Quantitative test method and device for detection performance attenuation of laser radar

By measuring the point cloud reflectivity reference value and tooling average reflectivity of lidar, the problem of attenuation evaluation of lidar detection performance is solved, quantitative evaluation and automated detection during vehicle operation are realized, and driving safety and rapid evaluation are ensured.

CN118915026APending Publication Date: 2024-11-08BEIJING AI FOR RAIL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410848703.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-27
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The prior art lacks a quantitative evaluation method for the degree of attenuation of lidar detection performance, which makes it difficult to quickly complete the lidar performance attenuation measurement during vehicle operation, affecting driving safety.

Method used

By measuring the point cloud reflectivity reference value of the reflectivity surface of the tooling equipment, and determining the attenuation of the lidar detection performance of the lidar is provided based on the relationship between the average point cloud reflectivity of the tooling equipment and the point cloud reflectivity reference value in different scenarios. Quantitative testing methods and devices for lidar detection performance attenuation, supporting automated detection and output evaluation conclusions.

Benefits of technology

Quantitative evaluation of lidar performance attenuation during vehicle operation is realized, risk that may affect the normal operation of the vehicle is timely discovered, driving safety is ensured, and is suitable for rapid determination such as windshield rear installation and inventory lidar availability assessment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915026A_ABST
    Figure CN118915026A_ABST
Patent Text Reader

Abstract

The invention provides a laser radar detection performance attenuation quantitative test method and device, and relates to the technical field of laser radars. The method comprises the following steps: determining a point cloud reflectivity reference value of a laser radar test tool reflecting surface; the point cloud reflectivity reference value comprises a first reflectivity reference value and a second reflectivity reference value; the tool average point cloud reflectivity of the laser radar in different scenes is determined; and determining the detection performance attenuation condition of the laser radar based on the size relationship between the tool average point cloud reflectivity and the point cloud reflectivity reference value. The laser radar detection performance attenuation quantitative test method and device provided by the invention are high in applicability and high in accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of laser radar technology, and in particular to a method and device for quantitatively testing the attenuation of laser radar detection performance. Background Art

[0002] LiDAR can sense vehicles, pedestrians, traffic lights and other targets on the road in real time, providing accurate and comprehensive environmental information for the autonomous driving system so that it can make quick and accurate decisions. It plays a vital role in the autonomous driving of vehicles. All on-board LiDARs meet outdoor protection requirements. To maximize the detection performance of LiDARs, the vehicle will reserve an installation position on the roof during structural design, so that the LiDAR mirror is exposed and the front is unobstructed.

[0003] The following situations will cause the laser radar detection performance to degrade: (1) There are moving parts such as prisms / rotating mirrors / micro-vibration mirrors inside the laser radar. The accuracy of the moving parts and the laser transmission power will decrease with the use time. The aging of the equipment will cause the laser radar detection performance to degrade; (2) The laser radar glass surface is dirty or the weather is bad, which will cause its detection performance to degrade; (3) For automotive applications where the laser radar is installed behind the windshield, the differences in windshield material, thickness, curvature, and angle will affect the optical path, resulting in different degrees of laser radar detection performance degradation. In addition, the needs of laser radar single attenuation assessment and inventory laser radar availability assessment cannot be quickly completed. In response to the above problems, there is currently a lack of a universal method for quantitatively assessing the degree of laser radar detection performance degradation. Summary of the invention

[0004] The present application provides a method and device for quantitatively testing the attenuation of laser radar detection performance, so as to solve the defect of the prior art that there is a lack of a general method for quantitatively evaluating the degree of attenuation of laser radar detection performance.

[0005] In a first aspect, the present application provides a method for quantitatively testing the attenuation of laser radar detection performance, comprising: Determine a point cloud reflectivity reference value of a reflective surface of a laser radar test fixture; the point cloud reflectivity reference value includes a first reflectivity reference value and a second reflectivity reference value; Determine the average point cloud reflectivity of the tooling of the laser radar in different scenes; Based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value, the attenuation of the laser radar detection performance is determined.

[0006] Optionally, determining a reference value of a point cloud reflectivity of a reflective surface of a laser radar test fixture includes: Determine the average reflectivity of the laser radar in an unobstructed scene in front of the laser radar as the first reflectivity reference value; and determine the average reflectivity of the laser radar in different preset scenes; the preset scenes are determined based on the lower limit value of the detection capability of the laser radar; The second reflectivity reference value is determined based on the average reflectivity of the laser radar in different preset scenarios.

[0007] Optionally, the different scenarios include: vehicle operation scenario, windshield scene and equipment aging scenario; the average point cloud reflectivity of the tooling includes a first point cloud reflectivity, a second point cloud reflectivity and a third point cloud reflectivity; the first point cloud reflectivity is the average reflectivity in the vehicle operation scenario; the second point cloud reflectivity is the average reflectivity in the windshield scene; the third point cloud reflectivity is the average reflectivity in the equipment aging scenario.

[0008] Optionally, in the vehicle operation scenario, determining the average point cloud reflectivity of the tooling of the laser radar in different scenarios includes: Determining the reflectivity of the first point cloud based on the tooling deployed in the vehicle operation road area; Accordingly, the attenuation of the laser radar detection performance is determined based on the relationship between the average point cloud reflectivity of the tooling and the reference value of the point cloud reflectivity, including: When the reflectivity of the first point cloud is greater than or equal to the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is normal; When the reflectivity of the first point cloud is less than the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is abnormal, and the cause of the fault is determined.

[0009] Optionally, in the scenario where there is a windshield, determining the average point cloud reflectivity of the tooling of the laser radar in different scenarios includes: When the average reflectivity in the scene without the windshield is consistent with the first reflectivity reference value, measuring the average reflectivity in the scene with the windshield as the second point cloud reflectivity; Accordingly, the attenuation of the laser radar detection performance is determined based on the relationship between the average point cloud reflectivity of the tooling and the reference value of the point cloud reflectivity, including: When the reflectivity of the second point cloud is greater than or equal to the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is normal; When the reflectivity of the second point cloud is less than the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is abnormal and the designed windshield of the vehicle does not meet the usage requirements.

[0010] Optionally, in the equipment aging scenario, determining the average point cloud reflectivity of the tooling of the laser radar in different scenarios includes: Determining the reflectivity of the third point cloud in the device aging scenario; the device aging scenario is a scenario for testing the performance of a single laser radar or a stock laser radar; Accordingly, the attenuation of the laser radar detection performance is determined based on the relationship between the average point cloud reflectivity of the tooling and the reference value of the point cloud reflectivity, including: When the reflectivity of the third point cloud is greater than or equal to the first reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is normal; When the reflectivity of the third point cloud is less than the first reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is abnormal.

[0011] In a second aspect, the present application also provides a laser radar detection performance attenuation quantitative testing device, comprising: A first determination module is used to determine a point cloud reflectivity reference value of a reflective surface of a laser radar test fixture; the point cloud reflectivity reference value includes a first reflectivity reference value and a second reflectivity reference value; A second determination module is used to determine the average point cloud reflectivity of the tooling under different scenes by the laser radar; The third determination module is used to determine the attenuation of the laser radar detection performance based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value.

[0012] In a third aspect, the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0013] In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0014] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0015] The quantitative testing method and device for the attenuation of laser radar detection performance provided in the present application determine the attenuation of laser radar detection performance by measuring the reference value of point cloud reflectivity and based on the relationship between the average point cloud reflectivity of the laser radar tooling in different scenarios and the reference value of the point cloud reflectivity. It has low requirements for the test environment, can perform quantitative and periodic measurements in both static and moving states, has high accuracy, and is easy to use. It can be used for quantitative evaluation of laser radar detection performance attenuation during vehicle operation, feasibility evaluation of laser radar installation behind windshield, and rapid measurement such as laser radar single-unit attenuation evaluation and inventory laser radar availability evaluation. It is suitable for large-scale engineering application evaluation, can automatically detect and output evaluation conclusions, and promptly discover risks that may affect the normal operation of the vehicle to ensure driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 It is a flow chart of the quantitative test method for laser radar detection performance attenuation provided in this application; Figure 2 It is a schematic diagram of the method for calculating the average reflectivity of the tooling reflective surface point cloud provided in this application; Figure 3 It is a schematic diagram of a method for determining a reference value of reflectivity of a tooling without windshield shading provided in the present application; Figure 4 It is a schematic diagram of a method for determining a reference value of reflectivity of a pedestrian and vehicle head recognition distance provided by the present application; Figure 5 It is a schematic diagram of the implementation process of the quantitative test method for the attenuation of laser radar detection performance during vehicle operation provided by the present application; Figure 6 This is one of the schematic diagrams of the deployment of the laser radar status regular inspection tooling during vehicle operation provided by this application; Figure 7 This is the second schematic diagram of the deployment of the laser radar status regular inspection tooling during vehicle operation provided by this application; Figure 8 It is a schematic diagram of the implementation process of the quantitative test method for laser radar detection performance attenuation in the presence of a windshield provided in this application; Fig. 9 This is a schematic diagram of the reflectivity measurement of the tooling under the cover of the windshield of a real vehicle provided in this application; Fig.10It is a schematic diagram of the implementation process of the quantitative test method for the attenuation of detection performance of a single laser radar and a stock laser radar provided in this application; Fig.11 It is a structural schematic diagram of a quantitative testing device for laser radar detection performance attenuation provided in the present application; Fig.12 It is a schematic diagram of the structure of the electronic device provided by this application. DETAILED DESCRIPTION

[0018] The LiDAR will undergo complete function and performance testing before leaving the factory, including indoor and outdoor testing.

[0019] Indoor testing mainly uses high-precision turntables, guide rails, echo simulators, optical power meters and other instruments for testing, which can evaluate the laser radar's field of view (FOV), reflectivity, maximum detection distance, transmission and reception efficiency and other parameters.

[0020] Outdoor testing is divided into static and dynamic testing: static testing mainly uses reflectivity calibration plates that conform to the Lambertian characteristics to improve the lidar's perception accuracy of objects and distances. Reflectivity calibration is achieved through the lidar calibration plate; dynamic testing mainly conducts functional scenario testing of traffic facilities and obstacles on actual roads.

[0021] All LiDARs will undergo the above-mentioned tests before leaving the factory. The consistency of LiDARs before leaving the factory is high, and they can meet the detection capability requirements of autonomous driving. Since there is no obstruction in front of the LiDAR, it only needs to be fused and calibrated with sensors such as cameras when used.

[0022] When the LiDAR surface is dirty or bad weather affects its use, some manufacturers' equipment has dirt detection and alarm prompt functions; and for the usability assessment of the LiDAR's aging degree, it is often returned to the factory for testing and calibration after a failure occurs.

[0023] During vehicle operation, dirty lidar glass, bad weather and aging equipment can all cause its detection performance to degrade. After the vehicle is delivered for use, it is very difficult to return it to the factory for attenuation availability assessment, and there is currently no method for quantitatively evaluating lidar detection performance during vehicle operation. For equipment aging assessment, returning the equipment to the factory for regular inspection takes a long time and is costly, and it will also reduce the number of trains available for operation. If regular inspections are not performed, it is impossible to know in advance that the detection capability of the perception system has degraded, and inspections are often performed only after a fault occurs that affects normal use. As the most important perception source for vehicles, lidar will pose a huge driving safety hazard if its detection performance degradation cannot be discovered in time. In view of the current industry status, there is a lack of a general automated testing method that can periodically perform quantitative evaluations of lidar detection performance attenuation during vehicle operation.

[0024] For vehicle applications where LiDAR is installed behind the windshield, the performance attenuation evaluation of the LiDAR by the windshield mainly includes indoor testing and verification of data collected from the actual vehicle: indoor testing is mainly static testing, which is equivalent to verification of the radar's factory performance parameters to test whether the factory performance of the equipment meets the application requirements; actual vehicle testing requires the installation of sensors after vehicle production is completed, and the vehicle collects data for analysis, and uses algorithm verification to evaluate whether it can meet the design requirements.

[0025] Indoor static testing can only verify the performance of the radar itself, and cannot simulate the actual working conditions during installation; the actual vehicle test mainly collects point cloud data after the laser radar is installed on the actual vehicle, which can evaluate the degree of attenuation of the radar performance caused by the current installation method. However, this method can only be carried out after the vehicle design and manufacturing are completed. At the same time, it requires mature system software and a large amount of data analysis. It has high requirements for operators and often lacks automated testing capabilities. At the same time, due to the tight engineering nodes, there are only two options for problems that seriously affect the performance of the laser radar, such as the windshield being too thick, the curvature and angle being too large, which seriously affect the performance of the laser radar: (1) Accept the reduction in laser radar performance: The impact is the functional degradation of the entire system, and it also reduces the safety and reliability of the system and fails to meet the design indicators; (2) Promote the change of the windshield: However, at this point in time, the body and windshield have been finalized and manufactured, and the adjustment of the glass is limited. At the same time, it also involves communication and coordination among multiple parties, which undoubtedly makes the already tight engineering nodes worse, causing huge losses in manpower, financial resources and time.

[0026] In addition, the attenuation assessment of laser radar units and the availability assessment of inventory laser radars are often time-sensitive, but the industry currently lacks a means to complete the measurement quickly.

[0027] This application mainly proposes a standard test environment and quantitative evaluation method based on the pain points in the application of LiDAR. It has strong versatility and high accuracy. It can be used for quantitative evaluation of LiDAR detection performance attenuation during vehicle operation, feasibility evaluation of LiDAR installation behind windshield, and rapid determination of LiDAR monomer attenuation evaluation and inventory LiDAR availability evaluation. At the same time, in order to facilitate on-site operation and improve test accuracy, the solution needs to have an automated test tool that can automatically select the target point cloud and analyze and output conclusions.

[0028] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] Figure 1 : is a flow chart of a quantitative test method for laser radar detection performance attenuation provided in an embodiment of the present application. Figure 1 The embodiment of the present application provides a method for quantitatively testing the attenuation of laser radar detection performance, and the execution subject can be an electronic device, for example, a laser radar performance attenuation evaluation system. The system is mainly composed of a laser radar, a test fixture, a test host, a mobile power supply, a windshield (only used when evaluating the availability of the windshield) and cables. The whole system has independent power supply, communication and automated host computer tools, and can quickly perform quantitative evaluation and measurement of laser radar performance attenuation in any environment.

[0030] The quantitative test method for the attenuation of laser radar detection performance provided in the embodiment of the present application may include: Step 110, determining a point cloud reflectivity reference value of a reflective surface of a laser radar test fixture; the point cloud reflectivity reference value includes a first reflectivity reference value and a second reflectivity reference value; Step 120, determining the average point cloud reflectivity of the tooling under different scenes by the laser radar; Step 130: Determine the attenuation of the laser radar detection performance based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value.

[0031] LiDAR transmits a detection signal (laser beam) to the target, then compares the received signal reflected from the target (target echo) with the transmitted signal, and determines the distance to the target through the laser beam flight time (ToF). It can be used for environmental perception, target perception and ranging.

[0032] Radar Cross-Section (RCS) is a property of target reflectivity and is an indicator of radar detectability. The larger the RCS, the easier it is for the target to be detected by radar.

[0033] The performance degradation of LiDAR is often reflected in the recognition distance of different targets in engineering applications, and the most essential manifestation is the reflectivity of the same target. The factors affecting RCS mainly include: target material, target distance, incident and exit angles. The principle of this application is mainly to solidify the factors affecting RCS, which is achieved through the following two methods: (1) In order to facilitate carrying and deployment, it is recommended that the tooling be made of low-reflectivity and stable reflective materials, such as dark-colored canvas, velvet, etc., and stand in front of the LiDAR through a simple support pole or bracket, keeping a fixed distance from the LiDAR and aligning it with the center of the LiDAR. In principle, the factors affecting RCS, such as target material, target distance, incident and exit angles, are solidified; (2) By counting the average reflectivity of all points on the tooling plane, continuous quantitative measurement of the LiDAR RCS value is achieved.

[0034] The method provided in this application can maintain consistency in other factors affecting RCS through standard environment deployment, except for the performance differences of the lidar itself and the influence of occlusion in front of the lidar mirror, so that the lidar performance degradation can be quantitatively evaluated under the same scale benchmark.

[0035] This application can quantitatively evaluate the performance of the laser radar by counting the average reflectivity of the tooling reflective surface point cloud. Specifically, the quantitative measurement steps of the tooling reflective surface point cloud reflectivity are as follows (e.g. Figure 2 shown): (1) Environmental deployment: The tooling can be made of materials with low reflectivity and stable reflectivity, such as dark-colored canvas or flannel, and placed directly in front of the LiDAR using a simple pole or bracket. The tooling should maintain a fixed distance from the LiDAR and be aligned with the center of the LiDAR. (2) After the environment is deployed, the test begins. The host computer automatically selects the reflective surface of the tooling in the laser point cloud and generates a test record file, which contains the reflectivity value corresponding to each point cloud; (3) The host computer automatically calculates the average reflectivity of the tooling reflective surface point cloud.

[0036] In step 110 and step 120, the laser radar performance attenuation evaluation system can determine the point cloud reflectivity baseline value of the laser radar test tooling reflective surface or the average point cloud reflectivity of the laser radar tooling in different scenarios by the above method to obtain the point cloud reflectivity baseline value and the average point cloud reflectivity of the tooling.

[0037] In step 130, the laser radar performance attenuation evaluation system can determine the laser radar detection performance attenuation by comparing the average point cloud reflectivity of the tooling with the point cloud reflectivity baseline value, and further, can determine the cause of the laser radar detection performance attenuation.

[0038] The quantitative test method for the attenuation of laser radar detection performance provided in the embodiment of the present application determines the attenuation of laser radar detection performance by measuring the reference value of point cloud reflectivity and based on the relationship between the average point cloud reflectivity of the laser radar tooling in different scenarios and the reference value of the point cloud reflectivity. It has low requirements for the test environment, can perform quantitative and periodic measurements in both static and moving states, has high accuracy, and is easy to use. It can be used for quantitative evaluation of laser radar detection performance attenuation during vehicle operation, feasibility evaluation of laser radar installation behind windshield, and rapid measurement such as single laser radar attenuation evaluation and inventory laser radar availability evaluation. It is suitable for large-scale engineering application evaluation, can automatically detect and output evaluation conclusions, and promptly discover risks that may affect the normal operation of the vehicle to ensure driving safety.

[0039] In one embodiment, determining a reference value of a point cloud reflectivity of a reflective surface of a laser radar test fixture includes: Determine the average reflectivity of the laser radar in an unobstructed scene in front of the laser radar as a first reflectivity reference value; and determine the average reflectivity of the laser radar in different preset scenes; the preset scene is determined based on the lower limit value of the laser radar detection capability; Based on the average reflectivity of the laser radar in different preset scenarios, a second reflectivity reference value is determined.

[0040] The determination process of the first reflectivity reference value is as follows (see Figure 3 ): The laser radar is placed horizontally at a certain height from the ground, with no obstructions in front of the radar. A tool is placed at a fixed distance (such as 25m) directly in front of the radar. The host computer tool can automatically select the point cloud of the tool area and perform data analysis, and output the average point cloud reflectivity RCS0 (i.e., the first reflectivity reference value). Among them, RCS0 can be used as a reference value for subsequent tooling environment consistency inspection and single laser radar performance attenuation evaluation.

[0041] The determination process of the second reflectivity reference value is as follows: In the case of clear demand input and specific project requirements, the acceptable lower limit of LiDAR detection capability is used as a reference value, such as vehicle / pedestrian recognition distance. This application uses vehicle / pedestrian recognition distance as an example for measurement (the indicator item to be used needs to be determined in combination with actual project requirements).

[0042] Pedestrian (or dummy) identification distance reference value determination (see Figure 4): The pedestrian is located directly in front of the radar, and the radar is placed horizontally at a certain height from the ground. The relative distance between the radar and the pedestrian meets the acceptable lower limit. A material that can achieve smooth and continuous attenuation of the lidar RCS is selected as the attenuation plate (such as glass). The angle of the front attenuation plate is adjusted to reduce its detection ability. When the host computer shows that the pedestrian meets the minimum point number requirement, the tooling is placed at a fixed distance (such as 25m) directly in front of the radar. The host computer tool can automatically select the point cloud of the tooling area and perform data analysis, and output the average point cloud reflectivity RCS1.

[0043] Determination of reference value of vehicle head recognition distance: The radar is located in the center of the track and placed horizontally at a certain height from the ground. The vehicle head is placed at the position with the lowest recognition distance requirement. The angle of the front attenuation plate is adjusted to reduce its detection capability. When the host computer shows that the opposite vehicle head meets the minimum point number requirement, the tooling is placed at a fixed distance (such as 25m) in front of the radar. The host computer tool can automatically select the point cloud of the tooling area and perform data analysis to output the average point cloud reflectivity RCS2.

[0044] Except for the vehicle / pedestrian recognition distance, other indicators are measured in the same way. Here we take three indicator requirements as an example. The third indicator test outputs the average point cloud reflectivity of RCS3.

[0045] Three sets of reflectivity parameters that meet the minimum requirements of laser radar detection are obtained respectively (this application takes 3 sets as an example), and the most stringent reflectivity value MIN (RCS1, RCS2, RCS3) is selected as the second reflectivity reference value as the reference value for determining the attenuation availability of the windshield. RCS0 and MIN (RCS1, RCS2, RCS3) are automatically set as reference values ​​in the host computer for subsequent actual vehicle test comparison.

[0046] The quantitative testing method for the attenuation of laser radar detection performance provided in the embodiment of the present application determines the attenuation of laser radar detection performance by measuring the reference value of point cloud reflectivity. It has low environmental requirements, high accuracy, and is easy to use. It facilitates automated detection and output of evaluation conclusions, and can promptly detect risks that may affect the normal operation of the vehicle, thereby ensuring driving safety.

[0047] In one embodiment, different scenarios include: vehicle operation scenario, windshield presence scenario and equipment aging scenario; the average point cloud reflectivity of the tooling includes a first point cloud reflectivity, a second point cloud reflectivity and a third point cloud reflectivity; the first point cloud reflectivity is the average reflectivity in the vehicle operation scenario; the second point cloud reflectivity is the average reflectivity in the windshield presence scenario; the third point cloud reflectivity is the average reflectivity in the equipment aging scenario.

[0048] During vehicle operation, dirt on the surface of the LiDAR glass, bad weather and aging equipment will all cause a degradation in its detection performance. Therefore, it is necessary to conduct a quantitative assessment of the LiDAR availability during vehicle operation, promptly detect potential performance degradation of the LiDAR and output prompt information to provide data support for safe vehicle operation, avoid malfunctions caused by LiDAR failure, and reduce safety hazards.

[0049] For applications where LiDAR is installed behind a windshield, there is a potential risk of serious attenuation of LiDAR performance due to differences in material, thickness, curvature, and angle. Therefore, a general automated testing method is needed to quantitatively evaluate the attenuation of LiDAR by windshield in the early stages of design. The method can automatically select the target point cloud and synchronously output the analysis conclusions.

[0050] This application also proposes a means of quickly evaluating lidar performance attenuation, which is suitable for various scenarios such as single lidar performance evaluation and inventory lidar availability evaluation.

[0051] The quantitative test method for attenuation of laser radar detection performance provided in the embodiment of the present application can be used for quantitative evaluation of attenuation of laser radar detection performance during vehicle operation, for feasibility evaluation of installation of laser radar behind windshield, and for rapid determination such as single laser radar attenuation evaluation and availability evaluation of inventory laser radar. It has low requirements for the test environment, can be applied to differentiated detection needs in various scenarios, has strong versatility, high reliability, and is easy to operate on site. It can automatically detect and output evaluation conclusions, promptly discover risks that may affect the normal operation of the vehicle, and ensure driving safety.

[0052] In one embodiment, in a vehicle operation scenario, determining the average point cloud reflectivity of a tooling under different scenarios by a laser radar includes: Determine a first point cloud reflectivity based on the tooling deployed in the vehicle operation road area; Accordingly, based on the relationship between the average point cloud reflectivity of the tooling and the reference point cloud reflectivity value, the attenuation of the laser radar detection performance is determined, including: When the reflectivity of the first point cloud is greater than or equal to the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is normal; when the reflectivity of the first point cloud is less than the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is abnormal, and the cause of the fault is determined.

[0053] like Figure 5 As shown in the figure, the evaluation process of radar detection performance attenuation for running vehicles is as follows: A set of tooling is deployed on both sides of the road where vehicles are running (both incoming and outgoing vehicles can be evaluated for availability). The tooling is fixedly installed and the deployment area is selected on a straight road section, with the same distance from the center line of the road. The tooling deployment diagram is as follows: Figure 6 ,7 shown.

[0054] The vehicle-mounted host deploys a laser radar performance attenuation evaluation system. After identifying the fixed tooling on the roadside, it starts to measure the distance between the radar and the tooling (the point cloud contains distance information). When the radar is at a certain distance from the tooling (such as 25m), the point cloud single frame storage is triggered. The laser radar performance attenuation evaluation system can automatically select the tooling area and calculate the average reflectivity, that is, the reflectivity of the first point cloud.

[0055] The LiDAR performance attenuation evaluation system can automatically analyze the data and draw conclusions. If the reflectivity of the first point cloud is greater than or equal to MIN (RCS1, RCS2, RCS3), the LiDAR meets the operating conditions. If the reflectivity is less than MIN (RCS1, RCS2, RCS3), the LiDAR performance has reached the minimum threshold and a prompt or alarm message needs to be output. In addition, the system combines dirt detection algorithms, camera photography and other means to further confirm whether the impact is caused by dirty LiDAR glass, bad weather or equipment aging, providing a basis for subsequent vehicle safety operation, glass cleaning and equipment maintenance and replacement.

[0056] The quantitative testing method for the attenuation of laser radar detection performance provided in the embodiment of the present application can be used to periodically and automatically perform quantitative evaluation of the laser radar detection performance during normal vehicle operation. The degree of performance attenuation of the current laser radar can be determined. The process does not require human operation, and the test is convenient and accurate.

[0057] In one embodiment, in a scene with a windshield, determining the average point cloud reflectivity of the tooling in different scenes by the laser radar includes: When the average reflectivity in the scene without the windshield is consistent with the first reflectivity reference value, measuring the average reflectivity in the scene with the windshield as the second point cloud reflectivity; Accordingly, based on the relationship between the average point cloud reflectivity of the tooling and the reference point cloud reflectivity value, the attenuation of the laser radar detection performance is determined, including: When the reflectivity of the second point cloud is greater than or equal to the second reflectivity reference value, it is determined that the laser radar detection performance attenuation is normal; when the reflectivity of the second point cloud is less than the second reflectivity reference value, it is determined that the laser radar detection performance attenuation is abnormal, and the vehicle design windshield does not meet the usage requirements.

[0058] like Figure 8 As shown, before evaluating the windshield attenuation, it is necessary to test the average reflectivity in the scene without windshield to confirm whether the test environment is consistent with the reference value during evaluation, that is, whether it is consistent with the first reflectivity benchmark value. Specifically, the host computer can automatically select and calculate the reflectivity of the tooling at this time. If the difference is large, the tooling test environment needs to be checked until the average reflectivity of the tooling is basically consistent with the previously measured reference RCS0.

[0059] The host computer uses the actual application measurement mode, keeps the radar and tooling positions unchanged, uses the real car glass to block the laser radar, and the relative position relationship between the windshield and the radar must be kept basically consistent with the actual vehicle installation (see Fig. 9 ), the host computer tool can automatically select the point cloud of the tooling area and perform data analysis, and output the average point cloud reflectivity as the second point cloud reflectivity.

[0060] The host computer compares the reflectivity of the second point cloud with the reference value (second reflectivity baseline value) and outputs the conclusion: if the reflectivity of the second point cloud is greater than or equal to MIN (RCS1, RCS2, RCS3), the vehicle windshield design can meet the use requirements and the attenuation degree of the laser radar is acceptable; if the reflectivity of the second point cloud is less than MIN (RCS1, RCS2, RCS3), the vehicle windshield design does not meet the use requirements and the attenuation degree of the laser radar is serious. It is necessary to communicate with the glass manufacturer to optimize the measures and solve the problem before the vehicle is produced.

[0061] The quantitative test method for attenuation of laser radar detection performance provided in the embodiment of the present application can be used for feasibility evaluation of laser radar installation behind windshield. It has low environmental requirements and only requires the use of radar, real vehicle glass and test tooling. It does not require human and vehicle environment, nor does it require a moving vehicle to collect data. The usability of the windshield can be evaluated in the early design stage, problems can be exposed in advance and resolved and verified before vehicle production, avoiding subsequent losses.

[0062] In one embodiment, in an equipment aging scenario, determining the average point cloud reflectivity of a tooling under different scenarios of a laser radar includes: Determine the reflectivity of the third point cloud in the equipment aging scenario; the equipment aging scenario is a scenario for testing the performance of a single laser radar or a stock laser radar. Accordingly, based on the relationship between the average point cloud reflectivity of the tooling and the reference point cloud reflectivity value, the attenuation of the laser radar detection performance is determined, including: When the reflectivity of the third point cloud is greater than or equal to the first reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is normal; when the reflectivity of the third point cloud is less than the first reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is abnormal.

[0063] like Fig.10 As shown, the performance attenuation evaluation of single laser radar and inventory laser radar is similar to the attenuation evaluation of laser radar on windshield, except that the windshield is not used in the test. The average reflectivity of the test tooling is directly compared with the reference value RCS0 to output the availability evaluation conclusion.

[0064] Single laser radars and inventory laser radars are mainly evaluated to see if the performance of the equipment itself has been degraded. As a regular inspection item and periodic test record, the host computer uses the average reflectivity RCS0 (first reflectivity reference value) of the tooling under no obstruction as a reference value for quantitative evaluation. If the average reflectivity of the tooling (the third point cloud reflectivity) is greater than or equal to RCS0, the laser radar performance has not been degraded; if the average reflectivity of the tooling is less than RCS0, the laser radar performance has been degraded compared to the factory state; if the average reflectivity of the tooling is lower than the reference value RCS0 and exceeds a certain limit (for example, 10%), the equipment can be identified as faulty.

[0065] The quantitative test method for attenuation of laser radar detection performance provided in the embodiment of the present application can be used for rapid measurements such as laser radar single-unit attenuation evaluation and inventory laser radar availability evaluation. It is not limited to specific scenarios, has strong applicability, can quickly complete measurement and evaluation, and has strong timeliness.

[0066] Based on the description of the above embodiments, the present application has the following advantages compared with the prior art: (1) Regarding the problem of LiDAR’s own surface dirt and bad weather, some manufacturers’ equipment has dirt detection function, but the accuracy is difficult to guarantee, and there is a lack of quantitative data support for surface dirt and bad weather availability; at the same time, since LiDAR has moving parts and laser sources inside, the long-term use of the equipment will also cause performance degradation. The existing LiDAR performance evaluation needs to be carried out in a standard laboratory after returning to the factory, which has high environmental requirements and cannot be carried out periodically while the vehicle is running. The solution proposed in this application can use roadside tooling to periodically conduct quantitative equipment availability evaluation during vehicle operation, and use automated testing tools to automatically select the tooling area point cloud and perform data analysis, output prompts or alarm information, and provide data support for safe vehicle operation; (2) For vehicle applications where the LiDAR is installed behind the windshield, it is often necessary to collect data from the actual vehicle before analyzing whether it meets the application requirements. At this time, the vehicle has been designed and mass-produced, and the LiDAR installation position has been determined. Adjusting the windshield or installation position is often passive, involving a large amount of manpower and financial resources, and affecting engineering nodes. The solution proposed in this application can be quantitatively evaluated in the early stages of design, has low environmental requirements, is universal for different project requirements, can expose problems in advance, and solve and verify them before vehicle production, avoiding subsequent losses; (3) There is currently a lack of a fast and effective evaluation method for specific needs such as single-body laser radar performance evaluation and inventory laser radar availability evaluation. The evaluation method provided in this application is not limited to specific scenarios, has strong applicability, and can quickly complete the measurement and evaluation, with strong timeliness; (4) The present application also has an automated host computer that can automatically select the tooling area in the lidar point cloud and perform data analysis, output parameters such as the RCS average value, the total number of point clouds, and the final comparison results, with high accuracy and easy operation.

[0067] The following is a description of the laser radar detection performance attenuation quantitative test device provided in the present application. The laser radar detection performance attenuation quantitative test device described below and the laser radar detection performance attenuation quantitative test method described above can be referenced to each other.

[0068] Fig.11 Schematic diagram of the structure of the laser radar detection performance attenuation quantitative test device provided in the embodiment of the present application. Fig.11 The laser radar detection performance attenuation quantitative testing device provided in the embodiment of the present application may include: The first determination module 1110 is used to determine a point cloud reflectivity reference value of a reflective surface of a laser radar test fixture; the point cloud reflectivity reference value includes a first reflectivity reference value and a second reflectivity reference value; The second determination module 1120 is used to determine the average point cloud reflectivity of the tooling under different scenes by the laser radar; The third determination module 1130 is used to determine the attenuation of the laser radar detection performance based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value.

[0069] The laser radar detection performance attenuation quantitative testing device provided in the embodiment of the present application determines the laser radar detection performance attenuation by measuring the point cloud reflectivity baseline value and based on the relationship between the average point cloud reflectivity of the laser radar tooling in different scenarios and the point cloud reflectivity baseline value. It has low requirements for the test environment, can perform quantitative and periodic measurements in both static and moving states, has high accuracy, and is easy to use. It can be used for quantitative evaluation of the laser radar detection performance attenuation during vehicle operation, for feasibility evaluation of laser radar installation behind a windshield, and for rapid measurements such as laser radar single-body attenuation evaluation and inventory laser radar availability evaluation. It is suitable for large-scale engineering application evaluation, can automatically detect and output evaluation conclusions, and promptly discover risks that may affect the normal operation of the vehicle to ensure driving safety.

[0070] Specifically, the above-mentioned laser radar detection performance attenuation quantitative testing device provided in the embodiment of the present application can implement all the method steps implemented by the method embodiment in which the above-mentioned execution subject is the laser radar performance attenuation evaluation system, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0071] Fig.12 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.12 As shown, the electronic device may include: a processor 1210, a communication interface 1220, a memory 1230 and a communication bus 1240, wherein the processor 1210, the communication interface 1220 and the memory 1230 communicate with each other through the communication bus 1240. The processor 1210 may call the logic instructions in the memory 1230 to execute the quantitative test method for the attenuation of the laser radar detection performance, for example, including: Determine a point cloud reflectivity reference value of a reflective surface of a laser radar test fixture; the point cloud reflectivity reference value includes a first reflectivity reference value and a second reflectivity reference value; Determine the average point cloud reflectivity of the tooling of the laser radar in different scenes; Based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value, the attenuation of the laser radar detection performance is determined.

[0072] In addition, the logic instructions in the above-mentioned memory 1230 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0073] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the quantitative test method for attenuation of laser radar detection performance provided by the above methods, for example, including: Determine a point cloud reflectivity reference value of a reflective surface of a laser radar test fixture; the point cloud reflectivity reference value includes a first reflectivity reference value and a second reflectivity reference value; Determine the average point cloud reflectivity of the tooling of the laser radar in different scenes; Based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value, the attenuation of the laser radar detection performance is determined.

[0074] In another aspect, the present application further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the steps of the quantitative test method for attenuation of laser radar detection performance provided by the above methods, for example, including: determining a point cloud reflectivity reference value of a reflective surface of a laser radar test fixture; the point cloud reflectivity reference value comprises a first reflectivity reference value and a second reflectivity reference value; Determine the average point cloud reflectivity of the tooling of the laser radar in different scenes; Based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value, the attenuation of the laser radar detection performance is determined.

[0075] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0076] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0077] It should also be noted that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0078] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0079] "Determine B based on A" in the embodiments of the present application means that the factor A should be considered when determining B. It is not limited to "B can be determined based on A alone", but should also include: "Determine B based on A and C", "Determine B based on A, C and E", "Determine C based on A, and further determine B based on C", etc. In addition, it can also include taking A as a condition for determining B, for example, "When A meets the first condition, use the first method to determine B"; for another example, "When A meets the second condition, determine B", etc.; for another example, "When A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor for determining B, for example, "When A meets the first condition, use the first method to determine C, and further determine B based on C", etc.

[0080] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A quantitative test method for laser radar detection performance attenuation, characterized in that: include: Determine a point cloud reflectivity reference value of a reflective surface of a laser radar test fixture; the point cloud reflectivity reference value includes a first reflectivity reference value and a second reflectivity reference value; Determine the average point cloud reflectivity of the tooling of the laser radar in different scenes; Based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value, the attenuation of the laser radar detection performance is determined.

2. The method for quantitatively testing the attenuation of laser radar detection performance according to claim 1, characterized in that: Determining the reference value of the point cloud reflectivity of the reflective surface of the laser radar test fixture includes: Determine the average reflectivity of the laser radar in an unobstructed scene in front of the laser radar as the first reflectivity reference value; and determine the average reflectivity of the laser radar in different preset scenes; the preset scenes are determined based on the lower limit value of the detection capability of the laser radar; The second reflectivity reference value is determined based on the average reflectivity of the laser radar in different preset scenarios.

3. The quantitative test method for laser radar detection performance attenuation according to claim 1 is characterized in that: The different scenarios include: vehicle operation scenario, windshield presence scenario and equipment aging scenario; the average point cloud reflectivity of the tooling includes a first point cloud reflectivity, a second point cloud reflectivity and a third point cloud reflectivity; the first point cloud reflectivity is the average reflectivity in the vehicle operation scenario; the second point cloud reflectivity is the average reflectivity in the windshield presence scenario; the third point cloud reflectivity is the average reflectivity in the equipment aging scenario.

4. The quantitative test method for laser radar detection performance attenuation according to claim 3 is characterized in that: In the vehicle operation scenario, determining the average point cloud reflectivity of the tooling of the laser radar in different scenarios includes: Determining the reflectivity of the first point cloud based on the tooling deployed in the vehicle operation road area; Accordingly, the attenuation of the laser radar detection performance is determined based on the relationship between the average point cloud reflectivity of the tooling and the reference value of the point cloud reflectivity, including: When the reflectivity of the first point cloud is greater than or equal to the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is normal; When the reflectivity of the first point cloud is less than the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is abnormal, and the cause of the fault is determined.

5. The method for quantitatively testing the attenuation of laser radar detection performance according to claim 3, characterized in that: In the scenario where there is a windshield, determining the average point cloud reflectivity of the tooling of the laser radar in different scenarios includes: When the average reflectivity in the scene without the windshield is consistent with the first reflectivity reference value, measuring the average reflectivity in the scene with the windshield as the second point cloud reflectivity; Accordingly, the attenuation of the laser radar detection performance is determined based on the relationship between the average point cloud reflectivity of the tooling and the reference value of the point cloud reflectivity, including: When the reflectivity of the second point cloud is greater than or equal to the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is normal; When the reflectivity of the second point cloud is less than the second reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is abnormal and the designed windshield of the vehicle does not meet the usage requirements.

6. The method for quantitatively testing the attenuation of laser radar detection performance according to claim 3, characterized in that: In the equipment aging scenario, determining the average point cloud reflectivity of the tooling of the laser radar in different scenarios includes: Determining the reflectivity of the third point cloud in the device aging scenario; the device aging scenario is a scenario for testing the performance of a single laser radar or a stock laser radar; Accordingly, the attenuation of the laser radar detection performance is determined based on the relationship between the average point cloud reflectivity of the tooling and the reference value of the point cloud reflectivity, including: When the reflectivity of the third point cloud is greater than or equal to the first reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is normal; When the reflectivity of the third point cloud is less than the first reflectivity reference value, it is determined that the attenuation of the laser radar detection performance is abnormal.

7. A quantitative test device for laser radar detection performance attenuation, characterized in that: include: A first determination module is used to determine a reference value of the point cloud reflectivity of the reflective surface of the laser radar test fixture; The point cloud reflectivity reference value includes a first reflectivity reference value and a second reflectivity reference value; A second determination module is used to determine the average point cloud reflectivity of the tooling under different scenes by the laser radar; The third determination module is used to determine the attenuation of the laser radar detection performance based on the relationship between the average point cloud reflectivity of the tooling and the point cloud reflectivity reference value.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the quantitative testing method for the attenuation of laser radar detection performance as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the quantitative testing method for the attenuation of laser radar detection performance as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the quantitative testing method for the attenuation of laser radar detection performance as described in any one of claims 1 to 6.