Simulation test task processing method and device

Abstract

The embodiment of the invention relates to a simulation test task processing method and device. The method comprises the following steps: receiving a test road / time period / mode; if the mode is the first mode, segmenting the test time period into a plurality of continuous intersection fragmentation time periods and creating an intersection test scene based on real road network data, and if the mode is the second mode, creating the intersection test scene according to the road network data of the maximum pressure time period of each intersection in the test time period; the scene simulator executes a simulation test according to each intersection test scene and outputs a corresponding test recording scene; and forming a corresponding simulation test record by each test recording scene, the corresponding self-vehicle object index and the intersection test scene, and forming a simulation test task report by all the simulation test records and storing the simulation test task report. According to the invention, the test complexity and comprehensiveness of the automatic driving algorithm can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for processing simulation test tasks. Background Art

[0002] The prediction-planning-decision-control algorithm of the autonomous driving system (referred to as the autonomous driving algorithm) is used to predict the motion trajectories of other traffic participants around the vehicle based on perception information, and to plan the vehicle's driving trajectory based on the prediction results and high-precision maps. It also makes decisions on the vehicle's traffic behavior type (such as going straight, changing lanes, overtaking, and parking) based on the planned trajectory and traffic light status, and predicts the vehicle's lateral / longitudinal driving control parameters based on the decision results and the vehicle's motion status to output corresponding vehicle driving control instructions (such as steering wheel angle, throttle opening and closing, brake opening and closing, gear position, etc.).

[0003] Simulation testing is a new approach to testing autonomous driving algorithms. It can replicate scenarios, improve testing efficiency, and reduce road testing costs. Currently, conventional simulation testing uses two types of raw data to construct scenarios: road data collected from the vehicle's perspective and manually designed simulated data. Both sources of data have shortcomings: 1) DRIVE data has limited scene coverage and high acquisition costs; 2) artificial data lacks fidelity and lacks generalizability. Testing autonomous driving algorithms based solely on these two types of data is neither complex nor comprehensive enough.

[0004] Traffic intersections are complex traffic scenarios, requiring reliable and voluminous traffic network data. Building simulation test scenarios based on real-world intersection data would significantly improve the complexity and comprehensiveness of algorithm testing. Testing autonomous driving algorithms using simulated intersection scenarios constructed using real-world network data is precisely the technical challenge addressed by this invention. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, device, electronic device and computer-readable storage medium for processing simulation test tasks in response to the defects of the prior art. The present invention provides two real intersection scene creation methods to enhance the complexity and diversity of the scene: based on time continuity, continuous scene creation is performed for all intersections of any test road, and based on the characteristics of traffic pressure test, pressure scene creation is performed for all intersections of any test road; and after completing the scene creation, simulation-test docking is achieved by connecting the self-vehicle algorithm interface to the scene simulator; and three types of self-vehicle selection rules (random, long-range, and efficient) are provided in each scene test to improve the comprehensiveness of the test; and the scene simulator simulates the automatic driving algorithm based on the currently loaded intersection test scene and the connected self-vehicle algorithm interface, and records the real-time scene of the test during the test. Based on the present invention, the authenticity, complexity and diversity of the test scene can be enhanced, the types and scope of the test vehicles can be expanded, and the comprehensiveness of the test can be improved. The complexity and comprehensiveness of the algorithm test can be effectively improved through the present invention.

[0006] To achieve the above-mentioned object, a first aspect of an embodiment of the present invention provides a method for processing a simulation test task, the method comprising:

[0007] Receiving test road R test , test period T test and test mode; and the autonomous driving algorithm interface to be tested is used as the corresponding self-vehicle algorithm interface; the test road R test is a real traffic network road; the test period T test The timing period is within 24 hours; the test mode includes the first and second modes;

[0008] Identify the test mode; if the test mode is the first mode, then test The real road network data will be the test period T test Divide into multiple continuous intersection segments, and create a test simulation scene for each intersection of the current road in its corresponding intersection segment based on the real road network data to obtain a corresponding intersection test scene; if the test mode is the second mode, then according to the test road R test The real road network data for each intersection of the current road in the test period T test Creating a test simulation scenario on the maximum pressure period within the intersection to obtain the corresponding intersection test scenario;

[0009] Each of the intersection test scenes is used as a corresponding current intersection test scene; and based on a preset self-vehicle selection rule, a car object is selected from the current intersection test scene as the corresponding self-vehicle object; and the current intersection test scene is imported into a preset scene simulator for initialization; and the self-vehicle algorithm interface is connected to the scene simulator to take over the driving control of the self-vehicle object; and the scene simulator performs a simulation test according to the loaded current intersection test scene and the connected self-vehicle algorithm interface and outputs a corresponding test recording scene; the self-vehicle selection rule includes at least random, long-range and efficient;

[0010] The object index of the self-vehicle object in each of the test recording scenes is used as the corresponding self-vehicle object index; and each of the test recording scenes and its corresponding self-vehicle object index and the intersection test scene form a corresponding simulation test record; and all the obtained simulation test records form a corresponding simulation test task report and save it.

[0011] Preferably, the input data of the self-vehicle algorithm interface includes a simulation timestamp, a traffic participant data set, a signal light data set, a self-vehicle state data, a self-vehicle target position and high-precision map data, and the output is a vehicle driving control instruction; the traffic participant data set is composed of one or more traffic participant data, and the traffic participant data includes participant type, participant coordinates, participant speed, participant heading angle, and participant acceleration; the signal light data set is composed of one or more signal light data, and the signal light data includes signal light coordinates and light status, and the light status includes red light, green light, yellow light, and flashing yellow light; the self-vehicle state data includes self-vehicle coordinates, self-vehicle heading angle, self-vehicle speed, and self-vehicle acceleration; the self-vehicle target position is a target position coordinate; the instruction parameters of the vehicle driving control instruction include at least steering wheel angle, throttle opening degree, brake opening degree, and gear position;

[0012] The test road R test Including multiple intersections C i and multiple road segments j , 1≤intersection index i≤N, 1≤road section index j≤N-1, N is the total number of intersections; the test road R test The starting and ending positions are intersection C i＝1 、C i＝N , the road section r j For intersection C i＝j 、C i＝j+1 connecting sections between

[0013] The test period T test The start and end time are recorded as t start , t end ;

[0014] The test period T test The test duration L test =t end -t start ;

[0015] Each of the intersections C i The corresponding intersection segment period is recorded as TA i ,TA i ∈T test ; The first and second adjacent intersection segments TA i TA i+1 The end time of the first period is aligned with the start time of the second period; the intersection segmentation period TA i The start and end time are recorded as ta s,i 、ta e,i ,ta s,i＝1 =t start ,ta s,i+1 =ta e,i ,ta e,i＝N =t end ;

[0016] Each of the intersections C i The corresponding maximum pressure period is recorded as TB i , TB i ∈T test The maximum pressure period TB i The start and end time are recorded as tb s,i 、tb e,i ;

[0017] Each of the intersections C i The corresponding intersection test scene and the test recording scene are recorded as corresponding The test recording scenario With the intersection test scenario One-to-one correspondence; the intersection test scenario The test recording scenario The data encapsulation format of the scene files complies with the data encapsulation format of the OpenSCENARIO standard;

[0018] The intersection test scenario The data content includes at least high-precision intersection maps and scene object sets The high-precision intersection map The map elements at least include traffic signs / markings / line elements, road edge line elements, dangerous area elements, obstacle elements, and signal light elements of all roads at the current intersection; the scene object set Including multiple scene objects 1≤object index o≤N D,i , N D,i is the total number of objects in the i-th intersection test scene; the scene objects Include object types Object state trajectory t is the timestamp; the object type At least including cars, motorcycles, bicycles, pedestrians, and traffic lights; state trajectories of all the above objects The trajectory sampling frequency 1 / △t remains consistent; the object type When it is a car, motorcycle, bicycle, or pedestrian, the object status At least including coordinates, orientation angle, velocity and acceleration; the object type When it is a signal light, the object state Including the coordinates of the traffic light and the status of the traffic light, wherein the status of the traffic light includes at least red light, green light, yellow light, and flashing yellow light;

[0019] The test recording scenario The data content includes at least high-precision intersection maps and recording object sets The high-precision intersection map and the corresponding high-precision map of the intersection Remain consistent; the recording object set Including N D,i Recording objects The recording object With the scene object One-to-one correspondence; the recording object Include object types and object state trajectory The object type The object type corresponding to Keep consistent; the object state trajectory The object state trajectory corresponding to timestamp alignment; the object type When it is a car, motorcycle, bicycle, or pedestrian, the object status At least including coordinates, orientation angle, velocity and acceleration; the object type When it is a signal light, the object state Including the coordinates of the traffic light and the status of the traffic light, wherein the status of the traffic light includes at least red light, green light, yellow light, and flashing yellow light;

[0020] The scene simulator is a type of scene simulation tool that meets the OpenSCENARIO standard.

[0021] Preferably, the test road R test The real road network data will be the test period T test Divide into multiple continuous intersection segments, including:

[0022] Based on the test road R test The real road network data of each road section r within the preset specified time period j During the test period T test The average speed within the area is calculated to obtain the corresponding average speed And each of the road segments r j The length of the straight road is recorded as the corresponding length d j ; and based on each of the lengths d j and the corresponding average vehicle speed Calculate the corresponding average travel time And for N-1 average travel time △t j The sum of the corresponding total duration l is calculated sum The designated period includes at least a designated single day or multiple consecutive days, a designated single week or multiple consecutive weeks, a designated single month or multiple consecutive months, a designated single quarter or multiple consecutive quarters, or a designated single year or multiple consecutive years;

[0023] And the total duration l sum The test duration L test Identify; if the total duration l sum Less than the test duration L test , then set the corresponding tail intersection segment duration △l end =L test -l sum If the total duration is l sum Greater than or equal to the test duration L test , then choose any one of the average travel time △l j As the corresponding incremental time △l add , and for the test period T test The end time t end Delay the latest test time L test Meet L test =l sum +△l add , and set the corresponding tail intersection segment duration △l end =△l add ;

[0024] And based on the obtained N-1 average travel time △l j, the end intersection segmentation duration △l end And the test period T test The starting time t start and the end time t end , for N intersection segment time periods TA i The starting time ta s,i and the end time ta e,i To set it up:

[0025] ta s,i＝1 =t start ,ta e,i＝1 =ta s,i＝1 +Δl j＝i ,

[0026] ta s,1<i≤N-1 =ta e,i-1 ,ta e,1<i≤N-1 =ta s,1<i≤N-1 +Δl j＝i ,

[0027] ta s,i＝N =ta e,i＝N-1 ,ta s,i＝N =ta s,i＝N +Δl end =t end .

[0028] Preferably, the step of creating a test simulation scenario for each intersection of the current road in its corresponding intersection segment time period based on the real road network data to obtain a corresponding intersection test scenario specifically includes:

[0029] Based on the test road R test The real road network data of the current road is used for the test period T every day within the preset specified period. test The total number of vehicle flows on the data points is counted to obtain a corresponding first total number, and the single-day road network data corresponding to the largest first total number is used as the road network data for that day;

[0030] and the road network data of the day and the intersection C i The corresponding regional road network data is used as the corresponding intersection area data; and each of the intersection area data is used in the corresponding intersection segmentation period TA i The road network data within the time period is used as the corresponding intersection time period data;

[0031] And each of the intersections C i The corresponding high-precision map is used as the corresponding high-precision map of the intersection And each of the intersections C iThe corresponding intersection period data is used as the corresponding current intersection period data; and the motion state trajectory of each car, motorcycle, bicycle or pedestrian in the current intersection period data is sampled according to the preset trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results The coordinates and light-changing trajectories of each signal light in the current intersection period data are sampled according to the trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results. And all the scene objects obtained Composed of the corresponding scene object set And the obtained high-precision map of the intersection and the scene object set Composition of the corresponding intersection test scene

[0032] Preferably, the test road R test The real road network data for each intersection of the current road in the test period T test The test simulation scenario is created on the maximum pressure period within the intersection to obtain the corresponding intersection test scenario, specifically including:

[0033] Each of the intersections C i As the corresponding current intersection; and based on the test road R test The real road network data of the current intersection is used to calculate the test period T of each day in the preset specified period. test The maximum total number of traffic participants in the range is counted to obtain the corresponding second total number; and the maximum second total number is recorded as the total number y max,i ; and the total y max,i The corresponding single-day road network data is related to the current intersection and the test period T test The corresponding regional time period road network data is used as the corresponding current intersection data; and the total y max,i During the test period T test The corresponding time in is taken as the corresponding maximum pressure period TB i The starting time tb s,i , and the test period T test The end time t end As the current maximum pressure period TB i The end time tb e,i ; And the current intersection data meets the current maximum pressure period TB i The road network data is used as the corresponding intersection pressure period data;

[0034] And each of the intersections C iThe corresponding high-precision map is used as the corresponding high-precision map of the intersection And each of the intersections C i The corresponding intersection pressure period data is used as the corresponding current pressure period data; and the motion state trajectory of each car, motorcycle, bicycle or pedestrian in the current pressure period data is sampled according to the preset trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results The coordinates and light-changing trajectory of each signal light in the current pressure period data are sampled according to the trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results. And all the scene objects obtained Composed of the corresponding scene object set And the obtained high-precision map of the intersection and the scene object set Composition of the corresponding intersection test scene

[0035] Preferably, the selecting a car object as the corresponding ego vehicle object from the current intersection test scene based on a preset ego vehicle selection rule specifically includes:

[0036] The scene object set of the current intersection test scene Object type described in The scene object for the car Cluster them into a class to form a corresponding car object set; and identify the self-car selection rule; if the self-car selection rule is random, randomly select one of the scene objects from the car object set As the corresponding vehicle object; if the vehicle selection rule is long range, the vehicle object is concentrated on the object state trajectory The longest scene object As the corresponding vehicle object; if the vehicle selection rule is efficient, the vehicle object is concentrated on the object state trajectory The average speed of the fastest scene object As the corresponding vehicle object.

[0037] Preferably, the step of importing the current intersection test scene into a preset scene simulator for initialization specifically includes:

[0038] The scene simulator is based on the high-precision intersection map of the current intersection test scene currently imported Perform two-dimensional or three-dimensional simulation world construction; and according to the scene object set of the current intersection test scene Each of the scene objects A one-to-one simulation object is constructed in the current simulation world; and the simulation period of the current simulation world is configured based on the time span of the current intersection test scene; and the recording sampling frequency and single-step simulation frequency of the current simulation world are configured based on the trajectory sampling frequency of the current intersection test scene, the recording sampling frequency is consistent with the current trajectory sampling frequency, and the single-step simulation frequency is an integer multiple of the current trajectory sampling frequency; and the simulation objects of the object type of automobile, motorcycle, bicycle or pedestrian in the current simulation world are regarded as participant objects, and corresponding traffic participant behavior models, motion control models and dynamic models are assigned to each of the participant objects; and the simulation objects of the object type of traffic lights are regarded as traffic light objects, and corresponding traffic light control models are assigned to each of the traffic light objects; and based on the object state trajectory corresponding to each of the simulation objects The first of the objects in the state Set the initial simulation state of the current simulation object and set the second to last object state of each simulation object A multi-stage simulation target as the current simulation object;

[0039] The traffic participant behavior model is used to make decisions on the traffic behavior type of the current participant object at a future simulation moment based on the current simulation target and current historical trajectory of each participant object at the current simulation moment, the historical trajectories of other surrounding participant objects at the current simulation moment, and the historical trajectories of surrounding signal light objects at the current simulation moment; the traffic behavior types include at least slowing down and going straight, accelerating and going straight, going straight at a constant speed, changing lanes to the left, changing lanes to the right, overtaking, turning around, avoiding to the left, avoiding to the right, sudden braking, and stopping;

[0040] The motion control model is used to predict the motion control parameters of the current participant at a future simulation moment based on the current simulation target, current traffic behavior type, and current historical trajectory of each participant object at the current simulation moment; the motion control parameters include at least a steering force parameter, a longitudinal acceleration force parameter, and a longitudinal deceleration force parameter;

[0041] The dynamic model is used to predict the simulation state of the current participant at a future simulation moment based on the current simulation target, current simulation state and current motion control parameters of each participant object at the current simulation moment; the simulation state includes at least coordinates, orientation angle, velocity and acceleration;

[0042] The traffic light control model is used to predict the traffic light state of the current traffic light object at a future simulation moment based on the current simulation target and the current historical trajectory of each traffic light object at the current simulation moment.

[0043] Preferably, the step of connecting the vehicle algorithm interface to the scenario simulator to take over the driving control of the vehicle object specifically includes:

[0044] The simulation object corresponding to the ego vehicle object in the current simulation world of the scenario simulator is used as the corresponding current takeover object; the traffic participant behavior model and the motion control model assigned by the scenario simulator to the current takeover object are canceled; the input end of the dynamic model assigned by the scenario simulator to the current takeover object is connected to the output end of the ego vehicle algorithm interface; and a corresponding simulation data output interface is set in the scenario simulator to connect to the input end of the ego vehicle algorithm interface;

[0045] Among them, the simulation data output interface is used to use the real-time simulation state of the current takeover object in the current simulation world as the corresponding self-vehicle state data at each simulation moment in the simulation process; and use the real-time simulation state of each of the other participant objects around the current takeover object as the corresponding traffic participant data, and all the traffic participant data obtained are used to form a corresponding traffic participant data set; and use the coordinates and real-time traffic light state of each of the traffic light objects in the current simulation world as the corresponding traffic light coordinates and the lighting state to form a corresponding traffic light data set, and all the traffic light data obtained are used to form a corresponding traffic light data set; and use the coordinate position of the nearest next-stage simulation target in the multi-stage simulation target corresponding to the current takeover object as the corresponding self-vehicle target position; and use the high-precision map of the intersection corresponding to the current simulation world as the corresponding high-precision map data; and the current simulation moment is used as the corresponding simulation timestamp; and the obtained simulation timestamp, the traffic participant data set, the traffic light data set, the vehicle status data, the vehicle target position and the high-precision map data are output as the output data of this time to the vehicle algorithm interface.

[0046] Preferably, the scenario simulator performs a simulation test according to the loaded current intersection test scenario and the connected vehicle algorithm interface and outputs a corresponding test recording scenario, specifically including:

[0047] During the simulation process, the scene simulator simulates the motion trajectory of the current participant object by the traffic participant behavior model, the motion control model and the dynamic model of each participant object; and simulates the light change trajectory of the current signal light object by the signal light control model of each signal light object; and simulates the motion trajectory of the ego vehicle by the simulation data output interface, the ego vehicle algorithm interface and the dynamic model corresponding to the ego vehicle object; and based on the recording sampling frequency, the real-time simulation state of each simulation object is collected at each recording sampling point to generate the corresponding object state At the end of the simulation, the high-precision map of the intersection of the current intersection test scene is As the corresponding high-precision map of the intersection And the object type corresponding to each simulation object As a corresponding object type And all the object states corresponding to each of the simulation objects Form a corresponding state trajectory of the object And the object type corresponding to each simulation object and the object state trajectory Form a corresponding recording object And by all the recording objects Composed of the corresponding recording object set And the high-precision map of the intersection and the recording object set Composition of the corresponding test recording scene And output.

[0048] A second aspect of the embodiments of the present invention provides a device for implementing the method for processing the simulation test task described in the first aspect, the device comprising: a test task receiving module, a road intersection scene preparation module, a simulation test module, and a task report storage module;

[0049] The test task receiving module is used to receive the test road R test , test period T test and test mode; and the autonomous driving algorithm interface to be tested is used as the corresponding self-vehicle algorithm interface; the test road R test is a real traffic network road; the test period T test The timing period is within 24 hours; the test mode includes the first and second modes;

[0050] The intersection scene preparation module is used to identify the test mode; if the test mode is the first mode, then according to the test road R test The real road network data will be the test period T test Divide into multiple continuous intersection segments, and create a test simulation scene for each intersection of the current road in its corresponding intersection segment based on the real road network data to obtain a corresponding intersection test scene; if the test mode is the second mode, then according to the test road R test The real road network data for each intersection of the current road in the test period T test Creating a test simulation scenario on the maximum pressure period within the intersection to obtain the corresponding intersection test scenario;

[0051] The simulation test module is used to use each of the intersection test scenes as the corresponding current intersection test scene; and select a car object from the current intersection test scene as the corresponding self-vehicle object based on a preset self-vehicle selection rule; and import the current intersection test scene into a preset scene simulator for initialization; and connect the self-vehicle algorithm interface to the scene simulator to take over the driving control of the self-vehicle object; and the scene simulator performs a simulation test according to the loaded current intersection test scene and the connected self-vehicle algorithm interface and outputs a corresponding test recording scene; the self-vehicle selection rule includes at least random, long-range and efficient;

[0052] The task report saving module is used to use the object index of the self-vehicle object in each of the test recording scenes as the corresponding self-vehicle object index; and each of the test recording scenes and its corresponding self-vehicle object index and the intersection test scene form a corresponding simulation test record; and all the obtained simulation test records form a corresponding simulation test task report and save it.

[0053] A third aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0054] The processor is configured to be coupled to the memory, read and execute instructions in the memory, so as to implement the method steps described in the first aspect above;

[0055] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0056] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a computer, the computer executes the instructions of the method described in the first aspect above.

[0057] The embodiment of the present invention provides a method, device, electronic device and computer-readable storage medium for processing simulation test tasks. It can be seen from the above invention content that the embodiment of the present invention provides two real intersection scene creation methods to enhance the complexity and diversity of the scene: based on time continuity, continuous scene creation is performed for all intersections of any test road, and based on the characteristics of traffic pressure test, pressure scene creation is performed for all intersections of any test road; and after completing the scene creation, the simulation-test connection is achieved by connecting the self-vehicle algorithm interface to the scene simulator; and three types of self-vehicle selection rules (random, long-range, and efficient) are provided in each scene test to improve the comprehensiveness of the test; and the scene simulator simulates the automatic driving algorithm based on the currently loaded intersection test scene and through the connected self-vehicle algorithm interface, and records the real-time scene of the test during the test. The embodiment of the present invention enhances the authenticity, complexity and diversity of the test scene, expands the types and scope of test vehicles, and effectively improves the complexity and comprehensiveness of the algorithm test. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A schematic diagram of a method for processing a simulation test task provided in the first embodiment of the present invention;

[0059] Figure 2 Schematic diagram of test roads, intersections, and sections provided in Example 1 of the present invention;

[0060] Figure 3 A schematic diagram of the intersection segmentation time period provided in the first embodiment of the present invention;

[0061] Figure 4 A schematic diagram of the maximum pressure period provided in Example 1 of the present invention;

[0062] Figure 5 A module structure diagram of a device for processing simulation test tasks provided in the second embodiment of the present invention;

[0063] Figure 6 This is a structural diagram of an electronic device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0064] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the embodiments described herein are merely some, rather than all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0065] A method for processing a simulation test task is provided in a first embodiment of the present invention, such as Figure 1A method for processing a simulation test task provided in the first embodiment of the present invention is shown in a schematic diagram, which includes the following main steps:

[0066] Step 1: Receive the test road R test , test period T test and test mode; and use the autonomous driving algorithm interface to be tested as the corresponding vehicle algorithm interface.

[0067] Here, the test road R of the embodiment of the present invention test is a real traffic network road; the test road R test Including multiple intersections C i and multiple road segments j , 1≤intersection index i≤N, 1≤road section index j≤N-1, N is the total number of intersections; test road R test The starting and ending positions are intersection C i＝1 、C i＝N , road section r j For intersection C i＝j 、C i＝j+1 The connecting road between the test road R test 、Intersection C i and road section r j The subordinate and connection relationship, such as Figure 2 The test road, intersection and road section diagram provided in the first embodiment of the present invention are shown as follows. test The test period T is the timing period within 24 hours; test The start and end time are recorded as t start , t end ; Test period T test The test duration L test =t end -t start .

[0068] The test modes of the embodiments of the present invention include a first mode and a second mode. In the first mode, continuous scenarios are created for all intersections of any test road based on real road network data and in a temporal manner. In the second mode, stress scenarios are created for all intersections of any test road based on real road network data and in accordance with the characteristics of the traffic stress test. Real road network data is all-weather, all-section / intersection traffic data collected by roadside edge devices of a real traffic network, including at least the latest high-precision map of the current section / intersection, motion trajectory information of all traffic participants in the current section / intersection, light change trajectory information of all traffic lights in the current section / intersection, information on all construction / accident / hazardous areas in the current section / intersection, and so on.

[0069] The self-driving algorithm interface of the embodiment of the present invention is a docking interface for the autonomous driving algorithm / model / device / system of any car manufacturer. The input data of the self-driving algorithm interface includes a simulation timestamp, a traffic participant data set, a signal light data set, the self-driving vehicle status data, the self-driving vehicle target position and high-precision map data, and the output is a vehicle driving control instruction. Among them: 1) The traffic participant data set is composed of one or more traffic participant data, and the traffic participant data includes participant type, participant coordinates, participant speed, participant heading angle, and participant acceleration; 2) The signal light data set is composed of one or more signal light data, and the signal light data includes signal light coordinates and light status, and the light status includes red light, green light, yellow light, and flashing yellow light; 3) The self-driving vehicle status data includes self-driving vehicle coordinates, self-driving vehicle heading angle, self-driving vehicle speed, and self-driving vehicle acceleration; 4) The self-driving vehicle target position is a target position coordinate; 5) The instruction parameters of the vehicle driving control instruction include at least steering wheel angle, throttle opening, brake opening, and gear position.

[0070] Step 2: Identify the test mode; if the test mode is the first mode, then test The real road network data will be tested during the test period T test Divide into multiple continuous intersection segments, and create a test simulation scene for each intersection of the current road in its corresponding intersection segment based on the real road network data to obtain the corresponding intersection test scene; if the test mode is the second mode, then according to the test road R test The real road network data for each intersection of the current road in the test period T test A test simulation scenario is created on the maximum pressure period within the time period to obtain a corresponding intersection test scenario;

[0071] Specifically comprising: step 21, identifying the test pattern;

[0072] Step 22: If the test mode is the first mode, then according to the test road R test The real road network data will be tested during the test period T test Divide the time into multiple continuous intersection segments, and create a test simulation scenario for each intersection of the current road in its corresponding intersection segment based on the real road network data to obtain a corresponding intersection test scenario;

[0073] Here, each intersection C in the embodiment of the present invention i The corresponding intersection segment period is recorded as TA i ,TA i ∈T test ; The first and second adjacent intersection segments TA i TA i+1 The end time of the first period is aligned with the start time of the second period; the intersection segment period TA iThe start and end time are recorded as ta s,i 、ta e,i ,ta s,i＝1 =t start ,ta s,i+1 =ta e,i ,ta e,i＝N =t end ;like Figure 3 This is a schematic diagram of the intersection segmentation time period provided by the first embodiment of the present invention;

[0074] Each intersection C in the embodiment of the present invention i The corresponding intersection test scenario is recorded as Intersection test scenario The data encapsulation format meets the data encapsulation format of the OpenSCENARIO standard scene file; intersection test scene The data content includes at least high-precision intersection maps and scene object sets High-precision intersection map The map elements at least include traffic signs / markings / line elements, road edge line elements, dangerous area elements, obstacle elements, and signal light elements of all roads at the current intersection; the scene object set Including multiple scene objects 1≤object index o≤N D,i , N D,i is the total number of objects in the test scene of the i-th intersection; scene objects Include object types Object state trajectory t is the timestamp; object type At least including cars, motorcycles, bicycles, pedestrians, and traffic lights; all object state trajectories The trajectory sampling frequency 1 / △t remains consistent; object type When it is a car, motorcycle, bicycle, or pedestrian, the object status At least includes coordinates, orientation angle, velocity and acceleration; object type When it is a signal light, the object state Including traffic light coordinates and traffic light status, the traffic light status includes at least red light, green light, yellow light, and flashing yellow light;

[0075] The current step 22 specifically includes:

[0076] Step 221: According to the test road R test The real road network data will be tested during the test period T test Divide into multiple continuous intersection segments;

[0077] Specifically including: Step 2211, based on the test road R test The real road network data of each road section r within the preset specified time period j During the test period T test The average speed within the area is calculated to obtain the corresponding average speed And each road segment r j The length of the straight road is recorded as the corresponding length d j ; and based on the length d j and its corresponding average speed Calculate the corresponding average travel time And for N-1 average travel time △t j The sum of the corresponding total duration l is calculated sum ;

[0078] Here, the preset designated period mentioned in the embodiment of the present invention includes at least a designated single day or multiple consecutive days, a designated single week or multiple consecutive weeks, a designated single month or multiple consecutive months, a designated single quarter or multiple consecutive quarters, or a designated single year or multiple consecutive years;

[0079] Step 2212, and the total duration l sum and test duration L test Identify; if the total duration is l sum Less than the test duration L test , then set the corresponding tail intersection segment duration △l end =L test -l sum ; If the total duration is l sum Greater than or equal to the test duration L test , then choose any average travel time △l j As the corresponding incremental time △l add , and for the test period T test End time t end Delay the latest test time to L test Meet L test =l sum +△l add , and set the corresponding tail intersection segment duration △l end =△l add ;

[0080] Step 2213, based on the obtained N-1 average travel time △l j , the length of the segment at the end intersection △l end And the test period T test The starting time t start and end time t end , for N intersections, the time segment TAi The starting time ta s,i and end time ta e,i To set it up:

[0081] ta s,i＝1 =t start ,ta e,i＝1 =ta s,i＝1 +Δl j＝i ,

[0082] ta s,1<i≤N-1 =ta e,i-1 ,ta e,1<i≤N-1 =ta s,1<i≤N-1 +Δl j＝i ,

[0083] ta s,i＝N =ta e,i＝N-1 ,ta s,i＝N =ta s,i＝N +Δl end =t end ;

[0084] Step 222, based on the real road network data, a test simulation scenario is created for each intersection of the current road in its corresponding intersection segment time period to obtain a corresponding intersection test scenario;

[0085] Specifically including: Step 2221, based on the test road R test The real road network data of the current road is tested during the daily test period T within the preset specified period. test The total number of vehicle flows on the data is counted to obtain the corresponding first total number, and the single-day road network data corresponding to the largest first total number is used as the road network data for that day;

[0086] Step 2222, and compare the road network data of the day with the C of each intersection i The corresponding regional road network data is used as the corresponding intersection area data; and each intersection area data is divided into the corresponding intersection segment time period TA i The road network data within the time period is used as the corresponding intersection time period data;

[0087] Step 2223, and each intersection C i The corresponding high-precision map is used as the corresponding intersection high-precision map And each intersection C i The corresponding intersection period data is used as the corresponding current intersection period data; and the motion state trajectory of each car, motorcycle, bicycle or pedestrian in the current intersection period data is sampled according to the preset trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results The coordinates and light-changing trajectories of each signal light in the current intersection period data are sampled according to the trajectory sampling frequency, and the corresponding scene objects are constructed based on the sampling results. And all the scene objects obtained Composed of the corresponding scene object set And the obtained high-precision map of the intersection and scene object sets Composition of corresponding intersection test scenarios

[0088] Here, the preset trajectory sampling frequency is the object state trajectory The trajectory sampling frequency can be preset or dynamically configured based on application requirements;

[0089] Step 23: If the test mode is the second mode, then according to the test road R test The real road network data for each intersection of the current road in the test period T test A test simulation scenario is created on the maximum pressure period within the time period to obtain a corresponding intersection test scenario;

[0090] Among them, each intersection C i The corresponding maximum pressure period is recorded as TB i , TB i ∈T test ; Maximum pressure period TB i The start and end time are recorded as tb s,i 、tb e,i ;

[0091] Specifically including: Step 231, each intersection C i As the corresponding current intersection; and based on the test road R test The real road network data is used to test the current intersection during the daily test period T in the preset specified period. test The maximum total number of traffic participants in the total number is counted to obtain the corresponding second total number; and the maximum second total number is recorded as the total number y max,i ; and the total y max,i The corresponding single-day road network data is related to the current intersection and the test period T test The corresponding regional time period road network data is used as the corresponding current intersection data; and the total y max,i During the test period T test The corresponding time in is taken as the corresponding maximum pressure period TB i The starting time tb s,i , and set the test period T test End time t end As the current maximum pressure period TB i End time tb e,i; and the current intersection data that meets the current maximum pressure period TB i The road network data is used as the corresponding intersection pressure period data;

[0092] Here, the maximum pressure period TB i and the total y max,i and test period T test The relationship as Figure 4 This is a schematic diagram of the maximum pressure period provided by the first embodiment of the present invention;

[0093] Step 232, and each intersection C i The corresponding high-precision map is used as the corresponding intersection high-precision map And each intersection C i The corresponding intersection pressure period data is used as the corresponding current pressure period data; and the motion state trajectory of each car, motorcycle, bicycle or pedestrian in the current pressure period data is sampled according to the preset trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results The coordinates and light-changing trajectories of each signal light in the current pressure period data are sampled according to the trajectory sampling frequency, and the corresponding scene objects are constructed based on the sampling results. And all the scene objects obtained Composed of the corresponding scene object set And the obtained high-precision map of the intersection and scene object sets Composition of corresponding intersection test scenarios

[0094] Step 3: Use each intersection test scene as the corresponding current intersection test scene; select a car object from the current intersection test scene as the corresponding self-vehicle object based on the preset self-vehicle selection rule; import the current intersection test scene into the preset scene simulator for initialization; connect the self-vehicle algorithm interface to the scene simulator to take over the driving control of the self-vehicle object; and the scene simulator performs a simulation test based on the loaded current intersection test scene and the connected self-vehicle algorithm interface and outputs the corresponding test recording scene;

[0095] Specifically comprising: step 31, taking each intersection test scene as the corresponding current intersection test scene;

[0096] Step 32, selecting a car object from the current intersection test scene as the corresponding ego vehicle object based on a preset ego vehicle selection rule; wherein the ego vehicle selection rule includes at least random, long-range, and efficient;

[0097] Specifically include: the scene object set of the current intersection test scene Object Type Scene object for the car Cluster them into a class to form a corresponding car object set; and identify the car selection rule; if the car selection rule is random, randomly select a scene object from the car object set As the corresponding vehicle object; if the vehicle selection rule is long range, the vehicle object is concentrated into the object state trajectory Longest scene object As the corresponding vehicle object; if the vehicle selection rule is efficient, the vehicle object is concentrated into the object state trajectory The average speed of the fastest scene object As the corresponding ego vehicle object;

[0098] Step 33, and import the current intersection test scene into the preset scene simulator for initialization;

[0099] Specifically including: the scene simulator is based on the high-precision map of the intersection of the current intersection test scene currently imported Build a two-dimensional or three-dimensional simulation world; and test the scene object set according to the current intersection scene Each scene object A one-to-one simulation object is constructed in the current simulation world; and the simulation period of the current simulation world is configured based on the time span of the current intersection test scene; and the recording sampling frequency and single-step simulation frequency of the current simulation world are configured based on the trajectory sampling frequency of the current intersection test scene, the recording sampling frequency is consistent with the current trajectory sampling frequency, and the single-step simulation frequency is an integer multiple of the current trajectory sampling frequency; and the simulation objects of the object type of automobile, motorcycle, bicycle or pedestrian in the current simulation world are regarded as participant objects, and the corresponding traffic participant behavior model, motion control model and dynamic model are assigned to each participant object; and the simulation objects of the object type of signal light are regarded as signal light objects, and the corresponding signal light control model is assigned to each signal light object; and based on the object state trajectory corresponding to each simulation object The first object state in Set the initial simulation state of the current simulation object and set the second to last object state of each simulation object A multi-stage simulation target as the current simulation object;

[0100] Here, the scene simulator of the embodiment of the present invention is a scene simulation tool that meets the OpenSCENARIO standard;

[0101] The time span of the current intersection test scenario in the embodiment of the present invention is the intersection segmentation period TA corresponding to the current intersection test scenario. i or maximum pressure period TB i;

[0102] The traffic participant behavior model of the embodiment of the present invention is used to make decisions on the traffic behavior type of the current participant object at a future simulation moment based on the current simulation target and current historical trajectory of each participant object at the current simulation moment, the historical trajectories of other surrounding participant objects at the current simulation moment, and the historical trajectories of surrounding signal light objects at the current simulation moment; the traffic behavior types include at least slowing down and going straight, accelerating and going straight, going straight at a constant speed, changing lanes to the left, changing lanes to the right, overtaking, turning around, avoiding to the left, avoiding to the right, sudden braking, and stopping;

[0103] The motion control model of the embodiment of the present invention is used to predict the motion control parameters of the current participant at a future simulation moment based on the current simulation target, current traffic behavior type, and current historical trajectory of each participant object at the current simulation moment; the motion control parameters include at least a steering force parameter, a longitudinal acceleration force parameter, and a longitudinal deceleration force parameter;

[0104] The dynamic model of the embodiment of the present invention is used to predict the simulation state of the current participant at a future simulation moment based on the current simulation target, current simulation state, and current motion control parameters of each participant object at the current simulation moment; the simulation state includes at least coordinates, orientation angle, velocity, and acceleration;

[0105] The signal light control model of the embodiment of the present invention is used to predict the signal light state of the current signal light object at a future simulation moment based on the current simulation target and current historical trajectory of each signal light object at the current simulation moment;

[0106] Step 34, the vehicle algorithm interface is connected to the scene simulator to take over the driving control of the vehicle object;

[0107] Specifically, the method includes: setting the simulation object corresponding to the ego vehicle object in the current simulation world of the scenario simulator as the corresponding current takeover object; canceling the traffic participant behavior model and motion control model assigned by the scenario simulator to the current takeover object; connecting the input end of the dynamic model assigned by the scenario simulator to the output end of the ego vehicle algorithm interface; and setting a corresponding simulation data output interface in the scenario simulator to connect with the input end of the ego vehicle algorithm interface;

[0108] Here, the simulation data output interface of the embodiment of the present invention is used to use the real-time simulation state of the current takeover object in the current simulation world as the corresponding vehicle state data at each simulation moment in the simulation process; and use the real-time simulation state of other participant objects around the current takeover object as the corresponding traffic participant data, and all the traffic participant data obtained constitute a corresponding traffic participant data set; and use the coordinates and real-time traffic light states of each traffic light object in the current simulation world as the corresponding traffic light coordinates and lighting state to form a corresponding traffic light data set, and all the traffic light data obtained constitute a corresponding traffic light data set; and use the coordinate position of the nearest next-stage simulation target in the multi-stage simulation target corresponding to the current takeover object as the corresponding vehicle target position; and use the high-precision map of the intersection corresponding to the current simulation world as the corresponding high-precision map data; and the current simulation moment is used as the corresponding simulation timestamp; and the obtained simulation timestamp, traffic participant data set, signal light data set, vehicle status data, vehicle target position and high-precision map data are output to the vehicle algorithm interface as the output data of this time;

[0109] In step 35, the scene simulator performs a simulation test based on the loaded current intersection test scene and the connected vehicle algorithm interface and outputs the corresponding test recording scene;

[0110] Here, each intersection C in the embodiment of the present invention i The corresponding test recording scene is recorded as Test recording scene and intersection test scenarios One-to-one correspondence; test recording scene The data encapsulation format meets the data encapsulation format of the OpenSCENARIO standard scene file; test recording scene The data content includes at least high-precision intersection maps and recording object sets High-precision intersection map and the corresponding high-precision map of the intersection Keep consistent; record object set Including N D,i Recording objects Recording Object With scene objects One-to-one correspondence; recording object Include object types and object state trajectory Object Type The corresponding object type Stay consistent; object state track The corresponding object state trajectory timestamp alignment; object type When it is a car, motorcycle, bicycle, or pedestrian, the object status At least includes coordinates, orientation angle, velocity and acceleration; object type When it is a signal light, the object state Including traffic light coordinates and traffic light status, the traffic light status includes at least red light, green light, yellow light, and flashing yellow light;

[0111] The current step 35 specifically includes: during the simulation process, the scene simulator simulates the motion trajectory of the current participant object using the traffic participant behavior model, motion control model and dynamic model of each participant object; and the signal light control model of each signal light object simulates the light change trajectory of the current signal light object; and the simulation data output interface, self-vehicle algorithm interface and dynamic model corresponding to the self-vehicle object simulate the motion trajectory of the self-vehicle; and based on the recording sampling frequency, at each recording sampling point, the real-time simulation state of each simulation object is collected to generate the corresponding object state At the end of the simulation, the high-precision intersection map of the current intersection test scene will be As the corresponding high-precision map of the intersection And the object type corresponding to each simulation object As a corresponding object type And all object states corresponding to each simulation object Form a corresponding object state trajectory And the object type corresponding to each simulation object and object state trajectory Form a corresponding recording object And by all recorded objects Composed of corresponding recording object set And from the intersection high-precision map and recording object sets Composition of corresponding test recording scenes And output.

[0112] Step 4: Use the object index of the self-vehicle object in each test recording scene as the corresponding self-vehicle object index; and each test recording scene and its corresponding self-vehicle object index and intersection test scene form a corresponding simulation test record; and all the obtained simulation test records form a corresponding simulation test task report and save it.

[0113] It should be noted here that the method of the embodiment of the present invention also includes: after obtaining the simulation test task report, comprehensively evaluating the safety, efficiency, comfort and compliance of the autonomous driving algorithm according to each simulation test record to obtain a corresponding comprehensive score, and judging whether the intersection test corresponding to the current simulation test record is passed by a preset scoring threshold, and counting the number of passes / failures of the current simulation test task report, and rating the current evaluation algorithm based on the pre-set rating rules according to the comprehensive scores of all intersections and the total number of passed / failed intersections.

[0114] The rating rules here can be customized based on the actual needs of the application. For example, the comprehensive scores of all intersections are summed up and the total score is normalized. At the same time, the pass rate is calculated based on the total number of passed / failed intersections, and the normalized total score and the pass rate are weighted and summed to obtain a mixed total score. The level corresponding to the mixed total score is then confirmed based on different pre-set level segments.

[0115] It should also be noted that the specific steps of the embodiment of the present invention for comprehensively evaluating the safety, efficiency, comfort and compliance of the autonomous driving algorithm based on each simulation test record include: taking each simulation test record as the corresponding current record; and taking the intersection test scene, test recording scene, and self-vehicle object index of the current record as the corresponding current test scene, current recording scene, and current self-vehicle index; and taking the current test scene, the scene corresponding to the object index in the current recording scene and the current self-vehicle index, and the recording object as the corresponding self-vehicle label object and self-vehicle test object; and performing a safety assessment based on the self-vehicle test object and the current recording scene to obtain a corresponding safety score; and performing an efficiency assessment based on the self-vehicle label object and the self-vehicle test object to obtain a corresponding efficiency score; and performing a comfort assessment based on the self-vehicle test object to obtain a corresponding comfort score; and performing a compliance assessment based on the current recording scene and the self-vehicle test object to obtain a corresponding compliance score; and performing a scoring calculation based on the obtained safety, efficiency, comfort and compliance scores based on the preset comprehensive scoring rules to obtain a corresponding comprehensive score. The comprehensive scoring rules here can be customized based on application requirements. For example, the safety, efficiency, comfort and compliance scores can be summed up to obtain a comprehensive score. Another example is the weighted summation of the safety, efficiency, comfort and compliance scores to obtain a comprehensive score.

[0116] It should also be noted that the specific steps of the embodiment of the present invention for performing safety assessment based on the self-vehicle test object and the current recording scene to obtain the corresponding safety score include: identifying whether there are trajectory points / time points in the self-vehicle trajectory whose collision time (Time To Collision, TTC) with the front vehicle is less than a set threshold based on the object state trajectory of the self-vehicle test object and other scene objects around the self-vehicle, identifying whether the self-vehicle actively collides with other vehicles, identifying whether the self-vehicle is passively collided with other vehicles, and setting safety scores according to the three types of identification results based on preset safety scoring rules. Here, when identifying whether the ego vehicle actively collided with another vehicle or was passively collided with by another vehicle, the coordinate distance between the ego vehicle trajectory and the other object trajectory at the same time is first determined to be less than a set distance threshold. If the coordinate distance at a certain moment is less than the distance threshold, a collision is confirmed and the corresponding coordinates at the current moment are set as the collision position. If the coordinate distance at all time periods is greater than or equal to the distance threshold, it is confirmed that no collision has occurred. If the ego vehicle trajectory has not collided with any other object trajectory, the identification results of active collision with another vehicle and passive collision with another vehicle are both no collision. If it is confirmed that the ego vehicle trajectory has collided with another object trajectory, the traffic behavior type of the ego vehicle and the current collision object before the collision is determined by identifying the coordinates, heading angle, velocity and acceleration of the ego vehicle and the current collision object at the collision position, and the active / passive responsibility of the ego vehicle is determined according to the traffic behavior type of the two according to the pre-set collision responsibility confirmation rules, that is, whether the ego vehicle actively collided with the other vehicle or was passively collided with by another vehicle is confirmed. After confirming the above three types of recognition results, a safety score is set based on the safety scoring rules. The safety scoring rules here can be customized based on application requirements. For example, a 0 / 1 binary rule can be customized for the three types of recognition results of the above three types of events (collision time with the vehicle in front is too short, active collision with other vehicles, and passive collision with other vehicles): 0 if the event occurs and 1 if it does not occur. The three scores are then summed up to obtain the safety score.

[0117] It should also be noted that the specific steps for performing efficiency evaluations based on the ego-vehicle label object and the ego-vehicle test object to obtain corresponding efficiency scores in the embodiment of the present invention include: comparing the object state trajectories of the ego-vehicle label object and the ego-vehicle test object to identify whether the ego-vehicle has a yaw problem and whether the ego-vehicle has a temporary parking problem that is too long, and setting an efficiency score based on the two identification results based on a preset efficiency scoring rule. When identifying whether the ego-vehicle has a yaw problem, the two coordinates of the ego-vehicle label object and the ego-vehicle test object, which are simultaneously recorded, are first combined into a coordinate pair. The straight-line spacing between each coordinate pair is then calculated. The total number of straight-line spacings that exceed a preset spacing threshold is then counted. The ratio of the total number of coordinate pairs to the total number of coordinate pairs is then determined to determine whether it exceeds a preset ratio threshold. If so, a yaw problem is confirmed; otherwise, no yaw problem is confirmed. When identifying whether the ego vehicle has a problem of temporarily parking for too long, the coordinate position in the object state trajectory of the ego vehicle test object where the speed is lower than a preset minimum speed threshold is recorded as the parking position, and the trajectory segments corresponding to two or more consecutive parking positions are recorded as parking segments. The total number of parking segments is identified. If the total number of parking segments is 0, the problem of temporarily parking for too long does not occur. If the total number of parking segments is greater than 0, whether the duration of each parking segment exceeds a preset parking duration threshold is further identified. If the duration of one parking segment exceeds the parking duration threshold, the problem of temporarily parking for too long occurs. If the duration of all parking segments does not exceed the parking duration threshold, the problem of temporarily parking for too long does not occur. After confirming the above two types of recognition results, the efficiency score is set based on the efficiency scoring rule. The efficiency scoring rule here can be customized based on application requirements. For example, a 0 / 1 binary rule can be customized for the two types of recognition results of the above two types of events (yaw, temporary parking for too long): 0 if the event occurs and 1 if it does not occur. The two scores are then summed to obtain the safety score.

[0118] It should also be noted that the specific steps of the embodiment of the present invention for performing comfort evaluation based on the self-vehicle test object to obtain the corresponding comfort score include: identifying whether the self-vehicle has an excessive acceleration problem based on the object state trajectory of the self-vehicle test object, identifying whether the self-vehicle has an excessive lateral speed problem, and identifying whether the self-vehicle has an emergency braking behavior, and setting the comfort score according to the three types of identification results based on the preset comfort scoring rules. When identifying whether an excessive acceleration problem occurs in the ego vehicle, a correspondence rule between a speed range and an acceleration change rate range is pre-set, and an acceleration change rate range is assigned to each speed range according to the correspondence rule; then, based on the correspondence rule, the acceleration change rate range corresponding to the speed at each moment on the object state trajectory of the ego vehicle test object is identified; then, the acceleration change rate of the ego vehicle at each moment on the object state trajectory of the ego vehicle test object is calculated, and it is identified whether each acceleration change rate of the ego vehicle satisfies the corresponding acceleration change rate range; if there is a moment when the acceleration change rate of the ego vehicle does not satisfy the corresponding acceleration change rate range, it is confirmed that an excessive acceleration problem occurs; if the acceleration change rate of the ego vehicle at all moments satisfies the corresponding acceleration change rate range, it is confirmed that no excessive acceleration problem occurs. When identifying whether the ego vehicle has experienced excessive lateral speed, the ego vehicle's lateral speed is calculated based on the speed and heading angle at each moment on the ego vehicle's object state trajectory, as well as the road direction corresponding to the ego vehicle's coordinates at the current moment on the high-precision map. The ego vehicle's lateral speed at each moment is then determined to be greater than a preset lateral speed threshold. If any ego vehicle's lateral speed exceeds the threshold, it is determined that an excessive lateral speed has occurred; if all ego vehicles' lateral speeds do not exceed the threshold, it is determined that no excessive lateral speed has occurred. When identifying whether the ego vehicle has experienced sudden braking, the acceleration at each moment on the ego vehicle's object state trajectory is determined to be less than a preset sudden braking acceleration threshold. If any acceleration is less than the threshold, it is determined that no sudden braking has occurred; the sudden braking acceleration threshold is an acceleration threshold less than 0. After confirming the above three types of recognition results, the comfort score is set based on the comfort scoring rules. The comfort scoring rules here can be customized based on application requirements. For example, a 0 / 1 binary rule can be customized for the three types of recognition results of the above three types of events (excessive acceleration, excessive lateral speed, and sudden braking): 0 if the event occurs and 1 if it does not occur. The comfort score is then calculated by summing the three scores.

[0119] It should also be noted that the specific steps of the embodiment of the present invention for performing a compliance assessment based on the current recording scene and the self-vehicle test object to obtain a corresponding compliance score include: identifying whether the self-vehicle has run a red light, identifying whether the self-vehicle has left the lane, and identifying whether the self-vehicle has speeded based on the object state trajectory of the self-vehicle test object and the high-precision map of the intersection of the current recording scene, and setting a compliance score based on the three types of identification results based on preset compliance scoring rules. When identifying whether the self-vehicle has run a red light, the red light area at each time is given on the high-precision map of the intersection based on the object state trajectory of each signal light object in the current recording scene, and confirming whether the coordinates of at least one time in the object state trajectory of the self-vehicle test object enter a red light area. If it is confirmed that at least one time the coordinates enter a red light area, then a red light run is confirmed; if it is confirmed that the coordinates at all times do not enter any red light area, then a red light run is confirmed not to have occurred. When determining whether the ego vehicle has exited a lane, the intersection HD map is first used to identify prohibited areas during the ego vehicle's travel, such as areas outside the road edge, areas outside double-line lanes, and areas marked as no-parking. The system then checks whether the coordinates of the ego vehicle's object state trajectory at at least one moment enter a prohibited area. If at least one moment's coordinates enter a prohibited area, the vehicle has exited the lane; if no coordinates enter any prohibited area at any moment, the vehicle has not exited the lane. When determining whether the ego vehicle is speeding, the HD map is first used to determine the speed limit thresholds at each moment on the ego vehicle's object state trajectory. The system then determines whether the speed of the ego vehicle at each moment on the ego vehicle's object state trajectory exceeds the corresponding speed limit threshold. If the speed at any moment exceeds the corresponding speed limit threshold, speeding is confirmed; if the speed at all moments does not exceed the corresponding speed limit threshold, speeding is confirmed. After confirming the above three types of recognition results, a compliance score is set based on the compliance scoring rules. The compliance scoring rules here can be customized based on application requirements. For example, a 0 / 1 binary rule can be customized for the three types of recognition results of the above three types of events (running a red light, driving out of the lane, and overtaking): 0 if the event occurs and 1 if it does not occur. The compliance score is then calculated by summing the three scores.

[0120] Figure 5 This is a module structure diagram of a device for processing simulation test tasks provided in the second embodiment of the present invention. The device is a terminal device or server that implements the aforementioned method embodiment, or can be a device that enables the aforementioned terminal device or server to implement the aforementioned method embodiment. For example, the device can be a device or chip system of the aforementioned terminal device or server. Figure 5As shown, the device for processing simulation test tasks provided by the second embodiment of the present invention includes: a test task receiving module 201, a road intersection scene preparation module 202, a simulation test module 203, and a task report storage module 204.

[0121] The test task receiving module 201 is used to receive the test road R test , test period T test and test mode; and use the autonomous driving algorithm interface to be tested as the corresponding vehicle algorithm interface; test road R test is a real traffic network road; the test period T test It is a timing period within 24 hours; the test mode includes the first and second modes.

[0122] The intersection scene preparation module 202 is used to identify the test mode; if the test mode is the first mode, the test road R test The real road network data will be tested during the test period T test Divide into multiple continuous intersection segments, and create a test simulation scene for each intersection of the current road in its corresponding intersection segment based on the real road network data to obtain the corresponding intersection test scene; if the test mode is the second mode, then according to the test road R test The real road network data for each intersection of the current road in the test period T test A test simulation scenario is created on the maximum pressure period within the intersection to obtain the corresponding intersection test scenario.

[0123] The simulation test module 203 is used to use each intersection test scene as the corresponding current intersection test scene; and select a car object from the current intersection test scene as the corresponding self-vehicle object based on the preset self-vehicle selection rule; and import the current intersection test scene into the preset scene simulator for initialization; and connect the self-vehicle algorithm interface to the scene simulator to take over the driving control of the self-vehicle object; and the scene simulator performs a simulation test according to the loaded current intersection test scene and the connected self-vehicle algorithm interface and outputs the corresponding test recording scene; the self-vehicle selection rule includes at least random, long-range and efficient.

[0124] The task report saving module 204 is used to use the object index of the self-vehicle object in each test recording scene as the corresponding self-vehicle object index; and each test recording scene and its corresponding self-vehicle object index and intersection test scene form a corresponding simulation test record; and all the obtained simulation test records form a corresponding simulation test task report and save it.

[0125] It should be noted that the processing device for the simulation test task provided in the second embodiment of the present invention may also include an algorithm evaluation module; the algorithm evaluation module is used to, after obtaining the simulation test task report, comprehensively evaluate the safety, efficiency, comfort and compliance of the autonomous driving algorithm according to each simulation test record to obtain a corresponding comprehensive score, and use a preset scoring threshold to determine whether the intersection test corresponding to the current simulation test record has passed, and count the number of passes / failures in the current simulation test task report, and rate the current evaluation algorithm based on the comprehensive scores of all intersections and the total number of passed / failed intersections based on pre-set rating rules.

[0126] An embodiment of the present invention provides a processing device for a simulation test task, which can execute the method steps in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0127] It should be noted that it should be understood that the division of the various modules of the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into a physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software called by a processing element; or they can all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the test task receiving module can be a separately established processing element, or it can be integrated into a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called by a processing element of the above device to perform the functions of the above-mentioned determined module. The implementation of other modules is similar. In addition, these modules can all or partly be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed by hardware integrated logic circuits in the processor element or instructions in the form of software.

[0128] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0129] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the above method embodiments are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The above-mentioned computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the above-mentioned computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, Bluetooth, microwave, etc.) means. The above-mentioned computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The above-mentioned available medium can be a magnetic medium (such as a floppy disk, hard disk, tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0130] Figure 6 This is a schematic diagram of the structure of an electronic device provided in the third embodiment of the present invention. The electronic device can be a terminal device or server that implements the method of the aforementioned embodiment, or it can be a terminal device or server that implements the method of the aforementioned embodiment connected to the aforementioned terminal device or server. Figure 6As shown, the electronic device may include: a processor 301 (such as a CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiver 303's transceiver actions. Various instructions may be stored in the memory 302 for completing various processing functions and implementing the processing steps described in the aforementioned embodiment method. Preferably, the electronic device involved in the embodiment of the present invention further includes: a power supply 304, a system bus 305, and a communication port 306. The system bus 305 is used to realize communication connections between components. The above-mentioned communication port 306 is used for connecting and communicating between the electronic device and other peripherals.

[0131] exist Figure 6 The system bus 305 mentioned in the figure can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used to realize communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory (Non-Volatile Memory), such as at least one disk storage.

[0132] The above-mentioned processors can be general-purpose processors, including central processing units (CPUs), network processors (NPs), graphics processing units (GPUs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0133] It should be noted that an embodiment of the present invention further provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, it enables the computer to execute the methods and processing procedures provided in the above embodiments.

[0134] The embodiment of the present invention provides a method, device, electronic device and computer-readable storage medium for processing simulation test tasks. It can be seen from the above invention content that the embodiment of the present invention provides two real intersection scene creation methods to enhance the complexity and diversity of the scene: based on time continuity, continuous scene creation is performed for all intersections of any test road, and based on the characteristics of traffic pressure test, pressure scene creation is performed for all intersections of any test road; and after completing the scene creation, the simulation-test connection is achieved by connecting the self-vehicle algorithm interface to the scene simulator; and three types of self-vehicle selection rules (random, long-range, and efficient) are provided in each scene test to improve the comprehensiveness of the test; and the scene simulator simulates the automatic driving algorithm based on the currently loaded intersection test scene and through the connected self-vehicle algorithm interface, and records the real-time scene of the test during the test. The embodiment of the present invention enhances the authenticity, complexity and diversity of the test scene, expands the types and scope of test vehicles, and effectively improves the complexity and comprehensiveness of the algorithm test.

[0135] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0136] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for processing a simulation test task, characterized in that: The method comprises: Receiving test road R test , test period T test and test mode; and the autonomous driving algorithm interface to be tested is used as the corresponding self-vehicle algorithm interface; the test road R test is a real traffic network road; the test period T test The timing period is within 24 hours; the test mode includes the first and second modes; Identify the test mode; if the test mode is the first mode, then test The real road network data will be the test period T test Divide into multiple continuous intersection segments, and create a test simulation scene for each intersection of the current road in its corresponding intersection segment based on the real road network data to obtain a corresponding intersection test scene; if the test mode is the second mode, then according to the test road R test The real road network data for each intersection of the current road in the test period T test Creating a test simulation scenario on the maximum pressure period within the intersection to obtain the corresponding intersection test scenario; Each of the intersection test scenes is used as a corresponding current intersection test scene; and based on a preset self-vehicle selection rule, a car object is selected from the current intersection test scene as the corresponding self-vehicle object; and the current intersection test scene is imported into a preset scene simulator for initialization; and the self-vehicle algorithm interface is connected to the scene simulator to take over the driving control of the self-vehicle object; and the scene simulator performs a simulation test according to the loaded current intersection test scene and the connected self-vehicle algorithm interface and outputs a corresponding test recording scene; the self-vehicle selection rule includes at least random, long-range and efficient; The object index of the self-vehicle object in each of the test recording scenes is used as the corresponding self-vehicle object index; and each of the test recording scenes and its corresponding self-vehicle object index and the intersection test scene form a corresponding simulation test record; and all the obtained simulation test records form a corresponding simulation test task report and save it.

2. The method for processing a simulation test task according to claim 1, characterized in that: The input data of the self-vehicle algorithm interface includes a simulation timestamp, a traffic participant data set, a signal light data set, a self-vehicle state data, a self-vehicle target position and high-precision map data, and the output is a vehicle driving control instruction; the traffic participant data set is composed of one or more traffic participant data, and the traffic participant data includes participant type, participant coordinates, participant speed, participant heading angle, and participant acceleration; the signal light data set is composed of one or more signal light data, and the signal light data includes signal light coordinates and light status, and the light status includes red light, green light, yellow light, and flashing yellow light; the self-vehicle state data includes self-vehicle coordinates, self-vehicle heading angle, self-vehicle speed, and self-vehicle acceleration; the self-vehicle target position is a target position coordinate; the instruction parameters of the vehicle driving control instruction include at least steering wheel angle, throttle opening degree, brake opening degree, and gear position; The test road R test Including multiple intersections C i and multiple road segments j , 1≤intersection index i≤N, 1≤road section index j≤N-1, N is the total number of intersections; the test road R test The starting and ending positions are intersection C i＝1 、C i＝N , the road section r j For intersection C i＝j 、C i＝j+1 connecting sections between The test period T test The start and end time are recorded as t start , t end ; The test period T test The test duration L test =t end -t start ; Each of the intersections C i The corresponding intersection segment period is recorded as TA i ,TA i ∈T test ; The first and second adjacent intersection segments TA i TA i+1 In the example, the end time of the first period is aligned with the start time of the second period; The intersection segmentation period TA i The start and end time are recorded as ta s,i 、ta e,i ,ta s,i＝1 =t start ,ta s,i+1 =ta e,i ,ta e,i＝N =t end ; Each of the intersections C i The corresponding maximum pressure period is recorded as TB i , TB i ∈T test ; The maximum pressure period TB i The start and end time are recorded as tb s,i 、tb e,i ; Each of the intersections C i The corresponding intersection test scene and the test recording scene are recorded as corresponding The test recording scenario With the intersection test scenario One-to-one correspondence; the intersection test scenario The test recording scenario The data encapsulation format of the scene files complies with the data encapsulation format of the OpenSCENARIO standard; The intersection test scenario The data content includes at least high-precision intersection maps and scene object sets The high-precision intersection map The map elements at least include traffic signs / markings / line elements, road edge line elements, dangerous area elements, obstacle elements, and signal light elements of all roads at the current intersection; the scene object set Including multiple scene objects 1≤object index o≤N D,i , N D,i is the total number of objects in the i-th intersection test scene; the scene objects Include object types Object state trajectory t is the timestamp; the object type At least including cars, motorcycles, bicycles, pedestrians, and traffic lights; state trajectories of all the above objects The trajectory sampling frequency 1 / △t remains consistent; the object type When it is a car, motorcycle, bicycle, or pedestrian, the object status At least including coordinates, orientation angle, velocity and acceleration; the object type When it is a signal light, the object state Including the coordinates of the traffic light and the status of the traffic light, wherein the status of the traffic light includes at least red light, green light, yellow light, and flashing yellow light; The test recording scenario The data content includes at least high-precision intersection maps and recording object sets The high-precision intersection map and the corresponding high-precision map of the intersection Remain consistent; the recording object set Including N D,i Recording objects The recording object With the scene object One-to-one correspondence; the recording object Include object types and object state trajectory The object type The object type corresponding to Keep consistent; the object state trajectory The object state trajectory corresponding to timestamp alignment; the object type When it is a car, motorcycle, bicycle, or pedestrian, the object status At least including coordinates, orientation angle, velocity and acceleration; the object type When it is a signal light, the object state Including the coordinates of the traffic light and the status of the traffic light, wherein the status of the traffic light includes at least red light, green light, yellow light, and flashing yellow light; The scene simulator is a scene simulation tool that meets the OpenSCENARIO standard.

3. The method for processing a simulation test task according to claim 2, wherein: According to the test road R test The real road network data will be the test period T test Divide into multiple continuous intersection segments, including: Based on the test road R test The real road network data of each road section r within the preset specified time period j During the test period T test The average speed within the area is calculated to obtain the corresponding average speed And each of the road segments r j The length of the straight road is recorded as the corresponding length d j ; and based on each of the lengths d j and the corresponding average vehicle speed Calculate the corresponding average travel time And for N-1 average travel time △t j The sum of the corresponding total duration l is calculated sum The designated period includes at least a designated single day or multiple consecutive days, a designated single week or multiple consecutive weeks, a designated single month or multiple consecutive months, a designated single quarter or multiple consecutive quarters, or a designated single year or multiple consecutive years; And the total duration l sum The test duration L test Identify; if the total duration l sum Less than the test duration L test , then set the corresponding tail intersection segment duration △l end =L test -l sum If the total duration is l sum Greater than or equal to the test duration L test , then choose any one of the average travel time △l j As the corresponding incremental time △l add , and for the test period T test The end time t end Delay the latest test time L test Meet L test =l sum +△l add , and set the corresponding tail intersection segment duration △l end =△l add ; And based on the obtained N-1 average travel time △l j , the end intersection segmentation duration △l end And the test period T test The starting time t start and the end time t end , for N intersection segment time periods TA i The starting time ta s,i and the end time ta e,i To set it up: Yes s,i＝1 =t start ,Yes e,i＝1 <ta s,i＝1 +Δl j＝i , me s,1<i≤N-1 =ta e,i-1 ,I e,1<i≤N-1 =ta s,1<i≤N-1 +Δl j＝i , Yes s,i＝N <ta e,i＝N-1 ,Yes s,i＝N <ta s,i＝N +Δl end =t end 。 4. The method for processing a simulation test task according to claim 2, wherein: The method of creating a test simulation scenario for each intersection of the current road in its corresponding intersection segment time period based on the real road network data to obtain a corresponding intersection test scenario specifically includes: Based on the test road R test The real road network data of the current road is used for the test period T every day within the preset specified period. test The total number of vehicle flows on the data points is counted to obtain a corresponding first total number, and the single-day road network data corresponding to the largest first total number is used as the road network data for that day; and the road network data of the day and the intersection C i The corresponding regional road network data is used as the corresponding intersection area data; and each of the intersection area data is used in the corresponding intersection segmentation period TA i The road network data within the time period is used as the corresponding intersection time period data; And each of the intersections C i The corresponding high-precision map is used as the corresponding high-precision map of the intersection And each of the intersections C i The corresponding intersection period data is used as the corresponding current intersection period data; and the motion state trajectory of each car, motorcycle, bicycle or pedestrian in the current intersection period data is sampled according to the preset trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results The coordinates and light-changing trajectories of each signal light in the current intersection period data are sampled according to the trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results. And all the scene objects obtained Composed of the corresponding scene object set And the obtained high-precision map of the intersection and the scene object set Composition of the corresponding intersection test scene 5. The method for processing a simulation test task according to claim 2, wherein: According to the test road R test The real road network data for each intersection of the current road in the test period T test The test simulation scenario is created on the maximum pressure period within the intersection to obtain the corresponding intersection test scenario, specifically including: Each of the intersections C i As the corresponding current intersection; and based on the test road R test The real road network data of the current intersection is used to calculate the test period T of each day in the preset specified period. test The maximum total number of traffic participants in the range is counted to obtain the corresponding second total number; and the maximum second total number is recorded as the total number y max,i ; and the total y max,i The corresponding single-day road network data is related to the current intersection and the test period T test The corresponding regional time period road network data is used as the corresponding current intersection data; and the total y max,i During the test period T test The corresponding time in is taken as the corresponding maximum pressure period TB i The starting time tb s,i , and the test period T test The end time t end As the current maximum pressure period TB i The end time tb e,i ; And the current intersection data meets the current maximum pressure period TB i The road network data is used as the corresponding intersection pressure period data; And each of the intersections C i The corresponding high-precision map is used as the corresponding high-precision map of the intersection And each of the intersections C i The corresponding intersection pressure period data is used as the corresponding current pressure period data; and the motion state trajectory of each car, motorcycle, bicycle or pedestrian in the current pressure period data is sampled according to the preset trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results The coordinates and light-changing trajectory of each signal light in the current pressure period data are sampled according to the trajectory sampling frequency, and the corresponding scene object is constructed based on the sampling results. And all the scene objects obtained Composed of the corresponding scene object set And the obtained high-precision map of the intersection and the scene object set Composition of the corresponding intersection test scene 6. The method for processing a simulation test task according to claim 2, wherein: The step of selecting a car object as the corresponding ego vehicle object from the current intersection test scene based on a preset ego vehicle selection rule specifically includes: The scene object set of the current intersection test scene Object type described in The scene object for the car Cluster them into a class to form a corresponding car object set; and identify the self-car selection rule; if the self-car selection rule is random, randomly select one of the scene objects from the car object set As the corresponding vehicle object; if the vehicle selection rule is long range, the vehicle object is concentrated on the object state trajectory The longest scene object As the corresponding vehicle object; if the vehicle selection rule is efficient, the vehicle object is concentrated on the object state trajectory The average speed of the fastest scene object As the corresponding vehicle object.

7. The method for processing a simulation test task according to claim 2, wherein: The step of importing the current intersection test scene into a preset scene simulator for initialization specifically includes: The scene simulator is based on the high-precision intersection map of the current intersection test scene currently imported Perform two-dimensional or three-dimensional simulation world construction; and according to the scene object set of the current intersection test scene Each of the scene objects A one-to-one simulation object is constructed in the current simulation world; and the simulation period of the current simulation world is configured based on the time span of the current intersection test scene; and the recording sampling frequency and single-step simulation frequency of the current simulation world are configured based on the trajectory sampling frequency of the current intersection test scene, the recording sampling frequency is consistent with the current trajectory sampling frequency, and the single-step simulation frequency is an integer multiple of the current trajectory sampling frequency; and the simulation objects of the object type of automobile, motorcycle, bicycle or pedestrian in the current simulation world are regarded as participant objects, and corresponding traffic participant behavior models, motion control models and dynamic models are assigned to each of the participant objects; and the simulation objects of the object type of traffic lights are regarded as traffic light objects, and corresponding traffic light control models are assigned to each of the traffic light objects; and based on the object state trajectory corresponding to each of the simulation objects The first of the objects in the state Set the initial simulation state of the current simulation object and set the second to last object state of each simulation object A multi-stage simulation target as the current simulation object; The traffic participant behavior model is used to make decisions on the traffic behavior type of the current participant object at a future simulation moment based on the current simulation target and current historical trajectory of each participant object at the current simulation moment, the historical trajectories of other surrounding participant objects at the current simulation moment, and the historical trajectories of surrounding signal light objects at the current simulation moment; the traffic behavior types include at least slowing down and going straight, accelerating and going straight, going straight at a constant speed, changing lanes to the left, changing lanes to the right, overtaking, turning around, avoiding to the left, avoiding to the right, sudden braking, and stopping; The motion control model is used to predict the motion control parameters of the current participant at a future simulation moment based on the current simulation target, current traffic behavior type, and current historical trajectory of each participant object at the current simulation moment; the motion control parameters include at least a steering force parameter, a longitudinal acceleration force parameter, and a longitudinal deceleration force parameter; The dynamic model is used to predict the simulation state of the current participant at a future simulation moment based on the current simulation target, current simulation state and current motion control parameters of each participant object at the current simulation moment; the simulation state includes at least coordinates, orientation angle, velocity and acceleration; The traffic light control model is used to predict the traffic light state of the current traffic light object at a future simulation moment based on the current simulation target and the current historical trajectory of each traffic light object at the current simulation moment.

8. The method for processing a simulation test task according to claim 7, wherein: Connecting the self-vehicle algorithm interface to the scene simulator to take over the driving control of the self-vehicle object specifically includes: The simulation object corresponding to the ego vehicle object in the current simulation world of the scenario simulator is used as the corresponding current takeover object; the traffic participant behavior model and the motion control model assigned by the scenario simulator to the current takeover object are canceled; the input end of the dynamic model assigned by the scenario simulator to the current takeover object is connected to the output end of the ego vehicle algorithm interface; and a corresponding simulation data output interface is set in the scenario simulator to connect to the input end of the ego vehicle algorithm interface; Among them, the simulation data output interface is used to use the real-time simulation state of the current takeover object in the current simulation world as the corresponding self-vehicle state data at each simulation moment in the simulation process; and use the real-time simulation state of each of the other participant objects around the current takeover object as the corresponding traffic participant data, and all the traffic participant data obtained are used to form a corresponding traffic participant data set; and use the coordinates and real-time traffic light state of each of the traffic light objects in the current simulation world as the corresponding traffic light coordinates and the lighting state to form a corresponding traffic light data set, and all the traffic light data obtained are used to form a corresponding traffic light data set; and use the coordinate position of the nearest next-stage simulation target in the multi-stage simulation target corresponding to the current takeover object as the corresponding self-vehicle target position; and use the high-precision map of the intersection corresponding to the current simulation world as the corresponding high-precision map data; and the current simulation moment is used as the corresponding simulation timestamp; and the obtained simulation timestamp, the traffic participant data set, the traffic light data set, the vehicle status data, the vehicle target position and the high-precision map data are output as the output data of this time to the vehicle algorithm interface.

9. The method for processing a simulation test task according to claim 7, wherein: The scenario simulator performs a simulation test according to the loaded current intersection test scenario and the connected vehicle algorithm interface and outputs a corresponding test recording scenario, specifically including: During the simulation process, the scene simulator simulates the motion trajectory of the current participant object by the traffic participant behavior model, the motion control model and the dynamic model of each participant object; and simulates the light change trajectory of the current signal light object by the signal light control model of each signal light object; and simulates the motion trajectory of the ego vehicle by the simulation data output interface, the ego vehicle algorithm interface and the dynamic model corresponding to the ego vehicle object; and based on the recording sampling frequency, the real-time simulation state of each simulation object is collected at each recording sampling point to generate the corresponding object state At the end of the simulation, the high-precision map of the intersection of the current intersection test scene is As the corresponding high-precision map of the intersection And the object type corresponding to each simulation object As a corresponding object type And all the object states corresponding to each of the simulation objects Form a corresponding state trajectory of the object And the object type corresponding to each simulation object and the object state trajectory Form a corresponding recording object And by all the recording objects Composed of the corresponding recording object set And the high-precision map of the intersection and the recording object set Composition of the corresponding test recording scene And output.

10. A device for executing the processing method of the simulation test task according to any one of claims 1 to 9, characterized in that: The device includes: a test task receiving module, a road intersection scene preparation module, a simulation test module, and a task report storage module; The test task receiving module is used to receive the test road R test , test period T test and test mode; and the autonomous driving algorithm interface to be tested is used as the corresponding self-vehicle algorithm interface; the test road R test is a real traffic network road; the test period T test The timing period is within 24 hours; the test mode includes the first and second modes; The intersection scene preparation module is used to identify the test mode; if the test mode is the first mode, then according to the test road R test The real road network data will be the test period T test Divide into multiple continuous intersection segments, and create a test simulation scene for each intersection of the current road in its corresponding intersection segment based on the real road network data to obtain a corresponding intersection test scene; if the test mode is the second mode, then according to the test road R test The real road network data for each intersection of the current road in the test period T test Creating a test simulation scenario on the maximum pressure period within the intersection to obtain the corresponding intersection test scenario; The simulation test module is used to use each of the intersection test scenes as the corresponding current intersection test scene; and select a car object from the current intersection test scene as the corresponding self-vehicle object based on a preset self-vehicle selection rule; and import the current intersection test scene into a preset scene simulator for initialization; and connect the self-vehicle algorithm interface to the scene simulator to take over the driving control of the self-vehicle object; and the scene simulator performs a simulation test according to the loaded current intersection test scene and the connected self-vehicle algorithm interface and outputs a corresponding test recording scene; the self-vehicle selection rule includes at least random, long-range and efficient; The task report saving module is used to use the object index of the self-vehicle object in each of the test recording scenes as the corresponding self-vehicle object index; and each of the test recording scenes and its corresponding self-vehicle object index and the intersection test scene form a corresponding simulation test record; and all the obtained simulation test records form a corresponding simulation test task report and save it.

11. An electronic device, characterized in that: include: memory, processors, and transceivers; The processor is configured to be coupled to the memory, read and execute instructions in the memory, so as to implement the method according to any one of claims 1 to 9; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer is caused to execute the method according to any one of claims 1 to 9.

Images