Multifunctional scene testing method and device, electronic equipment and storage medium

Abstract

The application relates to a multifunctional scene test method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: receiving point cloud data of a multifunctional scene collected by a target radar, analyzing the point cloud data to obtain initial dynamic targets and initial static targets, removing interference targets based on a preset removal strategy to obtain final dynamic targets and final static targets, sending the final static targets according to a first preset sending frequency and sending the final dynamic targets to a target vehicle-mounted unit according to a second preset sending frequency; receiving intersection lamp control information generated by obstacle information and road edge information sent by the target vehicle-mounted unit, sending the information to a functional scene end, performing functional scene algorithm calculation, and generating a multifunctional scene test report. Therefore, the problem that the simulation environment is single and is not conducive to the iterative update and promotion of an automatic driving algorithm model is solved, the preparation work of real vehicle simulation test is reduced, and the manual work and test cost required for real vehicle test are reduced.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a multi-functional testing method, apparatus, electronic device, and storage medium. Background Technology

[0002] As the field of autonomous driving advances, it faces bottlenecks in environmental perception. Autonomous driving routes have been implemented in closed and semi-closed scenarios such as ports, mining areas, logistics parks, and highways, but its application in urban scenarios remains challenging. This is because urban environments feature open roads, complex structures, mixed traffic of motorized and non-motorized vehicles, high density, and significant behavioral differences. These changes place higher demands on the environmental perception capabilities of autonomous vehicles. The core sensors on autonomous vehicles have limited sensing distances and are limited to line-of-sight, human-like perception, which cannot meet the needs of ultra-long-distance and non-line-of-sight environmental perception, such as at intersections and obstructed areas.

[0003] Most related technologies focus on pure simulation in vehicle-road cooperation, or directly use roadside lidar for actual measurement, without involving joint testing with simulation. The simulation environment is too simple and urgently needs to be addressed. Summary of the Invention

[0004] This application provides a multi-functional scenario testing method, device, electronic device, and storage medium to solve the problem that the single simulation environment is not conducive to the iterative update and advancement of autonomous driving algorithm models, and to reduce the preparation work for real vehicle simulation testing and the manpower and testing costs required for real vehicle testing.

[0005] The first aspect of this application provides a testing method for a multi-functional scene, comprising the following steps: receiving point cloud data of a multi-functional scene collected by a target radar, and parsing the point cloud data to obtain an initial dynamic target and an initial static target; based on a preset elimination strategy, eliminating interfering targets in the initial dynamic target and the initial static target to obtain a final dynamic target and a final static target, and sending the final static target to a target vehicle unit at a first preset transmission frequency, and sending the final dynamic target to the target vehicle unit at a second preset transmission frequency, wherein the second preset transmission frequency is greater than the first preset transmission frequency; receiving intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, and sending the intersection light control information to a functional scene terminal, so as to generate a test report of the multi-functional scene after performing functional scene algorithm calculations through the functional scene terminal.

[0006] Optionally, in some embodiments, after generating the test report for the multifunctional scenario, the method further includes: obtaining early warning information from the test report; and sending the early warning information to a preset cloud and / or target display terminal.

[0007] Optionally, in some embodiments, the step of removing interfering targets from the initial dynamic targets and the initial static targets based on a preset removal strategy to obtain the final dynamic targets and the final static targets includes: acquiring false targets and perturbation targets from the initial dynamic targets and the initial static targets; and removing the false targets and perturbation targets from the initial dynamic targets and the initial static targets respectively to obtain the final dynamic targets and the final static targets.

[0008] Optionally, in some embodiments, after receiving the intersection light control information generated based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection sent by the target vehicle unit, the method further includes: controlling the traffic lights according to the intersection light control information.

[0009] A second aspect of this application provides a testing device for a multi-functional scene, comprising: a receiving module for receiving point cloud data of a multi-functional scene collected by a target radar, and parsing the point cloud data to obtain an initial dynamic target and an initial static target; a elimination module for eliminating interference targets in the initial dynamic target and the initial static target based on a preset elimination strategy to obtain a final dynamic target and a final static target, and transmitting the final static target to a target vehicle unit at a first preset transmission frequency, and transmitting the final dynamic target to the target vehicle unit at a second preset transmission frequency, wherein the second preset transmission frequency is greater than the first preset transmission frequency; and a generation module for receiving intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, and transmitting the intersection light control information to a functional scene terminal, so as to generate a test report of the multi-functional scene after performing functional scene algorithm calculations by the functional scene terminal.

[0010] Optionally, in some embodiments, after generating the test report for the multi-functional scenario, the generation module is further configured to: obtain warning information from the test report; and send the warning information to a preset cloud and / or target display terminal.

[0011] Optionally, in some embodiments, the elimination module is specifically used to: obtain false targets and disturbed targets from the initial dynamic targets and the initial static targets; and eliminate the false targets and disturbed targets from the initial dynamic targets and the initial static targets respectively to obtain the final dynamic targets and the final static targets.

[0012] Optionally, in some embodiments, after receiving the intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, the receiving module is further configured to: control the traffic lights according to the intersection light control information.

[0013] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a multi-functional scenario testing method as described in the above embodiments.

[0014] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement a multi-functional scenario testing method as described in the above embodiments.

[0015] Therefore, using actual roadside laser equipment in conjunction with simulation environments such as SUMO (Simulation of Urban Mobility) or VISSIMPTV-VISSIM for interactive simulation can effectively reduce the preparation work for real vehicle simulation testing, the manpower required for real vehicle testing itself, and the testing costs. At the same time, it can avoid the monotony of the simulation environment caused by a pure simulation environment, which is not conducive to the updating and advancement of autonomous driving algorithm models.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0018] Figure 1 This is a flowchart of a multi-functional scenario testing method provided according to an embodiment of this application;

[0019] Figure 2 This is a schematic diagram of the module architecture of a multi-functional scenario testing method provided according to a specific embodiment of this application;

[0020] Figure 3 This is a schematic diagram of data flow transmission in a functional scenario provided according to a specific embodiment of this application;

[0021] Figure 4 This is a data signal flow diagram provided according to a specific embodiment of this application;

[0022] Figure 5This is a schematic diagram of a traffic light scene simulation according to a specific embodiment of this application;

[0023] Figure 6 This is a schematic diagram of a multi-functional testing device according to an embodiment of this application;

[0024] Figure 7 This is a schematic diagram of an electronic device provided according to an embodiment of this application.

[0025] Explanation of reference numerals in the attached drawings: 10 - test device for multi-functional scenarios, 100 - receiving module, 200 - rejection module, and 300 - generation module. Detailed Implementation

[0026] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0027] The following description, with reference to the accompanying drawings, describes a testing method, apparatus, electronic device, and storage medium for multi-functional scenarios according to embodiments of this application. Addressing the problem mentioned in the background art, where a single simulation environment hinders the iterative updating and advancement of autonomous driving algorithm models, this application provides a testing method for multi-functional scenarios. In this method, point cloud data of a multi-functional scenario is received from a target radar. The point cloud data is then parsed to obtain initial dynamic and initial static targets. Interference targets are removed based on a preset elimination strategy, resulting in final dynamic and final static targets. The final static target is transmitted at a first preset transmission frequency, and the final dynamic target is transmitted to the target vehicle-mounted unit at a second preset transmission frequency. The method also receives obstacle information and curb information from the target vehicle-mounted unit to generate intersection light control information, which is then sent to the functional scenario end. After performing functional scenario algorithm calculations, a test report for the multi-functional scenario is generated. This solves the problem of a single simulation environment hindering the iterative updating and advancement of autonomous driving algorithm models, reduces preparation work for real-vehicle simulation testing, and lowers the labor and testing costs required for real-vehicle testing.

[0028] Before introducing the embodiments of this application, let's first introduce vehicle-road cooperation and 3D (3 Dimensions) LiDAR.

[0029] Vehicle-to-infrastructure (V2I) cooperation ultimately improves the "intelligence level" of both vehicles and roads to achieve safe and autonomous driving. The intelligence of V2I is another process in realizing autonomous driving. This intelligence process can be broken down into upgrades to intelligent devices and algorithms covering both vehicles and roads. Among these intelligent devices, sensors are the most crucial. LiDAR is the core perception sensor for autonomous driving on the vehicle side; it is a roadside sensor, commonly referred to as a Roadside Unit (RSU), which provides traffic environment information to vehicles through 5G and other communication methods.

[0030] In the perception system, road-based 3D LiDAR is the main component for road environment perception. It is deployed at key and complex intersections or road sections to accurately perceive the roads in the area. In the computing system, the edge stage collects road environment perception information within a certain area, performs calculations and fusion on massive amounts of data, and distributes, stores, and reports the processed information to build a dynamic high-precision map. In the transmission system, perception data is transmitted to edge nodes via 5G / V2X (vehicle to everything), and the environmental perception data analysis results are distributed to traffic participants via 5G / V2X.

[0031] Specifically, Figure 1 This is a flowchart illustrating a multi-functional scenario testing method provided in an embodiment of this application.

[0032] like Figure 1 As shown, the testing method for this multi-functional scenario includes the following steps:

[0033] In step S101, point cloud data of the multi-functional scene collected by the target radar is received, and the point cloud data is parsed to obtain the initial dynamic target and the initial static target.

[0034] The target radar can be a 32-line main radar and a 16-line blind spot radar. The 32-line lidar can provide depth and intensity information of the intersection within the coverage area, while covering four-way roads and intersections. It can detect, classify, track, and predict the behavior of obstacles in the scene. The 32-line distribution can also detect road boundaries such as shoulders and curbs, and provide accurate information for obstacle detection and forward collision warning in vehicle blind spots. Furthermore, at intersections, lidar is used to detect, locate, and track traffic participants within 200 meters of the intersection, collect traffic participant information, and monitor road conditions, enabling real-time detection and dissemination of road information.

[0035] Specifically, such as Figure 2As shown, in this embodiment of the application, raw point cloud data can be collected by the lidar front end and transmitted to the lidar industrial control computer via TCP (Transmission Control Protocol). The lidar industrial control computer parses the received data information, classifies it into initial dynamic targets and initial static targets, and sends it to the RSU end via DSRC (Dedicated Short Range Communications) according to the protocol.

[0036] In step S102, based on a preset elimination strategy, interference targets in the initial dynamic targets and the initial static targets are eliminated to obtain the final dynamic targets and the final static targets. The final static targets are sent to the target vehicle unit at a first preset transmission frequency, and the final dynamic targets are sent to the target vehicle unit at a second preset transmission frequency, wherein the second preset transmission frequency is greater than the first preset transmission frequency.

[0037] Optionally, in some embodiments, based on a preset elimination strategy, interfering targets in the initial dynamic targets and the initial static targets are eliminated to obtain the final dynamic targets and the final static targets, including: obtaining false targets and perturbation targets in the initial dynamic targets and the initial static targets; eliminating false targets and perturbation targets from the initial dynamic targets and the initial static targets respectively to obtain the final dynamic targets and the final static targets.

[0038] Specifically, in this embodiment, the RSU can be responsible for data processing and distribution. Data processing refers to filtering false and disturbing targets from the LiDAR data, performing Kalman tracing, and then further tracking the target. Data distribution refers to sending static and dynamic data to the target vehicle unit at different frequencies, for example, sending static data every 500ms and dynamic data every 100ms. Data distribution outputs different protocols and data streams for different functional scenarios to meet the needs of different functional scenarios.

[0039] In step S103, the intersection light control information generated based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection sent by the target vehicle unit is received, and the intersection light control information is sent to the functional scene terminal so that the functional scene algorithm is calculated by the functional scene terminal to generate a test report of the multi-functional scene.

[0040] Specifically, in this embodiment, the target on-board unit can receive information on obstacles at intersections and curbs transmitted by the RSU. The Sumo / vissim functional scenario terminal receives RSU data via TCP, performs functional scenario algorithm calculations, and outputs warning information to the cloud and display screen via UDP (User Datagram Protocol). The cloud platform collects real-time information and performs comprehensive processing of warning information, enabling multi-vehicle OBU (On Board Unit) monitoring and information warning.

[0041] In actual implementation, the data flow transmission process for functional scenarios can be as follows: Figure 3 As shown, specifically, real-time intersection information can be transmitted to the Roadside Unit (RSU) via the LiDAR industrial control computer (DSRC). Actual scene information is provided by the roadside LiDAR through data processing and distribution by the RSU, with data distribution transmitted to the sumo / vissim functional scene via TCP.

[0042] In summary, the data signal processing flow of the embodiments of this application can be as follows: Figure 4 As shown, after the LiDAR industrial control computer processes the information, it sends it to the roadside control unit (RSU) via TCP. The RSU further processes the real-time information of the intersection and distributes it via TCP data according to the functional scenario. The SUMO simulation terminal builds the functional scenario in real time, performs scenario algorithm calculations, and outputs the results to the large screen for display in real time. The SUMO simulation terminal itself can also provide early warning prompts.

[0043] Optionally, in some embodiments, after receiving the intersection light control information generated based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection sent by the target vehicle unit, the method further includes: controlling the traffic lights according to the intersection light control information.

[0044] Specifically, in the embodiments of this application, traffic lights are one of the functional scenarios. The functional scenario can send intersection light control information to the RSU via TCP, and the RSU can control the traffic lights.

[0045] Optionally, in some embodiments, after generating a test report for a multi-functional scenario, the method further includes: obtaining warning information from the test report; and sending the warning information to a preset cloud and / or target display terminal.

[0046] The preset cloud can be a cloud server, which is not specifically limited here, and the target display terminal is...

[0047] Vehicle-mounted or indoor display screens can display scene-specific warnings.

[0048] In actual implementation, the embodiments of this application can be tested for multi-functional scenarios in the following ways.

[0049] 1. Deployment of roadside lidar.

[0050] Roadside lidar deployment at intersections: 1 street light pole at a crossroads.

[0051] Hardware deployment plan: Deploy RS-LiDAR-32 roadside lidar unit 1 and RS-LiDAR-16 blind spot lidar unit 2. The industrial control computer for the roadside lidar is located in the terminal laboratory.

[0052] It is important to note that because LiDAR has a limited field of view in the vertical direction, there will be a certain blind spot directly below a single roadside LiDAR unit. The size of the blind spot is determined by the installation height and angle. Additionally, when a tall vehicle obstructs the LiDAR's scanning path, a blind spot is created behind the vehicle. To address these two blind spot issues, supplementary LiDAR units are needed to fill the blind spots of each LiDAR unit.

[0053] 2. Data processing of roadside lidar.

[0054] A 32-line LiDAR system provides depth and intensity information within its coverage area, enabling the detection, classification, tracking, and behavior prediction of obstacles within a scene. The 32-line distribution also allows for the detection of road boundaries such as shoulders and curbs. It provides accurate information for obstacle detection in vehicle blind spots and for forward collision warnings.

[0055] Roadside lidar perception primarily includes the detection and identification of both static and dynamic obstacles. Obstacle identification algorithms mainly consist of algorithms for single lidar units and algorithms that fuse data from multiple lidar units. Single lidar data fusion algorithms include preprocessing, ground point segmentation, and feature extraction steps, primarily performing target extraction for a single lidar unit. Multi-lidar data fusion algorithms include target updating, target tracking, and target classification steps, enriching target information through the fusion of data from multiple units and calculating the target's speed, position, and orientation.

[0056] Therefore, by deploying LiDAR on the roadside, the objective reality of weak information collection and environmental perception capabilities in the early stages of V2X system establishment, due to the limited availability of vehicle-mounted LiDAR on a large number of vehicles in the short term, can be greatly alleviated. The deployment of LiDAR on the roadside and on operating vehicles can rapidly improve the information acquisition capabilities of the V2X network, thereby enhancing the comprehensive analysis and calculation capabilities of V2X backend data. This provides information for big data applications based on V2X, and environmental perception is a crucial technology for autonomous driving, providing information for driving control and decision-making.

[0057] 4. This application embodiment utilizes the beyond-line-of-sight and blind-spot-free characteristics of V2X+3D LiDAR, combined with road-based and mobile vehicle-mounted LiDAR, to achieve full digital perception of the surrounding environment, providing actual environmental input for functional scenarios based on actual perception.

[0058] 5. Tables 1-5 contain the relevant data transmission content of the embodiments of this application.

[0059] Table 1. Data transmission of LiDAR at intersections

[0060]

[0061] Table 2. RSU Information Transmission

[0062]

[0063] Table 3. Early Warning and Alert Functions Output by Scene Algorithms

[0064]

[0065]

[0066] 6. This application uses a smart traffic light as an example to illustrate the scene simulation function:

[0067] Without traffic lights, the SUMO simulation data simulates the time, which is faster by default and indicates a large traffic flow.

[0068] When used in conjunction with traffic lights, the actual traffic light status is adopted, and the traffic flow passes through the intersection according to the actual time. The simulation interface is coordinated with the roadside terminal, and the traffic lights at the intersection and on the roadside operate in unison, forming an actual closed-loop display.

[0069] Specific scenario processes are as follows: Figure 5 As shown:

[0070] The scene establishes an actual intersection (GPS positioning information can be obtained based on the positioning of the roadside lidar to confirm the center of the intersection) and creates a two-way four-lane intersection;

[0071] Receive actual pedestrian and vehicle information transmitted by the RSU, and read the traffic light phase status;

[0072] The simulation terminal performs timing analysis and calculation, and sends the timing results to the large-screen cloud platform, RSU;

[0073] RSU performs traffic light control and sends confirmation and real-time traffic light phases to the SUMO simulation environment.

[0074] Vehicles in the scenario operate according to the timing information.

[0075] According to the multi-functional scenario testing method proposed in this application, point cloud data of the multi-functional scenario collected by the target radar is received, and the point cloud data is parsed to obtain initial dynamic targets and initial static targets. Interference targets are removed based on a preset elimination strategy to obtain final dynamic targets and final static targets. The final static targets are sent at a first preset transmission frequency, and the final dynamic targets are sent to the target vehicle unit at a second preset transmission frequency. The method also receives intersection light control information generated from obstacle information and curb information sent by the target vehicle unit, sends the information to the functional scenario end, performs functional scenario algorithm calculations, and generates a multi-functional scenario test report. This solves the problem of a single simulation environment hindering the iterative update and advancement of autonomous driving algorithm models, reduces the preparation work for real vehicle simulation testing, and lowers the manpower and testing costs required for real vehicle testing.

[0076] Next, the multi-functional testing apparatus according to the embodiments of this application is described with reference to the accompanying drawings.

[0077] Figure 6 This is a block diagram of a multi-functional scenario testing device according to an embodiment of this application.

[0078] like Figure 6 As shown, the multi-functional scene testing device 10 includes: a receiving module 100, a rejection module 200, and a generation module 300.

[0079] The receiving module 100 is used to receive point cloud data of the multi-functional scene collected by the target radar and parse the point cloud data to obtain the initial dynamic target and the initial static target; the elimination module 200 is used to eliminate interference targets in the initial dynamic target and the initial static target based on a preset elimination strategy to obtain the final dynamic target and the final static target, and send the final static target to the target vehicle unit at a first preset transmission frequency and send the final dynamic target to the target vehicle unit at a second preset transmission frequency, wherein the second preset transmission frequency is greater than the first preset transmission frequency; the generation module 300 is used to receive the intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, and send the intersection light control information to the functional scene terminal so that the functional scene terminal can perform functional scene algorithm calculations to generate a test report of the multi-functional scene.

[0080] Optionally, in some embodiments, after generating a test report for a multi-functional scenario, the generation module 300 is further configured to: obtain warning information from the test report; and send the warning information to a preset cloud and / or target display terminal.

[0081] Optionally, in some embodiments, the elimination module 200 is specifically used to: obtain false targets and disturbed targets in the initial dynamic target and the initial static target; and eliminate false targets and disturbed targets from the initial dynamic target and the initial static target respectively to obtain the final dynamic target and the final static target.

[0082] Optionally, in some embodiments, after receiving the intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, the generation module 300 is further configured to: control the traffic lights according to the intersection light control information.

[0083] It should be noted that the explanation of the aforementioned test method embodiment for multi-functional scenarios also applies to the test device for multi-functional scenarios in this embodiment, and will not be repeated here.

[0084] The multi-functional scenario testing device proposed in this application receives point cloud data of the multi-functional scenario collected by the target radar, parses the point cloud data to obtain initial dynamic and initial static targets, and removes interfering targets based on a preset elimination strategy to obtain final dynamic and final static targets. The final static target is transmitted at a first preset transmission frequency, and the final dynamic target is transmitted at a second preset transmission frequency to the target vehicle unit. The device also receives intersection light control information generated from obstacle and curb information transmitted by the target vehicle unit, sends the information to the functional scenario end, performs functional scenario algorithm calculations, and generates a multi-functional scenario test report. This solves the problem of a single simulation environment hindering the iterative update and advancement of autonomous driving algorithm models, reduces the preparation work for real vehicle simulation testing, and lowers the manpower and testing costs required for real vehicle testing.

[0085] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0086] The memory 701, the processor 702, and the computer program stored on the memory 701 and executable on the processor 702.

[0087] When the processor 702 executes the program, it implements the multi-functional scenario testing method provided in the above embodiments.

[0088] Furthermore, electronic devices also include:

[0089] Communication interface 703 is used for communication between memory 701 and processor 702.

[0090] The memory 701 is used to store computer programs that can run on the processor 702.

[0091] The memory 701 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0092] If the memory 701, processor 702, and communication interface 703 are implemented independently, then the communication interface 703, memory 701, and processor 702 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0093] Optionally, in a specific implementation, if the memory 701, processor 702, and communication interface 703 are integrated on a single chip, then the memory 701, processor 702, and communication interface 703 can communicate with each other through an internal interface.

[0094] The processor 702 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0095] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described multi-functional scenario testing method.

[0096] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0097] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0098] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0099] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0100] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0101] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A testing method for multi-functional scenarios, characterized in that, Includes the following steps: The system receives point cloud data of a multi-functional scene collected by a target radar and parses the point cloud data to obtain an initial dynamic target and an initial static target. The target radar includes a roadside lidar and a blind spot lidar. Based on a preset elimination strategy, interfering targets are eliminated from the initial dynamic targets and the initial static targets to obtain the final dynamic targets and the final static targets. Kalman tracking processing is then performed to track the targets. The final static targets are transmitted to the target vehicle unit at a first preset transmission frequency, and the final dynamic targets are transmitted to the target vehicle unit at a second preset transmission frequency, wherein the second preset transmission frequency is greater than the first preset transmission frequency, with static targets transmitted every 500ms and dynamic targets every 100ms. The system receives intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, and sends the intersection light control information to the functional scenario terminal. After the functional scenario terminal performs functional scenario algorithm calculation, a test report of the multi-functional scenario is generated. The step of removing interfering targets from the initial dynamic targets and the initial static targets based on a preset elimination strategy to obtain the final dynamic targets and the final static targets includes: Identify false targets and perturbation targets from the initial dynamic target and the initial static target; The false target and the disturbed target are removed from the initial dynamic target and the initial static target, respectively, to obtain the final dynamic target and the final static target.

2. The method according to claim 1, characterized in that, After generating the test report for the aforementioned multi-functional scenario, the following is also included: Obtain early warning information from the test report; Send the warning information to a preset cloud platform and / or a target display terminal.

3. The method according to claim 1, characterized in that, After receiving the intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, the following steps are also included: The traffic lights are controlled based on the intersection light control information.

4. A multi-functional testing device for various scenarios, characterized in that, include: The receiving module is used to receive point cloud data of a multi-functional scene collected by the target radar, and to parse the point cloud data to obtain the initial dynamic target and the initial static target, perform Kalman tracking processing, and perform target tracking. The target radar includes a roadside lidar and a blind spot lidar. The elimination module is used to eliminate interfering targets from the initial dynamic targets and the initial static targets based on a preset elimination strategy, obtaining final dynamic targets and final static targets. The final static targets are then transmitted to the target vehicle unit at a first preset transmission frequency, and the final dynamic targets are transmitted to the target vehicle unit at a second preset transmission frequency, wherein the second preset transmission frequency is greater than the first preset transmission frequency, with static targets transmitted every 500ms and dynamic targets every 100ms. The generation module is used to receive the intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, and send the intersection light control information to the functional scenario terminal so that the functional scenario terminal can perform functional scenario algorithm calculation and generate a test report of the multi-functional scenario. The rejection module is specifically used for: Identify false targets and perturbation targets from the initial dynamic target and the initial static target; The false target and the disturbed target are removed from the initial dynamic target and the initial static target, respectively, to obtain the final dynamic target and the final static target.

5. The apparatus according to claim 4, characterized in that, After generating the test report for the multi-functional scenario, the generation module is further configured to: Obtain early warning information from the test report; Send the warning information to a preset cloud platform and / or a target display terminal.

6. The apparatus according to claim 4, characterized in that, After receiving the intersection light control information generated by the target vehicle unit based on the final dynamic target, the final static target, obstacle information and curb information of the target intersection, the receiving module is further configured to: The traffic lights are controlled based on the intersection light control information.

7. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the multi-functional scenario testing method as described in any one of claims 1-3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the test method for the multi-functional scenario as described in any one of claims 1-3.

Images