Vehicle sensing performance test method and device based on environment sensing system

Abstract

The invention belongs to the technical field of vehicle performance testing, and discloses a whole vehicle sensing performance testing method and device based on an environment sensing system, and the method comprises the steps: controlling a tested vehicle to run in different scenes through setting an automatic driving robot, so as to guarantee the repeatability and normalization of a testing process; secondly, the vehicle data can be determined through the arranged truth value testing equipment in the testing process, and the sensing performance testing result of the environment sensing system is generated in combination with the triggering time point sent by the environment sensing system, so that the sensing performance robustness of the whole vehicle sensing system is effectively evaluated; and the normalization and reliability of a sensing performance test result can be ensured.

Description

Technical Field

[0001] The present application belongs to the technical field of vehicle performance testing, and in particular, relates to a whole vehicle perception performance testing method and device based on an environmental perception system. Background Art

[0002] The vehicle's environmental perception system is an important component of the vehicle control system for assisted driving. It uses a variety of devices such as radar, lidar, camera, ultrasonic sensor, and infrared sensor to help the vehicle detect the surrounding environment and ensure the safety and convenience of vehicle driving.

[0003] Currently, the perception performance test method of the environmental perception system is mainly based on the component level. For example, the detection distance, accuracy, angle, resolution and electrical performance of the camera and various radar equipment used in the environmental perception system are tested through tools such as turntables, rangefinders, thin rods or Brown reflectors, so as to test the optimal performance parameters of various equipment under ideal conditions, but does not take into account the perception performance of the environmental perception system in actual vehicle use scenarios. In addition, other perception performance test methods for environmental perception systems focus on function testing, and thus cannot provide standardized perception performance test results for environmental perception systems. Summary of the invention

[0004] In order to solve the above-mentioned technical defects that the current perception performance test method of the environmental perception system does not take into account the perception performance of the environmental perception system in the actual vehicle use scenario, and the test is performed around the function, and thus cannot provide standardized perception performance test results of the environmental perception system, this application proposes a whole vehicle perception performance test method and device based on the environmental perception system, and its technical solution is as follows: In a first aspect, an embodiment of the present application provides a vehicle perception performance testing method based on an environmental perception system, comprising: When the target object is in the ideal scene, the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, and obtains the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test equipment; After at least two test scenarios are determined based on the ideal scenario, the autonomous driving robot controls the test vehicle to drive toward the target object in each test scenario according to the preset first driving data, and obtains the test evaluation index corresponding to each test scenario according to the second trigger time point issued by the environment perception system and the second vehicle data detected by the true value test device; According to the ideal evaluation index and all the test evaluation indexes, the perception performance test results of the environmental perception system are obtained.

[0005] In an optional solution of the first aspect, before the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, the method further includes: Acquire the first pose data of the target object determined by the true value test device and the second pose data of the target object determined by the environment perception system, and perform normalization processing on the first pose data and the second pose data respectively; Inputting the normalized first pose data and the normalized second pose data into a preset deep learning model to obtain the similarity between the first pose data and the second pose data; wherein the preset deep learning model is trained by at least two groups of sample pose data and similarity labels corresponding to each group of sample pose data; The test vehicle is controlled by the autonomous driving robot to drive toward the target object according to the preset first driving data, including: When it is detected that the similarity exceeds a preset similarity threshold, the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data.

[0006] In another optional solution of the first aspect, the preset first driving data includes a preset driving speed and a preset relative distance; Before obtaining the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: When the test vehicle is in a stopped state, an initial distance between the test vehicle and the target object is obtained, and a test starting point position is determined according to the initial distance and a preset relative distance; After the test vehicle is in a driving state, the current speed of the test vehicle is obtained at a preset time interval, and when any current speed is detected to be consistent with a preset driving speed, it is determined whether the test vehicle has traveled to the test starting point; When the test vehicle drives to the test starting point, the starting time point is obtained.

[0007] In yet another optional solution of the first aspect, the first vehicle data includes a first vehicle position of the test vehicle at a first trigger time point; According to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test equipment, the ideal evaluation index is obtained, including: Calculate the ideal trigger time according to the first trigger time point and the starting time point issued by the environmental perception system; Obtaining a braking distance between the first vehicle position and the target object, and calculating a first ideal trigger distance according to the braking distance and a preset relative distance; The ideal trigger time and the first ideal trigger distance are used as ideal evaluation indicators.

[0008] In another optional solution of the first aspect, after obtaining the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the truth value test device, the method further includes: The autonomous driving robot controls the test vehicle to drive toward the target object according to the preset second driving data, and calculates the second ideal trigger distance according to the third vehicle data detected by the true value test device and the preset relative distance; An ideal braking triggering curve is generated according to the first ideal triggering distance, the second ideal triggering distance, the preset first driving data, and the preset second driving data.

[0009] In yet another optional solution of the first aspect, the test evaluation index corresponding to each test scenario includes a test trigger time and a test trigger distance; According to the ideal evaluation index and all test evaluation indexes, the perception performance test results of the environmental perception system are obtained, including: According to the ideal trigger time and each test trigger time, the corresponding initial time decay rate is obtained, and the target time decay rate is calculated based on all the initial time decay rates; According to the first ideal trigger distance and each test trigger distance, a corresponding initial distance decay rate is obtained, and a target distance decay rate is calculated based on all initial distance decay rates; A first score corresponding to the target time decay rate and the target distance decay rate is queried in a preset decay rate-score correspondence table, and the perception performance test result of the environmental perception system is obtained based on the first score; wherein the preset decay rate-score correspondence table includes at least two standard scores, a standard time decay rate and a standard distance decay rate corresponding to each standard score.

[0010] In yet another optional solution of the first aspect, obtaining a perception performance test result of the environment perception system according to the first score includes: The number of non-triggering times is counted according to all test triggering times, and the target non-triggering rate is calculated based on the number of non-triggering times and the total number of tests corresponding to all test triggering times; A second score corresponding to the target non-trigger rate is searched in a preset non-trigger rate-score correspondence table; wherein the preset non-trigger rate-score correspondence table includes at least two standard scores and a standard non-trigger rate corresponding to each standard score; The first score and the second score are weighted and summed according to preset weights to obtain a target score, and the evaluation level corresponding to the target score is used as the perception performance test result of the environmental perception system.

[0011] In a second aspect, an embodiment of the present application provides a vehicle perception performance testing device based on an environmental perception system, comprising: A first indicator generating module is used for, when the target object is in an ideal scene, controlling the test vehicle by the autonomous driving robot to drive toward the target object according to the preset first driving data, and obtaining an ideal evaluation indicator according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device; A second indicator generating module is used to, after determining at least two test scenarios based on the ideal scenario, control the test vehicle by the autonomous driving robot to drive toward the target object in each test scenario according to the preset first driving data, and obtain the test evaluation indicator corresponding to each test scenario according to the second trigger time point issued by the environment perception system and the second vehicle data detected by the true value test device; The test result generation module is used to obtain the perception performance test results of the environmental perception system based on the ideal evaluation indicators and all test evaluation indicators.

[0012] In a third aspect, the embodiment of the present application further provides a vehicle perception performance testing device based on an environmental perception system, including a processor and a memory; The processor is connected to the memory; A memory for storing executable program codes; The processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the vehicle perception performance testing method based on the environmental perception system provided by the first aspect of the embodiment of the present application or any implementation method of the first aspect.

[0013] In a fourth aspect, an embodiment of the present application provides a computer storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, the vehicle perception performance testing method based on the environmental perception system provided by the first aspect of the embodiment of the present application or any one of the implementation methods of the first aspect can be implemented.

[0014] Beneficial effects of this application: When testing the whole vehicle perception performance of the environmental perception system, when the target object is in an ideal scene, the automatic driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, and obtains the ideal evaluation index according to the first trigger time point issued by the environmental perception system and the first vehicle data detected by the true value test device; after determining at least two test scenes based on the ideal scene, the automatic driving robot controls the test vehicle to drive toward the target object according to the preset first driving data in each test scene, and obtains the test evaluation index corresponding to each test scene according to the second trigger time point issued by the environmental perception system and the second vehicle data detected by the true value test device; according to the ideal evaluation index and all the test evaluation indicators, the perception performance test results of the environmental perception system are obtained. The automatic driving robot is set to control the test vehicle to drive in different scenes to ensure the repeatability and standardization of the test process; secondly, the vehicle data can also be determined by the set true value test device during the test process to generate the perception performance test results of the environmental perception system in combination with the trigger time point issued by the environmental perception system, which not only effectively evaluates the robustness of the perception performance of the whole vehicle perception system, but also ensures the standardization and reliability of the perception performance test results. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 An overall flow chart of a vehicle perception performance testing method based on an environmental perception system provided in an embodiment of the present application; Figure 2 A schematic diagram of a vehicle perception performance test architecture provided in an embodiment of the present application; Figure 3 A schematic diagram of some scenarios of a vehicle perception performance test environment provided in an embodiment of the present application; Figure 4 A schematic diagram of the effect of an ideal braking trigger curve provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of a vehicle perception performance testing device based on an environmental perception system provided in an embodiment of the present application; Figure 6 A schematic diagram of the structure of another vehicle perception performance testing device based on an environmental perception system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0019] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application, and different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, although the embodiment may not be clearly recorded in the following text.

[0020] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0021] See also Figure 1 , Figure 1 An overall flow chart of a vehicle perception performance testing method based on an environmental perception system provided in an embodiment of the present application is shown.

[0022] like Figure 1 As shown, the vehicle perception performance testing method based on the environment perception system may at least include the following steps: Step 102: When the target object is in an ideal scene, the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, and obtains the ideal evaluation index based on the first trigger time point issued by the environmental perception system and the first vehicle data detected by the true value test equipment.

[0023] In the embodiment of the present application, the vehicle perception performance test method based on the environment perception system can be applied to, but not limited to, a test terminal, which can establish connections with the vehicle control system, the autonomous driving robot, and the true value test equipment of the test vehicle, respectively, so as to control the test vehicle to travel in different scenes through the autonomous driving robot, and obtain the vehicle perception performance test results of the environment perception system according to the trigger time point issued by the environment perception system in the vehicle control system and the vehicle data detected by the true value test equipment. Among them, the vehicle control system of the test vehicle can be used to control the test vehicle to drive normally, and during normal driving, it can also be combined with the auxiliary driving system to ensure the safety and convenience of vehicle driving. The environment perception system, as an auxiliary driving system, can help the test vehicle detect the surrounding environment by obtaining data collected by various types of radars, cameras, ultrasonic sensors, infrared sensors and other devices built into the test vehicle, for example, but not limited to, when pedestrians or other vehicles are detected in front of the test vehicle, the automatic emergency braking function is triggered to avoid collision of the test vehicle.

[0024] The autonomous driving robot may be, but is not limited to, composed of a steering robot, a combined brake and throttle robot, and an inertial navigation device, which is manually set in advance at the main driving position of the test vehicle, and controls the test vehicle to drive normally in different scenarios according to the preset driving data sent by the test terminal. Here, the preset driving data may be, but is not limited to, a preset driving speed, a preset relative distance, and a preset lane position. The preset driving speed may be understood as the stable driving speed that the test vehicle needs to reach when testing the whole vehicle perception performance of the environmental perception system; the preset relative distance may be understood as the vertical distance between the test vehicle and the target object when testing the whole vehicle perception performance of the environmental perception system; the preset lane position may be understood as the lane position that the test vehicle needs to drive relative to the target object when testing the whole vehicle perception performance of the environmental perception system.

[0025] It is understandable that the inertial navigation device mentioned above may include but is not limited to inertial sensors, so as to calculate the speed and pitch angle and other data of the test vehicle based on the angular velocity and acceleration detected by the inertial sensors, thereby ensuring the accuracy of the test vehicle's driving speed and position, and also ensuring the repeatability of the test vehicle during the test process.

[0026] The true value test equipment may include, but is not limited to, laser radar, millimeter wave radar, real-time dynamic positioning device (for example, a positioning receiver) and surveillance cameras, which are pre-installed on the surface of the test vehicle by hand, and when testing the whole vehicle perception performance of the environmental perception system, the radar point cloud data, positioning data and high-definition video data collected by various devices are processed using a preset algorithm, such as but not limited to obtaining the position, speed, size, category and vehicle position of the target object, and feeding back to the test terminal. Here, the category of the target object may be, but is not limited to, pedestrians, passenger cars, motorcycles or bicycles, and is not limited to this. Of course, the true value test equipment mentioned in the embodiment of the present application may also be, but is not limited to, obtaining the speed and pitch angle of the test vehicle calculated by the above-mentioned inertial navigation equipment, and the speed and pitch angle of the test vehicle may be synchronously fed back to the test terminal.

[0027] It should be noted that the data processing methods used by the inertial navigation device and the true value test device mentioned in the embodiments of the present application can refer to the technical means well known in the art, and after the inertial navigation device and the true value test device are manually installed on the test vehicle, the inertial navigation device and the true value test device can also be calibrated, but not limited to, respectively (the calibration processing method can refer to the calibration means well known in the art, but will not be elaborated here), so that the spatial coordinate system and time stamp configured by the inertial navigation device and the true value test device are consistent, thereby ensuring the accuracy and reliability of the subsequent vehicle data.

[0028] Also see here Figure 2 The schematic diagram of a vehicle perception performance test architecture provided by an embodiment of the present application is shown as follows: Figure 2 As shown in the figure, the whole vehicle perception performance test architecture includes a test terminal, and a 128-line laser radar, a 32-line blind laser radar, a monitoring camera, a whole vehicle control system of the test vehicle, a millimeter-wave radar, an inertial navigation antenna, a positioning receiver, and an autonomous driving robot that are connected to the test terminal. Among them, the 128-line laser radar, the 32-line blind laser radar, the monitoring camera, the millimeter-wave radar, the inertial navigation antenna, the positioning receiver, and the autonomous driving robot are all installed manually on the test vehicle. The inertial navigation antenna can have the same function as the inertial navigation device in the autonomous driving robot, and is used to calculate the position, speed, pitch angle and other data of the test vehicle.

[0029] Specifically, when testing the whole vehicle perception performance of the environmental perception system, it is possible but not limited to first artificially constructing an ideal scene so that the temperature in the ideal scene is controlled between 5-42 degrees, the wind speed in the ideal scene is less than 5 meters per second, the horizontal visibility of the site in the ideal scene is above 1000 meters, the lighting in the ideal scene is uniform natural light and the light intensity is not less than 2000 lux, and the above-mentioned environmental parameters such as temperature, wind speed and light intensity can be recorded at preset time intervals (for example, 10 minutes). Here, in order to ensure the accuracy of the whole vehicle perception performance of the environmental perception system in the ideal scene, the climatic conditions in the ideal scene are good, without severe weather conditions such as rain, snow, hail and dust.

[0030] In addition, the test site in this ideal scenario must be an asphalt or cement road surface, the road surface is dry (no visible moisture), the road surface is flat (no obvious potholes, cracks and other undesirable conditions, and its horizontal flatness should be less than 1%), and the width of each lane set up on the test site is controlled at 3.5-3.75 meters, the boundary line is white, and the deviation side line type should be a dotted line.

[0031] After the ideal scene is built, the test vehicle can also be manually prepared, but not limited to, so that the weight and tire pressure of the test vehicle meet the design requirements, and the oil level is at the rated state, and the test vehicle's built-in windows, various types of radars, cameras and other equipment surfaces can be cleaned to ensure the accuracy of the vehicle's perception performance of the environmental perception system in the ideal scene. Then, the above-mentioned autonomous driving robot and true value test equipment can be manually installed on the test vehicle, and the inertial navigation device and the true value test equipment can be calibrated respectively to ensure that the spatial coordinate system and timestamp configured by the inertial navigation device and the true value test equipment are consistent, thereby ensuring the accuracy and reliability of the subsequent vehicle data.

[0032] It should be noted that in order for the autonomous driving robot and the true value test equipment to meet the sampling and storage requirements of dynamic data, the inertial navigation device in the autonomous driving robot may, but is not limited to, require the longitudinal velocity accuracy of the inertial navigation device to be 0.1 kilometers per hour, the heading angle accuracy to be 0.1 degrees, the yaw angular velocity accuracy to be 0.1 degrees per second, and the steering wheel angular velocity accuracy to be 1 degree per second; and the longitudinal and lateral position accuracy of the true value test equipment to be 0.03 meters, but is not limited to this.

[0033] After the test vehicle is prepared, the target object can be manually placed at a specified position in the ideal scene to control the target object to move at a specified speed and direction. When the test terminal detects that the target object is in the ideal scene through a surveillance camera, it can send preset first driving data to the autonomous driving robot so that the autonomous driving robot controls the test vehicle to drive towards the target object according to the preset first driving data. Here, the preset first driving data may include but is not limited to a preset driving speed, a preset relative distance and a preset lane position, and the preset first driving data may also have a corresponding relationship with the category, specified speed and movement direction of the target object. For example, when the category of the target object is a pedestrian, the speed is 5 kilometers per hour and the movement direction is in the same direction as the test vehicle, the preset first driving data may include a driving speed of 30 kilometers per hour, a relative distance of 200 meters and a lane position in the same lane as the pedestrian; for another example, when the category of the target object is a pedestrian, the speed is 5 kilometers per hour and the movement direction is perpendicular to the test vehicle, the preset first driving data may include a driving speed of 30 kilometers per hour, a relative distance of 200 meters and a lane position in the left lane of the pedestrian (or the right lane of the pedestrian).

[0034] Also see here Figure 3 FIG. 1 is a schematic diagram of a partial scene of a vehicle perception performance test environment provided by an embodiment of the present application, such as Figure 3 As shown, for each group of target object categories, speeds and movement directions, there may be corresponding preset driving data including driving speed, relative distance and lane position, and the above-mentioned preset first driving data may include but is not limited to one or more groups of driving speed, relative distance and lane position, and is not limited to this.

[0035] Further, after controlling the test vehicle to drive toward the target object, the test terminal can, but is not limited to, obtain the ideal evaluation index of the environment perception system in the ideal scenario according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device. It can be understood that the first trigger time point issued by the environment perception system can be understood as the time point when the environment perception system triggers the automatic emergency braking function, which can be, but is not limited to, recorded by the vehicle control terminal of the test vehicle and sent to the test terminal, or can also be used to collect the video displayed on the central control screen using the sound and light acquisition camera set in the test vehicle, and the test terminal can recognize it from the video displayed on the central control screen; the first vehicle data detected by the true value test device can, but is not limited to, include the current vehicle position and vehicle speed of the test vehicle when the environment perception system triggers the automatic emergency braking function, the vehicle position can be, but is not limited to, calculated from the point cloud data collected by the above-mentioned multiple laser radars, and the vehicle speed can be, but is not limited to, calculated from the angular velocity and acceleration collected by the above-mentioned inertial navigation device.

[0036] Here, when a sound and light collection camera is installed inside the test vehicle, the vehicle control terminal may also, but is not limited to, pre-enable the assisted driving function and select a function operation prompt sound to improve the recognition accuracy of the first trigger time point.

[0037] As an option of the embodiment of the present application, before the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, the method further includes: Acquire the first pose data of the target object determined by the true value test device and the second pose data of the target object determined by the environment perception system, and perform normalization processing on the first pose data and the second pose data respectively; Inputting the normalized first pose data and the normalized second pose data into a preset deep learning model to obtain the similarity between the first pose data and the second pose data; wherein the preset deep learning model is trained by at least two groups of sample pose data and similarity labels corresponding to each group of sample pose data; The test vehicle is controlled by the autonomous driving robot to drive toward the target object according to the preset first driving data, including: When it is detected that the similarity exceeds a preset similarity threshold, the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data.

[0038] Specifically, in order to effectively determine whether the target object data pulled by the environmental perception system is accurate, before the test vehicle is controlled by the autonomous driving robot to travel toward the target object according to the preset first driving data, the test terminal can also obtain the first pose data of the target object determined by the true value test equipment, and obtain the second pose data of the target object determined by the environmental perception system. Here, the true value test equipment can, but is not limited to, use a preset algorithm to process radar point cloud data, positioning data, and high-definition video data collected by various radars, real-time dynamic positioning devices, and surveillance cameras and other equipment to obtain pose data including the position, speed, size, and category of the target object, that is, the first pose data of the target object, and the processing method of the pose data obtained by the true value test equipment in the embodiment of the present application can refer to the technical means known in the art, but will not be elaborated here.

[0039] Similarly, the environmental perception system can also process radar point cloud data, positioning data and high-definition video data collected by various radars, real-time dynamic positioning devices and surveillance cameras built into the test vehicle to obtain posture data including the position, speed, size and category of the target object, that is, the second posture data of the target object. In the embodiment of the present application, the environmental perception system can be set as a conventional technology in the field, and its working principle will not be elaborated here.

[0040] Next, after obtaining the first pose data and the second pose data of the target object, the test terminal may, but is not limited to, normalize the first pose data and the second pose data respectively, so as to transform each type of data in the first pose data into the same interval, and transform each type of data in the second pose data into the same interval, and input the normalized first pose data and the second pose data into a preset deep learning model, and obtain the similarity between the first pose data and the second pose data by means of neural network prediction. Here, the preset deep learning model may be a neural network structure well known in the art, which may be obtained by training at least two groups of sample pose data (each group of sample pose data may include two normalized sample pose data), and similarity labels corresponding to each group of sample pose data.

[0041] It can be understood that when it is detected that the similarity exceeds the preset similarity threshold, it indicates that the target object data pulled by the environmental perception system is more accurate, and the autonomous driving robot can control the test vehicle to drive towards the target object according to the preset first driving data; when it is detected that the similarity does not exceed the preset similarity threshold, it indicates that the target object data pulled by the environmental perception system is less accurate, and the staff can be notified to promptly check and process the various radars, real-time dynamic positioning devices, surveillance cameras and other equipment of the test vehicle to determine whether there is any abnormality.

[0042] As another option of the embodiment of the present application, the preset first driving data includes a preset driving speed and a preset relative distance; Before obtaining the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: When the test vehicle is in a stopped state, an initial distance between the test vehicle and the target object is obtained, and a test starting point position is determined according to the initial distance and a preset relative distance; After the test vehicle is in a driving state, the current speed of the test vehicle is obtained at a preset time interval, and when any current speed is detected to be consistent with a preset driving speed, it is determined whether the test vehicle has traveled to the test starting point; When the test vehicle drives to the test starting point, the starting time point is obtained.

[0043] Specifically, in order to ensure the accuracy and effectiveness of the ideal evaluation indicators, before obtaining the ideal evaluation indicators based on the first trigger time point issued by the environmental perception system and the first vehicle data detected by the true value test equipment, the test terminal can also identify the initial distance between the test vehicle and the target object through the point cloud data collected in real time by the true value test equipment when it detects that the test vehicle is in a stopped state, and obtain the vehicle position at the start of the test, that is, the test starting point, by performing a difference calculation between the initial distance and the preset relative distance.

[0044] Next, after the test vehicle is in a driving state, the test terminal can also obtain the current speed of the test vehicle determined by the above-mentioned inertial navigation device at preset time intervals, and when it is detected that the current speed corresponding to any time interval is consistent with the preset driving speed, it indicates that the current driving speed of the test vehicle has met the test requirements, and then the current distance between the test vehicle and the target object can be identified again through but not limited to the point cloud data collected in real time by the true value test equipment to determine whether the test vehicle has traveled to the test starting point based on the current distance and the preset relative distance.

[0045] It can be understood that if the current distance is consistent with the preset relative distance, it indicates that the current position of the test vehicle has met the test requirements, and the time point when the test vehicle is at the current position can be recorded, that is, the starting time point of the test process; if the current distance is less than the preset relative distance, it indicates that the test vehicle is not yet at the starting position of the test, and the current distance between the test vehicle and the target object can be identified through the point cloud data collected in real time by the true value test equipment until it is consistent with the preset relative distance.

[0046] As another option of the embodiment of the present application, the first vehicle data includes a first vehicle position of the test vehicle at a first trigger time point; According to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test equipment, the ideal evaluation index is obtained, including: Calculate the ideal trigger time according to the first trigger time point and the starting time point issued by the environmental perception system; Obtaining a braking distance between the first vehicle position and the target object, and calculating a first ideal trigger distance according to the braking distance and a preset relative distance; The ideal trigger time and the first ideal trigger distance are used as ideal evaluation indicators.

[0047] Specifically, when obtaining the ideal evaluation index, the test terminal may use the time point (that is, the first time point) emitted by the environmental perception system when the automatic emergency braking function is triggered and the time difference between the starting time point mentioned above as the ideal trigger time (that is, the time elapsed from the environmental perception system from the test starting position to the triggering of the automatic emergency braking function), and identify the braking distance (that is, the relative distance) between the first vehicle position and the target object through the point cloud data collected in real time by the true value test equipment, so as to perform a difference calculation between the preset relative distance and the braking distance to obtain the first ideal trigger distance.

[0048] Then, the test terminal may use the ideal trigger time and the first ideal trigger distance as ideal evaluation indicators of the environmental perception system under an ideal environment. It is understood that in the embodiment of the present application, the ideal evaluation indicators may include ideal evaluation indicators corresponding to the speed, movement direction and category of multiple sets of target objects, and may also include ideal evaluation indicators corresponding to multiple sets of preset driving data (different preset driving speeds, and different preset relative distances), and are not limited thereto.

[0049] As another optional embodiment of the present application, after obtaining the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: The autonomous driving robot controls the test vehicle to drive toward the target object according to the preset second driving data, and calculates the second ideal trigger distance according to the third vehicle data detected by the true value test device and the preset relative distance; An ideal braking triggering curve is generated according to the first ideal triggering distance, the second ideal triggering distance, the preset first driving data, and the preset second driving data.

[0050] Specifically, in order to further determine whether the ideal evaluation indicators are valid, after obtaining the ideal evaluation indicators, the test terminal may also send preset second driving data to the autonomous driving robot. The preset second driving data may include a preset driving speed, a preset relative distance, and a preset lane position, and the preset second driving data has at least a different preset driving speed compared to the preset first driving data, and the autonomous driving robot may control the test vehicle to return to the starting position so as to drive towards the target object again according to the preset second driving data.

[0051] Then, after the test vehicle drives towards the target object again, the test terminal can also obtain third vehicle data detected by the true value test equipment at the same time as the environmental perception system issues a trigger time point. The third vehicle data may include but is not limited to the current vehicle position of the test vehicle when the environmental perception system triggers the automatic emergency braking function, and the third vehicle data and the preset relative distance are processed with reference to the above embodiment to calculate the second ideal trigger distance.

[0052] Then, the test terminal may, but is not limited to, use a preset linear fitting algorithm to fit the first ideal trigger distance, the second ideal trigger distance, the driving data in the preset first driving data, and the driving data in the preset second driving data to construct an ideal brake trigger curve with the horizontal axis being the driving speed and the vertical axis being the trigger distance. Figure 4 FIG. 1 is a schematic diagram showing an effect of an ideal braking trigger curve provided by an embodiment of the present application, such as Figure 4 As shown, in the ideal brake trigger curve, when the stable driving speed of the test vehicle is 135 kilometers per hour, the corresponding brake trigger distance is 170 meters; when the stable driving speed of the test vehicle is 148 kilometers per hour, the corresponding brake trigger distance is 220 meters, and as the stable driving speed increases, the growth trend of the brake trigger distance becomes greater.

[0053] It is understandable that after obtaining the ideal braking trigger curve, the test terminal can also, but is not limited to, combine the historical braking trigger curve generated by the test vehicle based on other types of target objects, and determine whether there is an abnormality in the ideal braking trigger curve by comparing the slope change trend between the ideal braking trigger curve and the historical braking trigger curve. When it is determined that there is an abnormality in the ideal braking trigger curve, the staff can be notified in time to troubleshoot the environmental perception system.

[0054] Step 104: After at least two test scenarios are determined based on the ideal scenario, the autonomous driving robot controls the test vehicle to drive toward the target object in each test scenario according to the preset first driving data, and obtains the test evaluation index corresponding to each test scenario based on the second trigger time point issued by the environmental perception system and the second vehicle data detected by the true value test equipment.

[0055] Specifically, after the environmental perception system completes the vehicle perception performance test in an ideal scenario, the test terminal can also, but is not limited to, arrange a variety of test scenarios based on the ideal scenario. The climatic conditions of each test scenario compared to the ideal scenario can be any severe weather conditions such as rain, snow, hail, haze, and dust, or it can be arranged to set any driving conditions such as night, tunnels, and low-angle direct lighting, or the surfaces of equipment such as built-in windows, various types of radars and cameras in the test vehicle can be blocked. After constructing each test scenario, the target object is manually placed at a designated position in each test scenario to control the target object to move at the specified speed and direction of movement mentioned above. When the test terminal detects that the target object is in each test scenario through the monitoring camera, it can send the preset first driving data to the autonomous driving robot again, so that the autonomous driving robot controls the test vehicle to drive towards the target object according to the preset first driving data.

[0056] Furthermore, after controlling the test vehicle to drive toward the target object, the test terminal may, but is not limited to, obtain the test evaluation index of the environmental perception system in each test scenario based on the second trigger time point issued by the environmental perception system and the second vehicle data detected by the true value test device. It can be understood that the second trigger time point issued by the environmental perception system can be understood as the time point when the environmental perception system triggers the automatic emergency braking function in the test scenario; the second vehicle data detected by the true value test device may, but is not limited to, include the current vehicle position and vehicle speed of the test vehicle when the environmental perception system triggers the automatic emergency braking function in the test scenario. In addition, the method for the test terminal to obtain the test evaluation index of the environmental perception system in each test scenario can refer to one or more of the above-mentioned embodiments, which will not be elaborated here, and the test evaluation index in each test scenario may, but is not limited to, include the test trigger time and the test trigger distance.

[0057] Step 106: Obtain the perception performance test results of the environmental perception system based on the ideal evaluation index and all test evaluation indexes.

[0058] Specifically, after obtaining the ideal evaluation index and all test evaluation indexes, taking the ideal evaluation index including the ideal trigger time and the first ideal trigger distance mentioned above, and each test evaluation index including the test trigger time and the test trigger distance mentioned above as an example, the test terminal can, but is not limited to, substitute the ideal trigger time and each test trigger time into the preset time calculation formula to obtain the corresponding initial time decay rate. Here, the preset time calculation formula can be referred to as follows: In the above formula, Can be the ideal trigger time, Can be used to test trigger time.

[0059] Furthermore, after obtaining all the initial time decay rates, the test terminal may, but is not limited to, perform mean calculation on all the initial time decay rates to obtain a target time decay rate.

[0060] Furthermore, the test terminal may substitute the first ideal trigger distance and each test trigger distance into a preset distance calculation formula to obtain a corresponding initial distance attenuation rate. Here, the preset distance calculation formula may be referred to as follows: In the above formula, may be the first ideal trigger distance, and L may be the test trigger distance.

[0061] Further, after obtaining all the initial distance attenuation rates, the test terminal may, but is not limited to, perform mean calculation on all the initial distance attenuation rates to obtain a target distance attenuation rate.

[0062] Furthermore, after obtaining the target time attenuation rate and the target distance attenuation rate, the test terminal can also query the first score corresponding to the target time attenuation rate and the target distance attenuation rate in the preset attenuation rate-score correspondence table, and obtain the perception performance test result of the environmental perception system based on the first score.

[0063] Here, the preset decay rate-score correspondence table includes at least two standard scores, a standard time decay rate and a standard distance decay rate corresponding to each standard score, which can be but not limited to refer to the following: Among them, x can be the standard time decay rate, and y can be the standard distance decay rate.

[0064] Of course, in the embodiment of the present application, the braking distance or braking time can be used as an evaluation indicator, and the braking distance decay rate or braking time decay rate can be calculated according to the method of the above embodiment, so as to obtain the perception performance test result of the environmental perception system, and it is not limited to this.

[0065] As another option of the embodiment of the present application, obtaining a perception performance test result of the environment perception system according to the first score includes: The number of non-triggering times is counted according to all test triggering times, and the target non-triggering rate is calculated based on the number of non-triggering times and the total number of tests corresponding to all test triggering times; A second score corresponding to the target non-trigger rate is searched in a preset non-trigger rate-score correspondence table; wherein the preset non-trigger rate-score correspondence table includes at least two standard scores and a standard non-trigger rate corresponding to each standard score; The first score and the second score are weighted and summed according to preset weights to obtain a target score, and the evaluation level corresponding to the target score is used as the perception performance test result of the environmental perception system.

[0066] Specifically, after obtaining the evaluation score corresponding to the trigger rate, the test terminal can also count the number of non-triggering times based on all test trigger times, for example but not limited to taking the number of all test trigger times greater than a preset trigger time threshold as the number of non-triggering times, and calculating the ratio of the number of non-triggering times to the total number of tests of all test trigger times, and then obtaining the target non-triggering rate.

[0067] Then, after obtaining the target non-trigger rate, the test terminal can also query the preset non-trigger rate-score correspondence table to find out the second score corresponding to the target non-trigger rate. Here, the preset non-trigger rate-score correspondence table includes at least two standard scores and a standard non-trigger rate corresponding to each standard score, which can be but not limited to the following: Wherein, z may be the standard non-trigger rate.

[0068] Then, after obtaining the second score, the test terminal can also perform weighted summation processing on the first score and the second score according to the preset weight to obtain the target score. The preset weight can be but is not limited to 0.5, and the evaluation level corresponding to the target score is used as the perception performance test result of the environmental perception system. For example, but not limited to, when the target score is greater than or equal to 80, the corresponding evaluation level is excellent; when the target score is between 70 and 80, the corresponding evaluation level is good; when the target score is between 60 and 70, the corresponding evaluation level is average; when the target score is lower than 60, the corresponding evaluation level is poor, and is not limited to this.

[0069] See also Figure 5 , Figure 5 A schematic structural diagram of a vehicle perception performance testing device based on an environmental perception system provided in an embodiment of the present application is shown.

[0070] like Figure 5 As shown, the vehicle perception performance test device based on the environment perception system may include at least a first indicator generation module 501, a second indicator generation module 502 and a test result generation module 503, wherein: The first indicator generating module 501 is used to control the test vehicle to drive toward the target object according to the preset first driving data by the autonomous driving robot when the target object is in the ideal scene, and obtain the ideal evaluation indicator according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device; A second indicator generating module 502 is used to, after determining at least two test scenarios based on the ideal scenario, control the test vehicle by the autonomous driving robot to drive toward the target object in each test scenario according to the preset first driving data, and obtain the test evaluation indicator corresponding to each test scenario according to the second trigger time point issued by the environment perception system and the second vehicle data detected by the true value test device; The test result generation module 503 is used to obtain the perception performance test result of the environmental perception system according to the ideal evaluation index and all the test evaluation indexes.

[0071] In some possible embodiments, before the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, the method further includes: Acquire the first pose data of the target object determined by the true value test device and the second pose data of the target object determined by the environment perception system, and perform normalization processing on the first pose data and the second pose data respectively; Inputting the normalized first pose data and the normalized second pose data into a preset deep learning model to obtain the similarity between the first pose data and the second pose data; wherein the preset deep learning model is trained by at least two groups of sample pose data and similarity labels corresponding to each group of sample pose data; The test vehicle is controlled by the autonomous driving robot to drive toward the target object according to the preset first driving data, including: When it is detected that the similarity exceeds a preset similarity threshold, the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data.

[0072] In some possible embodiments, the preset first driving data includes a preset driving speed and a preset relative distance; Before obtaining the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: When the test vehicle is in a stopped state, an initial distance between the test vehicle and the target object is obtained, and a test starting point position is determined according to the initial distance and a preset relative distance; After the test vehicle is in a driving state, the current speed of the test vehicle is obtained at a preset time interval, and when any current speed is detected to be consistent with a preset driving speed, it is determined whether the test vehicle has traveled to the test starting point; When the test vehicle drives to the test starting point, the starting time point is obtained.

[0073] In some possible embodiments, the first vehicle data includes a first vehicle position of the test vehicle at a first trigger time point; According to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test equipment, the ideal evaluation index is obtained, including: Calculate the ideal trigger time according to the first trigger time point and the starting time point issued by the environmental perception system; Obtaining a braking distance between the first vehicle position and the target object, and calculating a first ideal trigger distance according to the braking distance and a preset relative distance; The ideal trigger time and the first ideal trigger distance are used as ideal evaluation indicators.

[0074] In some possible embodiments, after obtaining an ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: The autonomous driving robot controls the test vehicle to drive toward the target object according to the preset second driving data, and calculates the second ideal trigger distance according to the third vehicle data detected by the true value test device and the preset relative distance; An ideal braking triggering curve is generated according to the first ideal triggering distance, the second ideal triggering distance, the preset first driving data, and the preset second driving data.

[0075] In some possible embodiments, the test evaluation indicators corresponding to each test scenario include a test trigger time and a test trigger distance; According to the ideal evaluation index and all test evaluation indexes, the perception performance test results of the environmental perception system are obtained, including: According to the ideal trigger time and each test trigger time, the corresponding initial time decay rate is obtained, and the target time decay rate is calculated based on all the initial time decay rates; According to the first ideal trigger distance and each test trigger distance, a corresponding initial distance decay rate is obtained, and a target distance decay rate is calculated based on all initial distance decay rates; A first score corresponding to the target time decay rate and the target distance decay rate is queried in a preset decay rate-score correspondence table, and the perception performance test result of the environmental perception system is obtained based on the first score; wherein the preset decay rate-score correspondence table includes at least two standard scores, a standard time decay rate and a standard distance decay rate corresponding to each standard score.

[0076] In some possible embodiments, obtaining a perception performance test result of the environment perception system according to the first score includes: The number of non-triggering times is counted according to all test triggering times, and the target non-triggering rate is calculated based on the number of non-triggering times and the total number of tests corresponding to all test triggering times; A second score corresponding to the target non-trigger rate is searched in a preset non-trigger rate-score correspondence table; wherein the preset non-trigger rate-score correspondence table includes at least two standard scores and a standard non-trigger rate corresponding to each standard score; The first score and the second score are weighted and summed according to preset weights to obtain a target score, and the evaluation level corresponding to the target score is used as the perception performance test result of the environmental perception system.

[0077] See also Figure 6 , Figure 6A schematic structural diagram of another vehicle perception performance testing device based on an environmental perception system provided in an embodiment of the present application is shown.

[0078] like Figure 6 As shown, the whole vehicle perception performance testing device 600 based on the environment perception system may include at least one processor 601 , at least one network interface 604 , a user interface 603 , a memory 605 and at least one communication bus 602 .

[0079] The communication bus 602 may be used to realize the connection and communication among the above-mentioned components.

[0080] The user interface 603 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0081] The network interface 604 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0082] Among them, the processor 601 may include one or more processing cores. The processor 601 uses various interfaces and lines to connect the various parts in the whole vehicle perception performance test device 600 based on the environmental perception system, and executes various functions and processes data of the whole vehicle perception performance test device 600 based on the environmental perception system by running or executing instructions, programs, code sets or instruction sets stored in the memory 605, and calling the data stored in the memory 605. Optionally, the processor 601 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor 601 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application program; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 601, and it can be implemented by a single chip.

[0083] The memory 605 may include a RAM or a ROM. Optionally, the memory 605 includes a non-transitory computer-readable medium. The memory 605 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 605 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 605 may optionally be at least one storage device located away from the aforementioned processor 601. As Figure 6As shown, the memory 605 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a vehicle perception performance test application based on an environmental perception system.

[0084] Specifically, the processor 601 may be used to call the vehicle perception performance test application based on the environment perception system stored in the memory 605, and specifically perform the following operations: When the target object is in the ideal scene, the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, and obtains the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test equipment; After at least two test scenarios are determined based on the ideal scenario, the autonomous driving robot controls the test vehicle to drive toward the target object in each test scenario according to the preset first driving data, and obtains the test evaluation index corresponding to each test scenario according to the second trigger time point issued by the environment perception system and the second vehicle data detected by the true value test device; According to the ideal evaluation index and all the test evaluation indexes, the perception performance test results of the environmental perception system are obtained.

[0085] In some possible embodiments, before the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, the method further includes: Acquire the first pose data of the target object determined by the true value test device and the second pose data of the target object determined by the environment perception system, and perform normalization processing on the first pose data and the second pose data respectively; Inputting the normalized first pose data and the normalized second pose data into a preset deep learning model to obtain the similarity between the first pose data and the second pose data; wherein the preset deep learning model is trained by at least two groups of sample pose data and similarity labels corresponding to each group of sample pose data; The test vehicle is controlled by the autonomous driving robot to drive toward the target object according to the preset first driving data, including: When it is detected that the similarity exceeds a preset similarity threshold, the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data.

[0086] In some possible embodiments, the preset first driving data includes a preset driving speed and a preset relative distance; Before obtaining the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: When the test vehicle is in a stopped state, an initial distance between the test vehicle and the target object is obtained, and a test starting point position is determined according to the initial distance and a preset relative distance; After the test vehicle is in a driving state, the current speed of the test vehicle is obtained at a preset time interval, and when any current speed is detected to be consistent with a preset driving speed, it is determined whether the test vehicle has traveled to the test starting point; When the test vehicle drives to the test starting point, the starting time point is obtained.

[0087] In some possible embodiments, the first vehicle data includes a first vehicle position of the test vehicle at a first trigger time point; According to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test equipment, the ideal evaluation index is obtained, including: Calculate the ideal trigger time according to the first trigger time point and the starting time point issued by the environmental perception system; Obtaining a braking distance between the first vehicle position and the target object, and calculating a first ideal trigger distance according to the braking distance and a preset relative distance; The ideal trigger time and the first ideal trigger distance are used as ideal evaluation indicators.

[0088] In some possible embodiments, after obtaining an ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: The autonomous driving robot controls the test vehicle to drive toward the target object according to the preset second driving data, and calculates the second ideal trigger distance according to the third vehicle data detected by the true value test device and the preset relative distance; An ideal braking triggering curve is generated according to the first ideal triggering distance, the second ideal triggering distance, the preset first driving data, and the preset second driving data.

[0089] In some possible embodiments, the test evaluation indicators corresponding to each test scenario include a test trigger time and a test trigger distance; According to the ideal evaluation index and all test evaluation indexes, the perception performance test results of the environmental perception system are obtained, including: According to the ideal trigger time and each test trigger time, the corresponding initial time decay rate is obtained, and the target time decay rate is calculated based on all the initial time decay rates; According to the first ideal trigger distance and each test trigger distance, a corresponding initial distance decay rate is obtained, and a target distance decay rate is calculated based on all initial distance decay rates; A first score corresponding to the target time decay rate and the target distance decay rate is queried in a preset decay rate-score correspondence table, and the perception performance test result of the environmental perception system is obtained based on the first score; wherein the preset decay rate-score correspondence table includes at least two standard scores, a standard time decay rate and a standard distance decay rate corresponding to each standard score.

[0090] In some possible embodiments, obtaining a perception performance test result of the environment perception system according to the first score includes: The number of non-triggering times is counted according to all test triggering times, and the target non-triggering rate is calculated based on the number of non-triggering times and the total number of tests corresponding to all test triggering times; A second score corresponding to the target non-trigger rate is searched in a preset non-trigger rate-score correspondence table; wherein the preset non-trigger rate-score correspondence table includes at least two standard scores and a standard non-trigger rate corresponding to each standard score; The first score and the second score are weighted and summed according to preset weights to obtain a target score, and the evaluation level corresponding to the target score is used as the perception performance test result of the environmental perception system.

[0091] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0092] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

Claims

1. A vehicle perception performance testing method based on an environmental perception system, characterized in that: include: When the target object is in the ideal scene, the autonomous driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, and obtains the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device; After at least two test scenarios are determined based on the ideal scenario, the test vehicle is controlled by the autonomous driving robot to drive toward the target object in each test scenario according to the preset first driving data, and a test evaluation index corresponding to each test scenario is obtained according to the second trigger time point issued by the environmental perception system and the second vehicle data detected by the true value test device; According to the ideal evaluation index and all the test evaluation indexes, the perception performance test result of the environmental perception system is obtained.

2. The method according to claim 1, characterized in that Before the self-driving robot controls the test vehicle to drive toward the target object according to the preset first driving data, the method further includes: Acquire the first pose data of the target object determined by the true value test device and the second pose data of the target object determined by the environment perception system, and perform normalization processing on the first pose data and the second pose data respectively; Inputting the normalized first pose data and the normalized second pose data into a preset deep learning model to obtain the similarity between the first pose data and the second pose data; wherein the preset deep learning model is trained by at least two groups of sample pose data and similarity labels corresponding to each group of sample pose data; The step of controlling the test vehicle by the autonomous driving robot to drive toward the target object according to the preset first driving data includes: When it is detected that the similarity exceeds a preset similarity threshold, the automatic driving robot controls the test vehicle to drive toward the target object according to the preset first driving data.

3. The method according to claim 1, characterized in that The preset first driving data includes a preset driving speed and a preset relative distance; Before obtaining the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: When the test vehicle is in a stopped state, obtaining an initial distance between the test vehicle and the target object, and determining a test starting point position according to the initial distance and the preset relative distance; After the test vehicle is in a driving state, the current speed of the test vehicle is obtained at a preset time interval, and when it is detected that any of the current speeds is consistent with the preset driving speed, it is determined whether the test vehicle has traveled to the test starting point; When the test vehicle travels to the test starting point, a starting point time point is acquired.

4. The method according to claim 3, characterized in that The first vehicle data includes a first vehicle position of the test vehicle at the first trigger time point; The method of obtaining an ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device includes: Calculate the ideal trigger time according to the first trigger time point sent by the environment perception system and the starting time point; Acquiring a braking distance between the first vehicle position and the target object, and calculating a first ideal trigger distance according to the braking distance and the preset relative distance; The ideal trigger time and the first ideal trigger distance are used as ideal evaluation indicators.

5. The method according to claim 4, characterized in that After obtaining the ideal evaluation index according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device, the method further includes: The autonomous driving robot controls the test vehicle to drive toward the target object according to the preset second driving data, and calculates the second ideal trigger distance according to the third vehicle data detected by the true value test device and the preset relative distance; An ideal braking triggering curve is generated according to the first ideal triggering distance, the second ideal triggering distance, the preset first driving data, and the preset second driving data.

6. The method according to claim 4, characterized in that The test evaluation indicators corresponding to each of the test scenarios include test trigger time and test trigger distance; The step of obtaining the perception performance test result of the environment perception system according to the ideal evaluation index and all the test evaluation indexes includes: According to the ideal trigger time and each of the test trigger times, a corresponding initial time decay rate is obtained, and a target time decay rate is calculated based on all the initial time decay rates; According to the first ideal trigger distance and each of the test trigger distances, a corresponding initial distance attenuation rate is obtained, and a target distance attenuation rate is calculated based on all the initial distance attenuation rates; A first score corresponding to the target time decay rate and the target distance decay rate is queried in a preset decay rate-score correspondence table, and a perception performance test result of the environmental perception system is obtained based on the first score; wherein the preset decay rate-score correspondence table includes at least two standard scores, a standard time decay rate and a standard distance decay rate corresponding to each standard score.

7. The method according to claim 6, characterized in that The obtaining of a perception performance test result of the environment perception system according to the first score includes: Counting the number of non-triggering times according to all the test triggering times, and calculating the target non-triggering rate based on the number of non-triggering times and the total number of tests corresponding to all the test triggering times; A second score corresponding to the target non-trigger rate is searched in a preset non-trigger rate-score correspondence table; wherein the preset non-trigger rate-score correspondence table includes at least two of the standard scores and a standard non-trigger rate corresponding to each of the standard scores; The first score and the second score are weighted and summed according to preset weights to obtain a target score, and the evaluation level corresponding to the target score is used as the perception performance test result of the environmental perception system.

8. A vehicle perception performance testing device based on an environmental perception system, characterized in that: include: A first indicator generating module is used for, when the target object is in an ideal scene, controlling the test vehicle by the autonomous driving robot to drive toward the target object according to the preset first driving data, and obtaining an ideal evaluation indicator according to the first trigger time point issued by the environment perception system and the first vehicle data detected by the true value test device; A second indicator generating module is used to, after determining at least two test scenarios based on the ideal scenario, control the test vehicle by the autonomous driving robot to drive toward the target object in each of the test scenarios according to the preset first driving data, and obtain a test evaluation indicator corresponding to each of the test scenarios according to the second trigger time point issued by the environment perception system and the second vehicle data detected by the true value test device; The test result generation module is used to obtain the perception performance test result of the environmental perception system based on the ideal evaluation index and all the test evaluation indexes.

9. A vehicle perception performance testing device based on an environmental perception system, characterized in that: including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Images