the dynamic traffic participant trajectory, a traffic participant trajectory file is obtained for autonomous driving simulation testing.

4. The automatic driving simulation test method according to claim 3, characterized in that: The dynamic algorithm is: Among them, static traffic participant information includes X D , Y D , Yaw D 、V D , X E , Y E , Yaw E 、V E , X D , Y D , Yaw D 、V D Represents the X-axis coordinate position, Y-axis coordinate position, heading angle and speed when a static traffic participant appears. E , Y E , Yaw E 、V E Represents the X-axis coordinate position, Y-axis coordinate position, heading angle and speed when the static traffic participant disappears, Vx D , Vy D Represents the velocity component of a static traffic participant when entering the scene, and Δt1 is the sampling step.

5. The automatic driving simulation test method according to claim 1, characterized in that: The new traffic participant information includes the traffic participant outline information, which includes several attribute objects. Before the autonomous driving simulation test is performed based on the new traffic participant information, the following are included: Delete specific attribute objects in the traffic participant outline information and modify the content of the attribute objects according to preset modification rules.

6. The automatic driving simulation test method according to claim 1, characterized in that: After inputting the timestamp reference traffic participant list, system simulation time, and preset scenario model into the preset simulation test system to obtain the autonomous driving simulation scenario, it includes: Filter out traffic participants outside the preset driving focus area in the autonomous driving simulation scenario.

7. An automatic driving simulation test system, characterized in that: include: A traffic participant information acquisition module, used to acquire traffic participant information, wherein the traffic participant information includes trajectory points of the traffic participants; A self-parking trajectory point deletion module, used to delete the self-parking trajectory point in the trajectory points of traffic participants; A point supplement module is used to supplement regular new trajectory points to replace the parking trajectory points of the vehicle according to the continuous driving point supplement algorithm to obtain new traffic participant information; A simulation test module, used to conduct autonomous driving simulation tests based on new traffic participant information; The new track points supplemented according to the continuous driving point supplement algorithm replace the parking track points of the vehicle, and the new traffic participant information is obtained, including: By using the method of filling in points, new trajectory points are added in the real vehicle environment scene where the trajectory points of traffic participants are deleted; The continuous driving point filling algorithm is: Traffic participant information includes: X A , Y A , Yaw A 、V A , X B , Y B , Yaw B 、V B , T A , T B , T A , T B They represent the time of the first undeleted track point before the ego vehicle stops and the time of the first undeleted track point after the ego vehicle starts, respectively. C represents the time of the new trajectory point, X A , Y A , Yaw A 、V A Represents T A The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time. B , Y B , Yaw B 、V B Represents T B The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time. C , Y C , Yaw C 、V C Represents T C The X-axis coordinate position, Y-axis coordinate position, heading angle and speed of the vehicle at this time, Vx A , Vy A Represents T A The two component velocities of the vehicle on the X-axis and Y-axis on the horizontal plane; The new trajectory point is based on the vehicle position at the end and the beginning of the two adjacent scenes. The relative heading angle, relative speed, position and scene duration of the vehicle between the two positions are calculated. The scene duration is calculated by adding and subtracting 0.1s from the end and the beginning of the two adjacent scenes. After the deleted parking trajectory point of the vehicle is replaced by the new trajectory point, the new traffic participant information is obtained. The autonomous driving simulation test is performed according to the new traffic participant information, including: Establish a time-stamped reference traffic participant list based on the new traffic participant information; The timestamp reference traffic participant list, the preset system simulation time, and the preset scenario model are input into the preset simulation test system to obtain an autonomous driving simulation scenario. The autonomous driving simulation scenario has several traffic participants, and the coordinates of the traffic participants in the autonomous driving simulation scenario are converted into world coordinates for autonomous driving simulation testing.

8. An electronic device, characterized in that It includes a processor, a memory and a transceiver, wherein the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any method as claimed in claims 1-6.

Images