Method and test field for testing autonomous vehicles based on expected functional safety

Abstract

The application provides a kind of automatic driving vehicle test method and test field based on expected function safety, and the method comprises: make the vehicle to be tested enter first test test field, second test test field and third test test field in turn for testing;Obtain the real-time vehicle driving data information of the vehicle to be tested driving in first test test field, second test test field and third test test field respectively;Compare real-time vehicle driving data information with preset evaluation table, obtain the rating information of the vehicle to be tested.The application is based on real vehicle scene, can effectively test the expected function safety of automatic driving vehicle in township road, highway and urban expressway scene, make up the major defects of unstable performance and imperfect function of automatic driving vehicle, and also can judge the robust performance of camera and other sensors of automatic driving vehicle based on the evaluation result of this scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electronics, and particularly relates to a test method and a test field for an autonomous vehicle based on expected functional safety. BACKGROUND

[0002] The expected functional safety problem of an autonomous vehicle is derived from the performance limitation and functional deficiency of an autonomous driving system. The performance limitation and functional deficiency of the autonomous driving system will bring potential hazard risks to the vehicle. Under such risks, once the vehicle encounters a scene triggering the hazard (a known scene or an unknown scene containing a triggering condition), a hazard event will occur. If no measures are taken to effectively control the hazard event, harm and loss will be caused. However, at present, intelligent connected vehicles claiming to have "assisted driving" or "autonomous driving" functions in China are still not fully capable of correctly responding to the complex expected functional safety problems. In recent years, a number of different models of vehicles of several vehicle manufacturers have caused a number of accidents resulting from expected functional safety problems in China, which not only caused huge losses, but also seriously affected the confidence of the society in the intelligent connected vehicle industry and products. Therefore, there are two industry problems to be solved: one is to explore a method to solve the expected functional safety problem of intelligent connected vehicles in the development stage; the other is to prove the reliability of the expected functional safety through a reasonable test evaluation system in the test and verification stage.

[0003] At present, there are mainly two types of ideas for the research of expected functional safety. One is to continue the idea of functional safety, which is to identify the problems of a specific system in a small range based on engineering experience, and to identify the corresponding risk scene and solve it in a targeted manner. The other is to start from the analysis of the scene, which is no longer limited to a specific function or system, and more widely finds the general scene problem from the elements of the scene. The advantage of the former is that through the systematic analysis method, it is easier to find the hazard scene of this specific system in a limited range, which can better guarantee the effectiveness of the scene. The advantage of the latter is that although it does not completely follow the analysis of the expected functional safety standard, it can guarantee the comprehensiveness of the hazard scene identification from a broader perspective. At present, neither of the two has summarized a large number of conclusive solutions, so in the short term, the two research ideas will coexist and complement each other.

[0004] From the perspective of scene analysis, there are more non-motor vehicles in the township area, and the non-motor vehicles often appear in parallel with the vehicles, especially in the case of direct sunlight, which will cause great interference to the vehicle camera. At this time, the lane changing function of the vehicle automatic driving function will also be greatly challenged, and traffic accidents are easy to occur. In addition, some special scenes of expressways and urban expressways are also typical road dangerous scenes for automatic driving vehicles. Safety accidents caused by the inability to identify the front traffic construction signs and traffic cones on the expressway occur from time to time, and a large number of logistics vehicles carrying goods are running on the expressway, plus some passenger cars with roof or trunk carrying goods or luggage, which is easy to appear the scene of paper box falling, causing traffic accidents. Therefore, how to test the risk recognition ability of the automatic driving system of the automatic driving vehicle in the township area traffic scene, the expressway scene and other special scenes is a problem to be solved at present. SUMMARY

[0005] The present application aims to solve one of the above problems.

[0006] The main purpose of the present application is to provide a kind of automatic driving vehicle test method based on expected function safety.

[0007] Another purpose of the present application is to provide a kind of automatic driving vehicle test field based on expected function safety.

[0008] In order to achieve the above purpose, the technical scheme of the present application is as follows:

[0009] The present application provides an automatic driving vehicle test method based on expected function safety, which comprises: making the vehicle to be tested enter a first test test field, a second test test field and a third test test field in turn, wherein the first test test field is a lane changing test field under strong light, and the first test test field comprises at least two lanes and a light simulation device; the second test test field is a traffic construction sign recognition test field under dust raising, and the second test test field comprises at least two lanes, a traffic construction sign and a dust raising simulation device; the third test test field is a dynamic falling object recognition test field, and the third test test field comprises at least one lane and a falling object loading vehicle; obtaining real-time vehicle driving data information of the vehicle to be tested driving in the first test test field, the second test test field and the third test test field; comparing the real-time vehicle driving data information with a preset evaluation table to obtain the rating information of the vehicle to be tested.

[0010] Another aspect of the present application provides an automatic driving vehicle test field based on expected functional safety, comprising: a central control unit, a data collection unit, a data analysis unit, a first test test field, a second test test field and a third test test field; the central control unit is used for making the vehicle to be tested enter the first test test field, the second test test field and the third test test field in turn, wherein the first test test field is a lane change test field under strong light, and the first test test field comprises at least two lanes and a light simulation device; the second test test field is a traffic construction sign recognition test field under dust raising, and the second test test field comprises at least two lanes, a traffic construction sign and a dust raising simulation device; the third test test field is a dynamic thrown object recognition test field, and the third test test field comprises at least one lane and a thrown object loading vehicle; the data collection unit is used for acquiring real-time vehicle driving data information of the vehicle to be tested driving in the first test test field, the second test test field and the third test test field respectively; and the data analysis unit is used for comparing the real-time vehicle driving data information with a preset evaluation table to obtain rating information of the vehicle to be tested.

[0011] As can be seen from the technical solutions of the present application, the present application provides an automatic driving vehicle test method and test field based on expected functional safety, mainly considering the scenes in rural areas and special scenes such as highways and urban expressways. In the conditions of more non-motor vehicles on rural area highways and interference of sunlight on vehicle cameras, the ability of the vehicle to automatically change lanes is tested; and in the special scenes of traffic road construction and thrown objects in front of vehicles on highways and urban expressways, the response ability of the vehicle to automatically drive is tested. The present application simulates complex scenes such as strong light, dust raising, traffic construction and object throwing, builds a closed site test environment, formulates corresponding test methods and evaluation standards according to different test fields, obtains a complete site test process, effectively tests the expected functional safety of the automatic driving vehicle, and provides an important basis for the unstable performance and imperfect function of the automatic driving vehicle. The present application does not require additional operations by designers through the application of automatic scene recognition and evaluation of scenes and test triggering events. In summary, the present application can effectively test the expected functional safety of the automatic driving vehicle in the scenes of rural roads, highways and urban expressways based on real vehicle scenes, which makes up for the major defects of unstable performance and imperfect function of the automatic driving vehicle, and also can judge the robust performance of the camera and other sensors of the automatic driving vehicle based on the evaluation results of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and all other drawings obtained by those skilled in the art without creative effort based on these drawings also belong to the protection scope of the present application.

[0013] Figure 1 The flow chart of the automatic driving vehicle test method based on expected functional safety provided for the embodiment 1 of the present application is shown in FIG. 1.

[0014] Figure 2 The structural schematic diagram of the automatic driving vehicle test field based on expected functional safety provided for the embodiment 1 of the present application is shown in FIG. 2.

[0015] Figure 3 The simulation scene diagram of the lane change test field under strong light provided for the embodiment 1 of the present application is shown in FIG. 3.

[0016] Figure 4 The simulation scene diagram of the lane change test field under strong light with obstacle vehicle provided for the embodiment 1 of the present application is shown in FIG. 4.

[0017] Figure 5 The simulation scene diagram of the traffic construction sign recognition test under dust provided for the embodiment 1 of the present application is shown in FIG. 5.

[0018] Figure 6 The simulation scene diagram of the dynamic falling object recognition test field provided for the embodiment 1 of the present application is shown in FIG. 6. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative effort belong to the protection scope of the present application.

[0020] In the description of the present application, it should be understood that the terms “center”, “longitudinal”, “transverse”, “upper”, “lower”, “front”, “rear”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inner”, “outer” and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms “first” and “second” are only for the purpose of description, and cannot be understood as indicating or implying relative importance or quantity or position.

[0021] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connecting" should be understood in a broad sense, for example, can be fixed connection, can also be detachable connection, or integrally connected; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0022] The embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0023] Embodiment 1

[0024] The present embodiment provides a kind of automatic driving vehicle test method based on expected function safety, as shown in Fig. Figure 1 The method comprises:

[0025] Step S101, make the vehicle to be tested enter first test test field, second test test field and third test test field in turn, wherein the first test test field is the lane change test field under strong light, and the first test test field includes at least two lanes and light simulation device;Second test test field is the traffic construction sign recognition test field under dust, and the second test test field includes at least two lanes, traffic construction sign and dust simulation device;The third test test field is dynamic thrown object recognition test field, and the third test test field includes at least one lane and thrown object loading vehicle;Specifically, the first test test field, the second test test field and the third test test field can be built into a closed field real vehicle test environment to prevent external factors from interfering with the test results. The first test test field simulates the scene when the vehicle-mounted camera is disturbed by strong sunlight intensity through the light simulation device;The dust simulation device of the second test test field can simulate the scene of dust weather;The third test test field simulates the scene that the front car drops objects on the highway or other expressway. Since the first test test field and the second test test field involve lane change of vehicle, the first test test field and the second test test field should include at least two lanes, and the third test test field should include at least one lane, in order to better test the ability of the vehicle, a plurality of lanes can also be provided to simulate more complex test conditions. In addition, the present application only lists several typical cases, as long as it is within the scope that can be tested in the first test test field, the second test test field and the third test test field of the present application, it should be within the protection scope of the present application.

[0026] In step S102, real-time vehicle driving data information of the vehicle to be tested driving in the first test site, the second test site and the third test site is obtained. Specifically, the test site can be equipped with measuring equipment, monitoring equipment and sensing equipment and other detection equipment. By reasonably configuring the hardware and software of these detection equipment, the motion state and video data of the vehicle to be tested during the test process can be recorded. The vehicle motion state data to be detected and recorded can include the speed, deceleration, deceleration rate, lateral offset speed, lateral distance from the center line of the lane, relative distance from the target object, whether the impact occurs and the like. During the actual test process, different test conditions can be selected and combined.

[0027] In step S103, the real-time vehicle driving data information is compared with the preset evaluation table to obtain the rating information of the vehicle to be tested. Specifically, the motion state and video data obtained in step S102 need to be evaluated. The evaluation table can be set in advance. The evaluation table sets the motion state parameters to be evaluated, the reference values of the parameters, the weights of the parameters and the like. The motion state data is compared with the corresponding reference values. The comprehensive evaluation result is obtained by combining the comparison results of each motion state data and the weights of each motion state data. In addition, in the specific embodiment, the test can be performed in sequence according to the test site. The test data is recorded and saved. The test result is rated according to the corresponding evaluation table. Finally, the test report is output. According to the above steps S101-S103, the test can be repeated for each test site. The results of multiple tests are comprehensively evaluated to achieve more accurate evaluation results.

[0028] The automatic driving vehicle test method based on expected function safety of the embodiment mainly considers the scenes in town areas and special scenes such as highways and urban expressways. For the road conditions of the town area highway with more non-motor vehicles and under the condition that the sunlight directly strikes the vehicle camera and causes interference, the ability of the vehicle automatic driving function to change lanes is tested. For the special scenes of traffic road construction and the front vehicle goods spilling often appearing on the highway and urban expressway, the response ability of the vehicle automatic driving function is tested. The embodiment simulates complex scenes such as strong light, dust, traffic construction and article spilling, builds a closed site real vehicle test environment, formulates corresponding test methods and evaluation standards according to different test fields, obtains a complete site test process, effectively tests the expected function safety of the automatic driving vehicle, and provides an important basis for the unstable performance and imperfect function of the automatic driving vehicle. The automatic scene recognition and evaluation scene and the test triggering event are applied in the example, and the designer does not need to perform additional operations. In summary, the application based on the real vehicle scene can effectively test the expected function safety of the automatic driving vehicle in the scenes such as the town road, the highway and the urban expressway, make up for the major defects of the unstable performance and the imperfect function of the automatic driving vehicle, and also can judge the robust performance of the camera and other sensors of the automatic driving vehicle based on the evaluation results of the scheme.

[0029] In an optional embodiment of the embodiment, the entering of the vehicle to be tested into the first test field for testing specifically includes: turning on the light simulation device, and setting the illumination to be between L1 (Lux) and L2 (Lux), wherein L1 (Lux) and L2 (Lux) represent the minimum and maximum values of the light intensity; making the vehicle to be tested travel at a first speed; sending a lane changing instruction to the left or right to the vehicle to be tested; and acquiring real-time vehicle driving data information of the vehicle to be tested traveling in the first test field, specifically including: acquiring at least the speed, deceleration, deceleration rate, lateral offset speed and lateral distance from the center line of the vehicle to be tested within a first preset time period after receiving the lane changing instruction.

[0030] Specifically, in this embodiment, the recognition ability of the vehicle to be tested to the lane under the condition of strong direct light is mainly tested. The light intensity can be set to 20000-35000 lux, simulating the sunlight from 15:00 to 17:00, and the light source angle is 45°, and of course other light intensities can be selected according to the needs of the test. The speed of the vehicle to be tested, i.e. the first speed, is set to 30 km / h, and the lane changing instruction can be left lane changing or right lane changing, which is determined according to the lane conditions of the first test field. In this test, there are no other interference objects except the vehicle to be tested. The first preset time period can be determined according to the time required for lane changing, for example, the first preset time period can be set to 15s, or the first preset time period can be set from the beginning of the test to the end of the test. In the actual test process, the vehicle to be tested can be accelerated from a standstill to 30 km / h in the middle of the lane and kept stable, and the automatic driving function is started to drive at a constant speed. After the vehicle to be tested is stably driven in the straight lane for 2s, a lane changing instruction can be sent to the vehicle to be tested remotely, or a driver equipped in the vehicle (only if the driver is equipped) can issue a lane changing instruction according to the vehicle user manual. If the vehicle to be tested can successfully change lanes autonomously or drive within the line after lane changing, or the vehicle to be tested does not respond, the test is ended, and the test is repeated 3 times. The test data is recorded throughout the test, and the test data includes at least the speed, deceleration, deceleration rate, lateral offset speed, lateral distance from the center line of the lane, and whether the impact occurs, etc.

[0031] In an optional embodiment of the present embodiment, the first test field further includes a first obstacle vehicle; the first obstacle vehicle drives at a second speed in the left lane or the right lane of the lane where the vehicle to be tested is located, wherein the second speed is the same as the first speed; sending a left or right lane changing instruction to the vehicle to be tested includes: if the first obstacle vehicle is in the left lane of the lane where the vehicle to be tested is located, sending a left lane changing instruction to the vehicle to be tested; if the first obstacle vehicle is in the right lane of the lane where the vehicle to be tested is located, sending a right lane changing instruction to the vehicle to be tested.

[0032] In the embodiment, a first obstacle vehicle is added in the first test field as an obstacle to comprehensively detect the lane changing ability of the vehicle to be tested under strong light. The first obstacle vehicle can be a small vehicle such as a bicycle, an electric bicycle, or a motorcycle, and travels in the blind area of the vehicle to be tested. The second speed of the first obstacle vehicle is the same as the first speed, which can be set to 30 km / h, so that the vehicle to be tested and the first obstacle vehicle can follow each other for a period of time. The first obstacle vehicle can be placed in the left lane or the right lane of the lane where the vehicle to be tested is located, depending on the lane conditions of the test field. In the specific test process, the vehicle to be tested can be accelerated from a standstill to 30 km / h in the middle of the lane and kept stable, and the automatic driving function is started to move at a constant speed. The first obstacle vehicle is accelerated from a standstill to 30 km / h in the left lane or the right lane of the lane to be tested and kept stable. In order to better test the recognition ability of the vehicle to be tested to the blind area vehicle, the first obstacle vehicle can follow the vehicle to be tested at a rear position. After the first obstacle vehicle and the vehicle to be tested follow each other stably in the straight lane for 2s, a lane changing instruction can be sent to the vehicle to be tested remotely, or a lane changing instruction can be issued by the driver equipped in the vehicle (only if the driver is equipped) according to the vehicle user manual. If the vehicle to be tested suppresses lane changing or issues an alarm, the test is ended, and the test is repeated 3 times. The test data is recorded throughout the test, and the test data at least includes the speed, deceleration, deceleration rate, lateral offset speed, lateral distance from the center line of the lane, relative distance from the target, whether the impact occurs, and the like.

[0033] In an optional embodiment of the present embodiment, the traffic construction marker includes at least one traffic sign and a plurality of traffic cones, and the traffic construction markers are uniformly placed in the lane; the vehicle to be tested enters the second test field for testing, specifically including: starting the dust simulation device; causing the vehicle to be tested to travel in the lane where the traffic construction markers are located, and traveling at a third speed at a constant speed when the vehicle to be tested travels to a distance of S1 meters from the first traffic construction marker; obtaining real-time vehicle driving data information of the vehicle to be tested traveling in the second test field, specifically including: obtaining at least the speed, deceleration, deceleration rate, lateral offset speed, lateral distance from the center line of the lane, and lateral relative distance from the traffic construction marker of the vehicle to be tested within a second preset time period after the vehicle to be tested travels to a distance of S1 meters from the first traffic construction marker.

[0034] Specifically, in this embodiment, the test is mainly to test the recognition ability of the to-be-tested vehicle to the traffic construction sign in the environment with low visibility caused by dust. The second test test field requires at least a two-lane road, traffic cones and traffic signs are placed in a lane according to the traffic control requirements of the long-term construction area, the cone barrel has an inclination angle of 45°, the number of cones can be 6, the interval between the cones is 1m, and the site is accompanied by dust caused by the dust simulation device. The third speed can be set to 40km / h or 60km / h, which is set according to different test conditions. S1 can be set to 50m, and the second preset time period is determined according to the third speed and S1. For example, if the third speed is set to 40km / h, the second preset time period should be at least greater than 4.5s. In the specific implementation process, first, turn on the dust simulation device to cause dust conditions, and then make the to-be-tested vehicle drive in the lane where the traffic construction sign is located. The to-be-tested vehicle starts from a standstill and accelerates to 40 or 60km / h, and drives to a distance of 50m from the first traffic construction sign. At this time, the to-be-tested vehicle starts the automatic driving function, maintains the set speed, and gradually approaches the traffic construction sign area. If the to-be-tested vehicle detects that the traffic cone in front of the driving path blocks the road and actively deviates or stops, or collision or driver intervention occurs, the test is ended, and the test is repeated 3 times. The test data is recorded throughout the test, and the test data should at least include the speed, deceleration, deceleration rate, lateral deviation speed, lateral distance from the center line of the lane, relative distance from the target, whether the impact occurs, and the like.

[0035] In an optional embodiment of the present embodiment, the to-be-tested vehicle entering the third test test field for testing specifically includes: making the throwing object loading vehicle drive at a fourth speed, and making the to-be-tested vehicle drive at a fifth speed in the lane where the throwing object loading vehicle is located, and the to-be-tested vehicle drives behind the throwing object loading vehicle at a distance of S2 meters, wherein the fourth speed and the fifth speed are the same; after the to-be-tested vehicle follows the throwing object loading vehicle for N seconds, the throwing object loading vehicle throws at least one throwing object to the rear of the vehicle on the lane; and the real-time vehicle driving data information of the to-be-tested vehicle driving in the third test test field is obtained, specifically including: at least obtaining the speed, deceleration, deceleration rate, lateral deviation speed, lateral distance from the center line of the lane, and relative distance from the throwing object of the to-be-tested vehicle within a third preset time period after the throwing object loading vehicle throws the throwing object to the rear of the vehicle.

[0036] Specifically, in this embodiment, the main test is the recognition and processing ability of the vehicle to be tested when the front vehicle suddenly throws objects backward. In this embodiment, the thrown object can be an object such as a carton, and the fourth speed can be set to 30 km / h or 50 km / h, which is set according to different test conditions. The fifth speed is the same as the fourth speed. The thrown object loading vehicle and the vehicle to be tested are kept in the same lane at the same speed, and the carton throwing device is fixed on the roof of the thrown object loading vehicle. S2 can be determined according to the adaptive cruise distance, which can be set to 80-100 m. N seconds can be set to 3 s. The third preset period can be determined according to S2 and the fourth speed, for example, when S2 is set to 100 m and the fourth speed is set to 30 km / h, the third preset period should be at least greater than 12 s. The test scene can be set on a 3 km long two-lane road. In the specific implementation process, the target thrown object loading vehicle travels at a set fifth speed, the vehicle to be tested follows the target thrown object loading vehicle in the same lane from a stationary start, and travels at a fourth speed when it reaches S2 meters from the thrown object loading vehicle. After the vehicle to be tested has been following the vehicle for 3 s, the thrown object loading vehicle controls the carton throwing device to throw the carton backward, and if the vehicle to be tested actively deviates, stops, or collides or the driver intervenes, the test is ended. According to different test conditions, test 3 times respectively, record the test data throughout the test, and the test data should at least include the speed, deceleration, deceleration change rate, lateral deviation speed, lateral distance from the center line of the lane, relative distance from the target object, whether the collision occurs, and the like.

[0037] The present embodiment also provides an automatic driving vehicle test field based on expected functional safety. The test field of the present embodiment is used to perform the automatic driving vehicle test method based on expected functional safety described above. Here, only the specific settings of the test field are simply described, and other matters not fully described are described in the foregoing description of the automatic driving vehicle test method based on expected functional safety. The system architecture of the test field is as follows Figure 2As shown, it comprises: a central control unit 201, a data collection unit 202, a data analysis unit 203, a first test test field 204, a second test test field 205 and a third test test field 206. The central control unit 201, the data collection unit 202 and the data analysis unit 203 can be integrated on one device, or can be respectively arranged in different devices. When the central control unit 201, the data collection unit 202 and the data analysis unit 203 are respectively arranged in different devices, the mutual communication between the three can be completed through wireless or wired mode. One set of system composed of the central control unit 201, the data collection unit 202 and the data analysis unit 203 can be arranged in the first test test field 204, the second test test field 205 and the third test test field 206 respectively, or a set of system composed of the central control unit 201, the data collection unit 202 and the data analysis unit 203 can be shared.

[0038] The central control unit 201 is used for making the vehicle to be tested enter the first test test field 204, the second test test field 205 and the third test test field 206 in turn, wherein the first test test field 204 is a lane change test field under strong light, and the first test test field 204 at least includes two lanes and a light simulation device; the second test test field 205 is a traffic construction sign recognition test field under dust, and the second test test field 205 at least includes two lanes, a traffic construction sign and a dust simulation device; the third test test field 206 is a dynamic falling object recognition test field, and the third test test field 206 at least includes one lane and a falling object loading vehicle; specifically, the first test test field 204, the second test test field 205 and the third test test field 206 can be built into a closed field real vehicle test environment to prevent external factors from affecting the test results. The first test test field 204 simulates the scene of interference to the vehicle-mounted camera when the sunlight intensity is large through the light simulation device; the dust simulation device of the second test test field 205 can simulate the scene of dust weather; the third test test field 206 simulates the scene of the falling object of the front vehicle on the expressway or other expressway. Since the first test test field 204 and the second test test field 205 both involve lane change driving of the vehicle, the first test test field 204 and the second test test field 205 should at least include two lanes, and the third test test field 206 should include at least one lane, in order to better test the ability of the vehicle, a plurality of lanes can also be arranged to simulate more complex test conditions. In addition, the present application only lists several typical cases, as long as it is within the scope of the first test test field 204, the second test test field 205 and the third test test field 206 of the present application, it should be within the protection scope of the present application.

[0039] The data collection unit 202 is configured to acquire real-time vehicle driving data information of the vehicle to be tested driving on the first test site 204, the second test site 205 and the third test site 206 respectively. Specifically, the test site can be equipped with measuring devices, monitoring devices and sensing devices, etc. By reasonably configuring the hardware and software of these detection devices, the motion state and video data of the vehicle to be tested during the test process can be recorded. The vehicle motion state data to be detected and recorded can include the speed, deceleration, deceleration rate, lateral offset speed, lateral distance from the center line of the lane, relative distance from the target object, whether the impact occurs, etc. During the actual test process, different test conditions can be selected and combined according to different test conditions.

[0040] The data collection unit 202 can include a plurality of measuring tools, sensing tools and image acquisition devices for measuring and collecting data of the vehicle to be tested during driving, and collecting video and image data of the vehicle to be tested during driving. The data collection unit 202 sends the data to the data analysis unit 203 through wired or wireless mode.

[0041] The data analysis unit 203 is configured to compare the real-time vehicle driving data information with a preset evaluation table to obtain the rating information of the vehicle to be tested. Specifically, the motion state and video data obtained by the data collection unit 202 need to be evaluated. An evaluation table can be set in advance, which sets the motion state parameters to be evaluated, the reference values of the parameters, the weights of the parameters, etc. The motion state data is compared with the corresponding reference values, and the comprehensive evaluation result is obtained by combining the comparison result of each motion state data and the weight of each motion state data. When receiving the real-time vehicle driving data information sent by the data collection unit 202, the data analysis unit 203 finds the corresponding evaluation table, compares the real-time vehicle driving data information with the parameters and values in the evaluation table one by one, and finally obtains the evaluation information of the vehicle to be tested. In addition, in the specific embodiment, the test can be carried out in sequence according to the test site, the test data is recorded and saved, the test result is rated according to the corresponding evaluation table, and finally the test report is output. And for each test condition of each test site, multiple tests are carried out, and the results of multiple tests are comprehensively evaluated to achieve more accurate evaluation results.

[0042] The automatic driving vehicle test field based on the expected function safety of the embodiment mainly considers the scenarios of town areas and special scenarios such as highways and urban expressways. For the road conditions of the town area where there are many non-motor vehicles, and under the condition that the sunlight directly interferes with the vehicle camera, the ability of the test vehicle to automatically change lanes is tested. For the special scenarios of traffic road construction and goods spilling of the front vehicle often appearing on the highway and urban expressway, the response ability of the automatic driving function of the vehicle is tested. The embodiment simulates complex scenes such as strong light, dust, traffic construction, and article spilling, builds a closed site real vehicle test environment, formulates corresponding test methods and evaluation standards according to different test fields, obtains a complete site test process, effectively tests the expected function safety of the automatic driving vehicle, and provides an important basis for the unstable performance and imperfect function of the automatic driving vehicle. The designer does not need to perform additional operations by applying automatic scene recognition and evaluating the scene and testing the triggering event. In summary, the application based on the real vehicle scene can effectively test the expected function safety of the automatic driving vehicle in the town road, highway and urban expressway and other scenes, make up for the major defects of the unstable performance and imperfect function of the automatic driving vehicle, and also can judge the robust performance of the camera and other sensors of the automatic driving vehicle based on the evaluation results of the scheme.

[0043] In an optional embodiment of the embodiment, the entering of the vehicle to be tested into the first test field for testing specifically includes: turning on the light simulation device, and setting the illumination to be between L1 (Lux) and L2 (Lux), wherein L1 (Lux) and L2 (Lux) represent the minimum and maximum values of the light intensity; making the vehicle to be tested travel at a first speed; sending a lane changing instruction to the left or right to the vehicle to be tested; and acquiring real-time vehicle driving data information of the vehicle to be tested traveling in the first test field, specifically including: acquiring at least the speed, deceleration, deceleration rate, lateral offset speed, and lateral distance from the center line of the lane of the vehicle to be tested within a first preset time period after receiving the lane changing instruction.

[0044] In an optional embodiment of the embodiment, the first test field further includes: a first obstacle vehicle; and the first obstacle vehicle travels at a second speed on the left lane or the right lane of the lane where the vehicle to be tested is located, wherein the second speed is the same as the first speed; and the sending of the lane changing instruction to the left or right to the vehicle to be tested includes: if the first obstacle vehicle is on the left lane of the lane where the vehicle to be tested is located, sending a lane changing instruction to the left to the vehicle to be tested; and if the first obstacle vehicle is on the right lane of the lane where the vehicle to be tested is located, sending a lane changing instruction to the right to the vehicle to be tested.

[0045] In an optional implementation of the embodiment, the traffic construction sign includes at least one traffic sign and a plurality of traffic cones, and the traffic construction sign is uniformly placed in the lane; the specific process that the vehicle to be tested enters the second test field for testing includes: starting the dust simulation device; driving the vehicle to be tested to travel in the lane where the traffic construction sign is located, and driving the vehicle to be tested to travel at a third speed when the vehicle to be tested travels to a position 1 m away from the first traffic construction sign; and acquiring real-time vehicle travel data information of the vehicle to be tested traveling in the second test field, specifically including: acquiring at least the speed, deceleration, deceleration rate, lateral deviation speed, lateral distance from the lane center line, and lateral relative distance from the traffic construction sign of the vehicle to be tested within a second preset time period after the vehicle to be tested travels to a position 1 m away from the first traffic construction sign.

[0046] In an optional implementation of the embodiment, the specific process that the vehicle to be tested enters the third test field for testing includes: driving the spreading vehicle to travel at a fourth speed, and driving the vehicle to be tested to travel in the lane where the spreading vehicle is located at a fifth speed, and the vehicle to be tested travels behind the spreading vehicle at a distance of S2 m, wherein the fourth speed is the same as the fifth speed; after the vehicle to be tested travels behind the spreading vehicle for N seconds, the spreading vehicle throws at least one spreading object to the rear of the vehicle; and the specific process of acquiring real-time vehicle travel data information of the vehicle to be tested traveling in the third test field includes: acquiring at least the speed, deceleration, deceleration rate, lateral deviation speed, lateral distance from the lane center line, and relative distance from the spreading object of the vehicle to be tested within a third preset time period after the spreading vehicle throws the spreading object to the rear of the vehicle.

[0047] The embodiment also provides a specific test operation scheme, in which the method flow and evaluation details of the test are refined, and the following is a detailed description of the test operation scheme.

[0048] For the test operation scheme, first, the test field is constructed and each test working condition is set, and the test steps are completed according to the test working condition.

[0049] As Figure 3The simulation scene of the lane change test field under strong light is shown. The test scene is used to evaluate the lane recognition ability of the automatic driving system of the automatic driving vehicle to be tested under strong light interference. The scene is completed in a strong light environment. A light simulation device with an illuminance of 20000-35000 lux is placed 70 meters in front of the vehicle to be tested to simulate the sunlight from 15:00 to 17:00. The light source has an irradiation angle of 45°. The vehicle to be tested travels at a speed of 30 km / h in the lane line towards the light source. The axis of the vehicle to be tested is not more than ±0.5 m away from the center line of the lane line. When receiving the lane change instruction input by the central control unit or the driver, the vehicle to be tested can correctly perform the lane change action according to the vehicle surrounding environment. Table 1 lists the test conditions required to be performed in the lane change test field under strong light.

[0050] Table 1 Test conditions of the lane change test field under strong light

[0051] Serial number Vehicle speed to be tested Lane changing direction Test number 1 30 km / h Left or right 3

[0052] The specific test steps are as follows: The speed of the vehicle to be tested is set to 30 km / h, and the automatic driving function is turned on to travel in a straight lane for more than 2s. The vehicle to be tested can receive the lane change instruction sent by the central control unit, or the driver equipped in the vehicle can manually input the lane change intention according to the requirements of the vehicle user manual (such as turning on the turn signal), to test whether the vehicle to be tested can correctly change lanes. If the vehicle to be tested maintains driving in the middle of the lane after completing the lane change and does not press the line, it is considered that this test condition is passed. If three tests are passed, it is considered that the vehicle to be tested passes this test.

[0053] As shown in Figure 4 , the simulation scene diagram of the lane change test field under strong light with obstacles is shown. The test is carried out on the premise that the vehicle to be tested successfully passes the lane change test field under strong light without obstacles in the above Figure 3 . If the test in the above Figure 3 is not passed, this test will not be implemented. The test is used to judge the recognition of the automatic driving system of the automatic driving vehicle to the rear obstacle vehicle (a scooter is used in this example) and the lane change decision ability in a strong light environment. A light simulation device with an illuminance of 20000-35000 lux is placed 70 meters in front of the test vehicle to simulate the sunlight from 15:00 to 17:00. The light source has an irradiation angle of 45°. The vehicle to be tested travels at a speed of 30 km / h in the lane line towards the light source. The axis of the vehicle to be tested is not more than ±0.5 m away from the center line of the lane line. When receiving the lane change instruction input by the central control unit or the driver, the test vehicle to be tested can correctly execute / inhibit the lane change action according to the vehicle surrounding environment. Table 2 lists the test conditions required to be performed in the lane change test field under strong light with obstacles.

[0054] Table 2. Lane changing test conditions under strong light with obstructed vehicles.

[0055] Serial number Vehicle speed to be tested Barrier vehicle speed Lane changing direction Test number 1 30 km / h 30 km / h Left or right 3

[0056] The specific test steps are as follows: Set the speed of the test vehicle and the target obstacle vehicle to 30 km / h. Activate the intelligent driving function of the test vehicle. The target obstacle vehicle drives within the blind spot of the adjacent lane on the left. After both vehicles have been driving stably for more than 2 seconds, the test vehicle can receive a lane-changing command from the central control unit, or the driver inside the vehicle can manually input the lane-changing intention (such as activating the turn signal) according to the vehicle owner's manual. This will test whether the test vehicle can suppress the lane change and whether it issues an alarm message. If the test vehicle suppresses the lane change and issues an alarm message, the test condition is considered passed. If all three tests are passed, the test vehicle is considered to have passed this test.

[0057] Figure 3 and Figure 4 The specific evaluation rules for the test scenarios are shown in Table 3. The two test scenarios mentioned above—lane change test under strong light with unobstructed vehicles and lane change test under strong light with obstructed vehicles—primarily assess the safety of the lane change decision support function of the test vehicle under strong light conditions, with a maximum score of 1.0 point. For the unobstructed vehicle scenario, if the test vehicle can change lanes correctly, it receives 0.5 points; for the obstructed vehicle scenario, if the test vehicle can suppress lane changes, it receives 0.5 points.

[0058] Table 3 Evaluation Rules for Lane Change Test Conditions under High Light Conditions

[0059]

[0060] like Figure 5 The image shows a simulated scenario of a test site for recognizing traffic construction signs under dust conditions. This test scenario is used to evaluate the autonomous driving system of the tested autonomous vehicle's autonomous driving capabilities in recognizing traffic construction signs ahead under dusty road conditions. The scenario was conducted in a dusty environment using a dust simulation device. The test vehicle activated its autonomous driving function and drove steadily at a set speed. Traffic cones and signs were placed in the lane a certain distance directly ahead of the vehicle's path, according to the traffic control requirements of a long-term road construction area. The cones were tilted at a 45° angle, with six cones spaced 1 meter apart. To ensure the validity of the test, the following conditions must be met throughout the entire test: the lateral distance between the longitudinal axis of the traffic cones and the longitudinal axis of the test vehicle does not exceed ±0.5 meters, and the lateral distance between the longitudinal axis of the test vehicle and the center line of the lane does not exceed ±0.5 meters.

[0061] The specific test steps are as follows: a plurality of construction traffic cone barrels are placed on the test road, and at least one traffic cone is ensured to be on the vehicle driving path. The test vehicle drives at a speed of 40 or 60 km / h on the lane where the traffic cone barrels are located, gradually approaches the area where the traffic cone barrels are located, and records the test data throughout the journey. If the test vehicle collides with the traffic cone barrels or avoids collision, the test is considered to be completed. If the test vehicle does not collide with the traffic cone barrels and successfully passes through the road section, it is considered that the test vehicle passes the test. If three tests are passed, it is considered that the test vehicle passes the test.

[0062] The dust under the traffic construction sign recognition test field scene respectively evaluates the safety index and the experience index, and the full score is 2 points. The safety index judges whether the test vehicle brakes and avoids collision, as shown in Table 4. If the test vehicle collides with the traffic construction sign, the test scene ends, the test experience index is 0 points, and the other test conditions of the scene are 0 points.

[0063] Table 4 Safety index evaluation details of dust under traffic construction sign recognition test field

[0064]

[0065] Note: Triggering AEB refers to the case where the maximum deceleration exceeds 6 m / s -2 , TTC (Time to Collision) represents the predicted collision time, and only the test vehicle with a driver has the item of “driver deviation”.

[0066] The experience index mainly judges the deceleration and deceleration rate of the test vehicle, as shown in Table 5. Each index accounts for 0.2 points in each test condition.

[0067] Table 5 Experience index evaluation details of dust under traffic construction sign recognition test field

[0068]

[0069] C1 and C2 are defined as follows:

[0070] The deceleration limit C1 of the test vehicle requires that when the speed of the test vehicle is greater than 72 km / h, the deceleration should not exceed 3.5 m / s 2 ; when the speed of the test vehicle is less than 18 km / h, the deceleration should not exceed 5 m / s 2 ; when the speed of the test vehicle is between 18 km / h and 72 km / h, the deceleration should change linearly.

[0071] The deceleration rate limit C2 of the test vehicle requires that when the speed of the test vehicle is greater than 72 km / h, the deceleration rate should not exceed 2.5 m / s3 When the vehicle speed under test is less than 18 km / h, the rate of change of deceleration should not exceed 5 m / s². 3 When the speed of the vehicle to be tested is between 18 km / h and 72 km / h, the rate of change of deceleration should change linearly.

[0072] like Figure 6 The diagram shows a simulated scenario of the dynamic spillage recognition test field. This test evaluates the autonomous driving system's ability to recognize spillage in front of the test vehicle. A cardboard box throwing device is fixed to the roof of the spillage loading vehicle. The test vehicle activates its intelligent driving function. After both vehicles maintain a stable speed, the cardboard box throwing device throws cardboard boxes, simulating a scenario where the test vehicle avoids an obstacle after a cardboard box falls from the vehicle in front during stable following. To ensure the validity of the test, the following conditions must be met throughout the test: the longitudinal axis lateral distance between the test vehicle and the target spillage loading vehicle should not exceed ±0.5m; the speeds of the test vehicle and the target spillage loading vehicle should be maintained within ±2km / h of the set speed. Table 6 lists the test conditions to be performed at the dynamic spillage recognition test field.

[0073] Table 6 Test conditions at the dynamic spillage recognition test site

[0074]

[0075] Note: ACC (Adaptive Cruise Control) refers to adaptive cruise control. The maximum following distance for ACC is generally 80-100m.

[0076] The specific test steps are as follows: The target material-distributing vehicle is driven at a set speed. The test vehicle is driven at a speed exceeding that of the target vehicle, and the intelligent driving function is activated, set to the maximum following distance. Once the test vehicle reaches the maximum following distance from the target material-distributing vehicle, it begins to drive at a set speed at a constant speed. After the test vehicle has stably followed the target material-distributing vehicle, the cardboard box distributing equipment throws the cardboard boxes. Valid data after the test vehicle stably follows the target material-distributing vehicle is recorded until the test vehicle collides with or avoids the cardboard boxes and successfully passes through the section of road. The test ends when the test vehicle successfully passes through the section of road without colliding with the cardboard boxes. If the test vehicle passes all three tests without colliding with the cardboard boxes, the test condition is considered passed. If all three tests are passed, the test vehicle is considered to have passed the test.

[0077] The dynamic spill recognition test scenario evaluates both safety and user experience metrics, with a maximum score of 7 points. The safety metrics assess whether the test vehicle changes lanes and avoids collisions, as shown in Table 7. If the test vehicle collides with the cardboard box, the entire test scenario ends, and the user experience metric for that test receives 0 points. Other untested conditions in this scenario also receive 0 points.

[0078] Table 7 Safety Indicators for Dynamic Spray Recognition Test Site

[0079]

[0080] The performance metric primarily evaluates the lateral acceleration of the test vehicle during lane-changing and obstacle-avoiding maneuvers, accounting for 0.2 points. If the lateral acceleration does not exceed 2.3 m / s² during the lane-changing and obstacle-avoiding process... 2 If the speed at any point exceeds 2.3 m / s, then 0.2 points are awarded. 2 If you do not pass, you will get 0 points.

[0081] The expected functional safety of highway scenarios was rated through two test scenarios: traffic construction sign recognition and dynamic spillage recognition. The full score is 9.0 points, as shown in Table 8.

[0082] Table 8 Evaluation Details for Two Test Scenarios in High-Speed ​​Scenarios

[0083]

[0084] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0085] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0086] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0087] In addition, each function unit in each embodiment of the present application can be integrated in one processing module, or each unit can be physically present separately, or two or more units can be integrated in one module. The integrated module can be realized in the form of hardware, or in the form of a software function module. When the integrated module is realized in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0088] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0089] In the description of the present specification, the description referring to the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0090] Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those of ordinary skill in the art can make changes, modifications, replacements and variations to the above embodiments without departing from the principles and spirit of the present application within the scope of the present application. The scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A testing method for autonomous vehicles based on expected functional safety, characterized in that, The method includes: The vehicles to be tested were sequentially directed into the first, second, and third test tracks. The first test track was a lane-changing test track under strong sunlight, comprising at least two lanes and a light simulation device. The second test track was a traffic construction sign recognition test track under dust conditions, comprising at least two lanes, traffic construction signs, and a dust simulation device. The third test track was a dynamic spillage recognition test track, comprising at least one lane and a spillage loading vehicle. Acquire real-time vehicle driving data information of the vehicle under test driving in the first test field, the second test field and the third test field respectively; The real-time vehicle driving data is compared with a preset evaluation table to obtain the rating information of the vehicle under test. The specific steps involved in the vehicle under test entering the first test track for testing include: Turn on the light simulation device and set the illuminance to between L1 (Lux) and L2 (Lux), where L1 (Lux) and L2 (Lux) represent the minimum and maximum light intensity values; The vehicle under test is to be driven at a constant speed at a first speed. Send a lane change command to the vehicle under test to either turn left or right; Obtaining real-time vehicle driving data information of the vehicle under test in the first test field specifically includes: at least obtaining the speed, deceleration, rate of change of deceleration, lateral offset speed, and lateral distance from the lane centerline of the vehicle under test during a first preset time period after receiving the lane change command; The traffic construction signs include at least one traffic sign and multiple traffic cones, and the traffic construction signs are evenly placed within the lane. The specific steps involved in the vehicle being tested entering the second test track include: Turn on the dust simulation device; The vehicle to be tested is driven in the lane where the traffic construction sign is located. When the vehicle to be tested is S1 meters away from the first traffic construction sign, it moves forward at a constant speed at the third speed. Obtaining real-time vehicle driving data information of the vehicle under test in the second test field specifically includes: at least obtaining the speed, deceleration, rate of change of deceleration, lateral offset speed, lateral distance from the lane centerline, and lateral relative distance from the traffic construction sign of the vehicle under test within a second preset time period after the vehicle under test has traveled to a distance of S1 meters from the first traffic construction sign; The specific procedures for the vehicle to be tested to enter the third test track include: The dumping material loading vehicle is driven at a fourth speed, and the vehicle under test is driven at a fifth speed in the lane where the dumping material loading vehicle is located, and the vehicle under test is driven at a distance S2 meters behind the dumping material loading vehicle, wherein the fourth speed and the fifth speed are the same. After the vehicle under test has been following the dumping vehicle for N seconds, the dumping vehicle is instructed to throw at least one dumping material onto the lane behind the vehicle. Acquiring real-time vehicle driving data of the vehicle under test while it is driving in the third test field specifically includes: acquiring at least the speed, deceleration, rate of change of deceleration, lateral offset speed, lateral distance from the lane centerline, and relative distance from the spilled material of the vehicle under test within a third preset time period after the spilled material loading vehicle throws the spilled material behind it.

2. The method according to claim 1, characterized in that, The first test track also includes: a first obstacle vehicle; The first obstacle vehicle travels at a second speed in the left or right lane of the lane where the vehicle under test is located, wherein the second speed is the same as the first vehicle speed; Sending a left or right lane change command to the vehicle under test includes: if the first obstacle vehicle is in the left lane of the lane where the vehicle under test is located, then sending a left lane change command to the vehicle under test; if the first obstacle vehicle is in the right lane of the lane where the vehicle under test is located, then sending a right lane change command to the vehicle under test.

3. A test track for autonomous vehicles based on expected functional safety, characterized in that, include: Central control unit, data collection unit, data analysis unit, first test site, second test site and third test site; The central control unit is used to command the vehicle to be tested to sequentially enter the first test track, the second test track, and the third test track. The first test track is a lane change test track under strong sunlight, and includes at least two lanes and a light simulation device. The second test track is a traffic construction sign recognition test track under dust conditions, and includes at least two lanes, traffic construction signs, and a dust simulation device. The third test track is a dynamic spillage recognition test track, and includes at least one lane and a spillage loading vehicle. The data collection unit is used to acquire real-time vehicle driving data information of the vehicle under test driving in the first test field, the second test field and the third test field respectively; The data analysis unit is used to compare the real-time vehicle driving data with a preset evaluation table to obtain the rating information of the vehicle under test. The specific steps involved in the vehicle under test entering the first test track for testing include: Turn on the light simulation device and set the illuminance to between L1 (Lux) and L2 (Lux), where L1 (Lux) and L2 (Lux) represent the minimum and maximum light intensity values; The vehicle under test is to be driven at a constant speed at a first speed. Send a lane change command to the vehicle under test to either turn left or right; Obtaining real-time vehicle driving data information of the vehicle under test in the first test field specifically includes: at least obtaining the speed, deceleration, rate of change of deceleration, lateral offset speed, and lateral distance from the lane centerline of the vehicle under test during a first preset time period after receiving the lane change command; The traffic construction signs include at least one traffic sign and multiple traffic cones, and the traffic construction signs are evenly placed within the lane. The specific steps involved in the vehicle being tested entering the second test track include: Turn on the dust simulation device; The vehicle to be tested is driven in the lane where the traffic construction sign is located. When the vehicle to be tested is S1 meters away from the first traffic construction sign, it moves forward at a constant speed at the third speed. Obtaining real-time vehicle driving data information of the vehicle under test in the second test field specifically includes: at least obtaining the speed, deceleration, rate of change of deceleration, lateral offset speed, lateral distance from the lane centerline, and lateral relative distance from the traffic construction sign of the vehicle under test within a second preset time period after the vehicle under test has traveled to a distance of S1 meters from the first traffic construction sign; The specific procedures for the vehicle to be tested to enter the third test track include: The dumping material loading vehicle is driven at a fourth speed, and the vehicle under test is driven at a fifth speed in the lane where the dumping material loading vehicle is located, and the vehicle under test is driven at a distance S2 meters behind the dumping material loading vehicle, wherein the fourth speed and the fifth speed are the same. After the vehicle under test has been following the dumping vehicle for N seconds, the dumping vehicle is instructed to throw at least one dumping material onto the lane behind the vehicle. Acquiring real-time vehicle driving data of the vehicle under test while it is driving in the third test field specifically includes: acquiring at least the speed, deceleration, rate of change of deceleration, lateral offset speed, lateral distance from the lane centerline, and relative distance from the spilled material of the vehicle under test within a third preset time period after the spilled material loading vehicle throws the spilled material behind it.

4. The autonomous vehicle test field according to claim 3, characterized in that, The first test track also includes: a first obstacle vehicle; The first obstacle vehicle travels at a second speed in the left or right lane of the lane where the vehicle under test is located, wherein the second speed is the same as the first vehicle speed; Sending a left or right lane change command to the vehicle under test includes: if the first obstacle vehicle is in the left lane of the lane where the vehicle under test is located, then sending a left lane change command to the vehicle under test; if the first obstacle vehicle is in the right lane of the lane where the vehicle under test is located, then sending a right lane change command to the vehicle under test.

Images