Automatic driving system fusion perception test device and method

Abstract

The invention provides an automatic driving system fusion perception test device and method. The test device comprises a road simulation site, a brightness adjusting structure, a weather simulation structure and a control device. The control device is electrically connected with the brightness adjusting structure, the weather simulation structure and the to-be-tested automatic driving system, and is used for receiving a test requirement of the to-be-tested automatic driving system, controlling the brightness adjusting structure to carry out brightness adjustment according to a preset test rule, and controlling the weather simulation structure to carry out weather simulation so as to form a plurality of simulation test scenes; and receiving identification results of the to-be-tested automatic driving system on the test target object in each simulation test scene through an image identification function and a laser radar cloud picture identification function, and determining a score of the to-be-tested automatic driving system according to a preset scoring rule. The invention provides an automatic driving system fusion perception test device and method, and aims to solve the problem that the identification capability of an automatic driving system of a vehicle is inconvenient to evaluate or test in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a device and method for testing fusion perception of an autonomous driving system. Background Art

[0002] With the development of autonomous driving technology, the requirements for vehicle perception capabilities are getting higher and higher. Cameras and lidar, as the main perception devices of autonomous vehicles, require precise testing and calibration to ensure their reliability and accuracy under different environmental conditions. However, traditional technologies lack testing methods for the perception capabilities of autonomous driving systems, which makes it inconvenient to test and evaluate the perception capabilities of vehicle autonomous driving systems, further affecting technicians' maintenance and development of autonomous driving systems. Summary of the invention

[0003] The present invention provides an autonomous driving system fusion perception testing device and method, aiming to solve the problem of inconvenience in evaluating or testing the recognition capability of a vehicle's autonomous driving system in traditional technologies.

[0004] In view of the problems existing in the prior art, an embodiment of the present invention provides an autonomous driving system fusion perception test device for testing an autonomous driving system of a vehicle, wherein the autonomous driving system has an image recognition function and a laser radar cloud image recognition function. The autonomous driving system fusion perception test device comprises: A road simulation site, including a plurality of simulated roads, each of which is provided with a test target, and a vehicle to be tested is used to be set on any of the simulated roads to test the automatic driving system, so as to test the recognition result of the automatic driving system to be tested on the test target; A brightness adjustment structure, comprising a lamp body and an adjuster provided on each of the simulated roads, wherein the adjuster is used to adjust the brightness of the lamp body; A weather simulation structure, including a water sprayer, a sprayer and a snow sprayer, wherein the water sprayer is used to spray water to simulate rain, the sprayer is used to spray mist to simulate fog, and the snow sprayer is used to spray snow to simulate snow; and,

[0005] A control device is electrically connected to the brightness adjustment structure, the weather simulation structure and the autonomous driving system to be tested, and is used to receive test requirements of the autonomous driving system to be tested, control the brightness adjustment structure to adjust the brightness according to preset test rules, and control the weather simulation structure to simulate the weather to form multiple simulated test scenes; and receive recognition results of the test target objects in each of the simulated test scenes by the autonomous driving system to be tested through image recognition functions and lidar cloud map recognition functions, and determine the score of the autonomous driving system to be tested according to preset scoring rules.

[0006] According to a fusion perception test device for an autonomous driving system provided by the present invention, the road simulation site includes an urban simulation road, a highway simulation road, a rural simulation road, a mountain simulation road and a construction simulation road. The urban simulation road includes an intersection, a crosswalk and buildings, the highway simulation road includes lane lines, an overpass and billboards, the rural simulation road includes narrow roads, winding roads, farmlands and trees, and the construction simulation road includes a construction road and construction equipment.

[0007] According to a fusion perception test device for an autonomous driving system provided by the present invention, the test targets include non-semantic obstacles and semantic targets. The non-semantic obstacles include cones and temporary roadblocks. The semantic targets include signs and traffic lights. At least one of the test targets is arranged in each simulated road.

[0008] According to the present invention, a fusion perception test device for an autonomous driving system further comprises a rotating platform provided on each of the simulated roads, wherein the rotating platform is used to place the test target object; The rotating platform is electrically connected to the control device, and the control device is used to control the rotation of the rotating platform according to a preset test rule to adjust the viewing angle of the test target relative to the vehicle to be tested.

[0009] According to an automatic driving system fusion perception test device provided by the present invention, it also includes a slide arranged on each of the simulated roads, the slide is used to slide along each of the simulated roads to adjust the distance relative to the vehicle to be tested, and the rotating table is arranged on the slide.

[0010] The present invention also provides a method for testing fusion perception of an autonomous driving system, using the fusion perception testing device for an autonomous driving system as described in any one of the above items, the testing method comprising: The vehicle to be tested moves to the target simulated road; Obtain the test requirements of the autonomous driving system to be tested and determine the test target; According to the test requirements of the autonomous driving system to be tested and the test target, different simulation test scenarios are formed according to preset test rules; Obtaining recognition results of the automatic driving system to be tested on the test target object in each of the simulated test scenarios; A score of the autonomous driving system to be tested is determined according to the recognition result and preset scoring rules.

[0011] According to a method for testing fusion perception of an autonomous driving system provided by the present invention, the simulated test scenes include a lighting test scene, a weather test scene, a viewing angle test scene and a distance test scene; the brightness value of each lighting test scene is different, the weather test scene includes but is not limited to a sunny scene, a rainy scene, a foggy scene and a snowy scene, the viewing angle of each viewing angle test scene relative to the test target is different, and the distance of each distance test scene relative to the test target is different.

[0012] According to a method for testing a fusion perception of an autonomous driving system provided by the present invention, each of the simulated test scenarios includes at least one test scenario and at least one target object to be tested.

[0013] According to a method for testing fusion perception of an autonomous driving system provided by the present invention, determining the score of the autonomous driving system to be tested according to the recognition result and a preset scoring rule includes: Determine that the automatic driving system to be tested recognizes the i The test target in the simulated test scene is scored n i =1; Determine that the autonomous driving system under test does not recognize the i The test target in the simulated test scene is scored n i =0; After the test is completed, the score of the autonomous driving system to be tested is calculated according to the following formula; in, P For rating, w A weighting coefficient for each corresponding test scene and the test target object in the simulated test scene.

[0014] According to a fusion perception test method for an autonomous driving system provided by the present invention, the calculation formula of the weighting coefficient is as follows: w = S + V + C + R + E

[0015] in, S Indicates the degree of shape distinctness of the test object, S The value range is 0-a. V Indicates the volume of the target to be measured, V The value range is bc, C Indicates the color brightness of the target object to be measured, CThe value range of is de, R represents the reflectance or retroreflectance of the target object to be measured, R The value range is 0-f, E Indicates the difficulty of the test scenario, E The value range is gh.

[0016] The automatic driving system fusion perception test device provided by the present invention provides a road simulation site, which can be used to test the recognition ability of the vehicle's automatic driving system on the spot, and is equipped with a brightness adjustment structure and a weather simulation structure, which can realize a variety of simulation test scenarios and improve the comprehensiveness of the test scenario coverage. Furthermore, the control device can be fully automatically controlled to perform the test and obtain the score of the automatic driving system to be tested, so as to comprehensively evaluate the fusion perception ability of the camera image recognition and laser radar recognition of the automatic driving system to be tested, and improve the comprehensiveness and professionalism of the recognition ability test of the automatic driving system to be tested. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the autonomous driving system fusion perception testing method provided by the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0021] In the description of the embodiments of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present invention.

[0022] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0023] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0024] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplicity and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides various specific processes and examples of materials, but those of ordinary skill in the art can be aware of the applicability of other processes and / or the use of other materials.

[0025] Combine the following Figure 1 The present invention describes an autonomous driving system fusion perception testing device and method.

[0026] In view of the problem that traditional technologies have difficulty in evaluating or testing the recognition capabilities of a vehicle's autonomous driving system, an embodiment of the present invention provides an autonomous driving system fusion perception test device for testing a vehicle's autonomous driving system, including a road simulation site, a brightness adjustment structure, a weather simulation structure, and a control device.

[0027] The road simulation site includes a variety of simulated roads, all of which are set up in real scenes, and different road lengths can be selected according to the size of the site. When the site is small, a shorter road length can be selected and a static identification method can be used, that is, the vehicle to be tested is in a static state to identify the target object to be tested; when the site is large, a longer road length can be selected and a dynamic identification method can be used, that is, the vehicle to be tested can be moved to identify the target object to be tested. It should also be noted that the vehicle to be tested can be a complete vehicle actually driven, or a part of a vehicle, or a vehicle model, which can be determined according to the test requirements and test results, and the present invention does not limit this. In order to prevent mutual interference, the simulated roads should be set at intervals from each other, or adjacently set and then separated by partitions. The construction of the roads is all constructed by real-scene simulation, and can be constructed in imitation of different road conditions in daily driving scenes. During the test, each simulated road is equipped with a test target, and the vehicle to be tested can be set on any simulated road to test the automatic driving system to test the recognition results of the test target under different test scenarios.

[0028] The brightness adjustment structure includes a lamp body and an adjuster arranged on each simulated road, and the adjuster is used to adjust the brightness of the lamp body. By adjusting the brightness of the lamp body, the brightness of different simulated test scenes can be adjusted, and then the recognition of the target object to be tested by the autonomous driving system under different brightness environments can be tested. The lamp body can be set to one or more, preferably evenly set to multiple, and set in the area above the vehicle to be tested. The brightness adjustment of the lamp body can be regular or irregular, mainly by the control device to select the brightness according to the test requirements and preset test rules and control the lamp body to output according to the selected brightness.

[0029] The weather simulation structure includes a water sprayer, a sprayer and a snow sprayer. The water sprayer is used to spray water to simulate rain. The water sprayer can be set with multiple nozzles. The nozzle has a regulating valve to adjust the water spray size, so that the test scene of light rain, moderate rain and heavy rain can be simulated. The sprayer is used to spray to simulate foggy days. The sprayer can also be set with multiple nozzles to spray. It can spray water mist or dry ice mist. The size of the spray can also be adjusted to simulate light fog, moderate fog or heavy fog. The snow sprayer is used to spray snow to simulate snowy days. In order to reduce costs, the snow sprayer can spray fine foam or foam balls to simulate snow. The flow rate or wind force of the foam or foam balls can also be adjusted to simulate light snow, moderate snow and heavy snow. It should be noted that by setting up a weather simulation structure, various weathers can be simulated to test the recognition ability of the autonomous driving system in various weather scenes and improve the comprehensiveness of the test scene coverage. The flow rate size adjustment of the water sprayer, sprayer or snow sprayer lamp body can be regular or irregular, and is mainly selected and controlled by the control device according to the test requirements and preset test rules.

[0030] The control device is electrically connected to the brightness adjustment structure, the weather simulation structure and the automatic driving system to be tested, and is used to receive the test requirements of the automatic driving system to be tested, control the brightness adjustment structure to adjust the brightness according to the preset test rules, and control the weather simulation structure to simulate the weather to form multiple simulated test scenes; and receive the recognition results of the automatic driving system to be tested for the test target in each simulated test scene, and determine the score of the automatic driving system to be tested according to the preset scoring rules. It should be noted that the vehicle to be tested has a camera and a laser radar, the camera will take a simulated test scene to form a picture, and the laser radar will obtain a laser radar cloud map. The automatic driving system to be tested has an image recognition function and a laser radar cloud map recognition function. The present invention is mainly used to test the fusion perception ability of the automatic driving system to be tested. Therefore, when testing each simulated test scene, it is necessary to obtain the image recognition result and the laser radar cloud map recognition result respectively, and the two recognition results are scored independently to test the fusion perception ability of the automatic driving system to be tested.

[0031] The automatic driving system fusion perception test device provided by the present invention provides a road simulation site, which can be used to test the recognition ability of the vehicle's automatic driving system on the spot, and is equipped with a brightness adjustment structure and a weather simulation structure, which can realize a variety of simulation test scenarios and improve the comprehensiveness of the test scenario coverage. Furthermore, the control device can be fully automatically controlled to perform the test and obtain the score of the automatic driving system to be tested, so as to comprehensively evaluate the perception ability of the automatic driving system to be tested and improve the comprehensiveness and professionalism of the recognition ability test of the automatic driving system to be tested.

[0032] Specifically, the road simulation site includes urban simulation roads, high-speed simulation roads, rural simulation roads, mountain simulation roads and construction simulation roads. Urban simulation roads include intersections, crosswalks and buildings, high-speed simulation roads include lane lines, overpasses and billboards, rural simulation roads include narrow roads, winding roads, farmland and trees, and construction simulation roads include construction roads and construction equipment. The simulation road can be set according to the scene in the actual driving scene, using a one-to-one restoration, so that it can be closer to the actual driving scene and improve the accuracy of the test.

[0033] The test targets include non-semantic obstacles and semantic targets. Non-semantic obstacles include cones and temporary roadblocks. Semantic targets include signs and traffic lights. There is at least one test target in each simulated road. Among non-semantic obstacles, such as common cones or temporary roadblocks, cones are usually used to mark construction areas, dangerous areas on the road, or temporarily changed road layouts to alert drivers. Temporary roadblocks are used to close lanes, set up temporary traffic control, or protect specific areas. Cones or temporary roadblocks are defined as non-semantic obstacles to evaluate the autonomous driving system's ability to recognize temporary obstacles. Non-semantic obstacles are not limited to the above two. Among semantic targets, such as common road signs or traffic lights, signs are common traffic signs on the road, which are used to provide information such as direction, distance, and road conditions to help drivers make correct driving decisions. Traffic lights are traffic lights used to control traffic flow and ensure road safety. Their color changes (red, yellow, and green) represent different traffic instructions. In autonomous driving tests, semantic targets are used to evaluate the system's ability to recognize and understand traffic signs and signals. The present invention can evaluate the recognition and understanding capabilities of an autonomous driving system by setting a test target.

[0034] Furthermore, in order to comprehensively evaluate the recognition capability of the autonomous driving system, the simulated test scenario also includes a perspective test scenario. Specifically, the autonomous driving system fusion perception test device also includes a turntable provided on each simulated road, on which the test target is placed. The turntable is electrically connected to the control device, and the control device is used to control the rotation of the turntable according to preset test rules to adjust the perspective of the test target relative to the vehicle to be tested, so as to test the autonomous driving system's recognition capability of the target to be tested at different perspectives. The turntable can be driven by a rotating motor, and straps or bolts can be provided on the turntable to lock the target to be tested. The angle change of the turntable rotation can be regular or irregular, which can be determined specifically according to the test requirements.

[0035] Furthermore, when the area of ​​the road simulation site is large, the vehicle to be tested can be driven and moved, and the distance from the target object to be tested will change during the movement, so the recognition ability of the autonomous driving system to be tested at different distances can be tested. However, when the area of ​​the road simulation site is small or the vehicle to be tested does not have a driving function, it is necessary to adjust the distance between the target object to be tested and the vehicle to be tested to meet the test requirements. Specifically, the autonomous driving system fusion perception test device also includes a slide arranged on each simulated road, the slide is used to slide along each simulated road to adjust the distance relative to the vehicle to be tested, and the rotating table is arranged on the slide. It should be noted that a pulley can be arranged at the bottom of the slide, and a motor is used to drive the pulley to move and control the distance from the vehicle to be tested. The control device can control the movement of the slide during the test according to the test requirements and the preset test rules, thereby adjusting the distance between the target object to be tested and the vehicle to be tested. The test distance can change regularly or irregularly.

[0036] The present invention also provides a method for testing fusion perception of an autonomous driving system. The method uses the above-mentioned fusion perception testing device for the autonomous driving system. The method includes: S100, the vehicle to be tested moves to the target simulated road; S200, obtaining the test requirements of the autonomous driving system to be tested and determining the test target; S300, forming different simulation test scenarios according to the test requirements of the automatic driving system to be tested and the test target object according to preset test rules; S400, obtaining recognition results of the test target object in each of the simulated test scenarios by the automatic driving system to be tested; S500: Determine a score of the autonomous driving system to be tested according to the recognition result and preset scoring rules.

[0037] Furthermore, the simulated test scenes include illumination test scenes, weather test scenes, viewing angle test scenes, and distance test scenes; the brightness values ​​of the illumination test scenes are different, the weather test scenes include but are not limited to sunny scenes, rainy scenes, foggy scenes, and snowy scenes, the viewing angles of the viewing angles of the viewing angles relative to the test target are different, and the distances of the distance test scenes are different from the test target. The above-mentioned test scenes are completed by adjusting the brightness adjustment structure, weather adjustment structure, rotating table, and sliding table in the device.

[0038] The test targets need to be determined according to the test requirements of the autonomous driving system to be tested. The test requirements of some autonomous driving systems may be targeted at non-semantic obstacles or semantic targets alone. In this case, the simulated test scene only contains non-semantic obstacles or semantic targets, and the autonomous driving system's ability to recognize roadblocks or traffic lights can be tested separately. The test requirements of some autonomous driving systems are targeted at non-semantic obstacles and semantic targets. In this case, the simulated test scene includes both non-semantic obstacles and semantic targets.

[0039] Furthermore, after determining the test target, it is still necessary to determine the test scene according to the test requirements of the autonomous driving system. Even if the test target is the same, the recognition effect of the autonomous driving system will be greatly different due to the environmental influence of different test scenes. Therefore, in the technical solution provided by the present invention, it is necessary to assist the transformation of the test scene to comprehensively evaluate the recognition ability of the autonomous driving system to the test target. It should be noted that when the autonomous driving system is tested, the scene will be changed according to the test requirements of the autonomous driving system. In a simulated road, multiple scene changes will be performed, such as brightness change in sequence, and then weather change, or brightness and weather change at the same time, and then the perspective and distance change of the target to be tested will be assisted. At least 100 scene changes will be performed in each simulated road, so as to comprehensively test the recognition ability of the autonomous driving system to be tested. It should be noted that when performing each simulated scene test, it is necessary to wait for a certain time interval, and then obtain the image recognition result and the lidar cloud map recognition result respectively, and the two results are scored as two test results.

[0040] Furthermore, the autonomous driving system will output a recognition result after the scene change. By acquiring and calculating the recognition result of the autonomous driving system, the score of the autonomous driving system to be tested can be obtained. Under the positive scoring mechanism, the higher the score, the higher the recognition ability of the autonomous driving system. The autonomous driving system fusion perception test method provided by the present invention can evaluate the perception ability of the autonomous driving system to be tested, and further can evaluate and calibrate the autonomous driving system's recognition ability of targets in real road scenes. On the one hand, it is conducive to establishing a mechanism for scoring and detecting autonomous driving systems, and on the other hand, it is also conducive to technicians to maintain and redevelop autonomous driving systems based on recognition results and scoring results.

[0041] Furthermore, in order to improve the integration between the environment and the target object to be tested, each simulated test scene includes at least one test scene and at least one test target object. It is understandable that each simulated test scene may include one or more test scenes, such as the integration of a brightness test scene and a weather test scene, the integration of a weather test scene and a viewing angle test scene, or the integration of three or more test scenes. Furthermore, the simulated test scene may have one or more test targets. Correspondingly, when the more types of test scene integration and the more test targets are set, the higher the difficulty of identifying the simulated test scene will be, which will test the recognition ability of the autonomous driving system.

[0042] Specifically, S500, determining the score of the automatic driving system to be tested according to the recognition result and the preset scoring rule includes: S510: Determine whether the automatic driving system to be tested recognizes the i The test target in the simulated test scene is scored n i =1; S520: Determine that the automatic driving system to be tested does not recognize i The test target in the simulated test scene is scored n i =0; S530: After the test is completed, the score of the autonomous driving system to be tested is calculated according to the following formula; in, P For rating, w A weighting coefficient for each corresponding test scene and the test target object in the simulated test scene.

[0043] Specifically, the calculation formula of the weighting coefficient is as follows: w = S + V + C + R + E

[0044] in, S Indicates the degree of shape prominence of the test target. S The value range is 0-a. V Indicates the volume of the target to be measured. V The value range is bc, C Indicates the color vividness of the target object to be measured. C The value range of is de, R Indicates the reflectance or retroreflectance of the target object to be measured. RThe value range is 0-f, E Indicates the difficulty of the test scenario, E The value range is gh.

[0045] As mentioned above, the recognition difficulty of each simulation test scene will be different. The more test scenes are integrated in the simulation test scene and the more test targets are included, the greater the recognition difficulty of the simulation test scene. Furthermore, the recognition difficulty is also different for different test scenes and test targets of different forms. In order to improve the representation effect of the score, in the technical solution provided by the present invention, different weighting coefficients are set for different test scenes and test targets. By combining the weighting coefficients and the number of recognitions of the simulation test scenes, the comprehensive score of the autonomous driving system can be obtained. It should be noted that when all autonomous driving systems are tested using the same test method, different autonomous driving systems will obtain different scores. Under the positive scoring mechanism, the higher the score, the higher the fusion perception ability of the autonomous driving system. The mainstream autonomous driving systems on the market can be selected to form samples for scoring. According to the distribution of the scores, several evaluation conditions such as excellent, good, qualified, and unqualified can be determined, thereby assisting in establishing the scoring criteria for the autonomous driving system, which is conducive to forming a standard scoring test method and standard for the autonomous driving system. It should be noted that, assuming that 100 simulated test scenarios are tested, due to the existence of image recognition results and lidar cloud map recognition results, there will actually be 200 test results, and all 200 test results need to be scored.

[0046] Specifically, the present invention provides several methods for setting weighting coefficients. In the calculation formula of the weighting coefficients, S Indicates the degree of shape prominence of the test target. S The value range is 0-a. Specifically, a regular circle or square takes a value close to 1, and a complex irregular shape takes a value close to 0. In actual application, a specific value can be set for each different shape, and a specific value can be uniformly determined for irregular shapes that cannot be confirmed. V Indicates the volume of the target to be measured. V The value range of V is bc. The smaller the volume of the target to be measured, the larger the value of V is. Specific values ​​can be set for targets to be measured in different volume ranges. C Indicates the color vividness of the target object to be measured. C The value range of is de, and the chroma C value in the CIELAB color system can be used for assignment. The higher the chroma, the larger C is. R Indicates the reflectance or retroreflectance of the target object to be measured. RThe value range is 0-f. The R value of a completely non-reflective target is 0, and the R value of a reflective mark is usually above 1. Different R values ​​can be set according to the type of target. E Indicates the difficulty of the test scenario, E The value range of is gh. In an optional embodiment, the E value of the daytime scene is 1, the E value of the night scene is 2, and the E value of the rainy scene is 3. When multiple different scenes are combined, the sum of the E values ​​of the multiple different scenes can be used for calculation. It should also be noted that since the present invention provides multiple simulated roads, each simulated road can also be set with different weighting coefficients according to different driving difficulties. In this way, w F is introduced in , where F represents the difficulty of the simulated road. The value of F is a positive integer. The more difficult the simulated road is, the higher the value is. Therefore, the difficulty of the simulated road can be comprehensively considered to test the recognition ability of the autonomous driving system.

[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic driving system fusion perception test device, used to test the automatic driving system of a vehicle, wherein the automatic driving system has image recognition function and laser radar cloud image recognition function, and is characterized in that: The autonomous driving system fusion perception test device includes: A road simulation site, including a plurality of simulated roads, each of which is provided with a test target, and a vehicle to be tested is used to be set on any of the simulated roads to test the automatic driving system, so as to test the recognition result of the automatic driving system to be tested on the test target; A brightness adjustment structure, comprising a lamp body and an adjuster provided on each of the simulated roads, wherein the adjuster is used to adjust the brightness of the lamp body; A weather simulation structure, including a water sprayer, a sprayer and a snow sprayer, wherein the water sprayer is used to spray water to simulate rain, the sprayer is used to spray mist to simulate fog, and the snow sprayer is used to spray snow to simulate snow; and, A control device is electrically connected to the brightness adjustment structure, the weather simulation structure and the autonomous driving system to be tested, and is used to receive test requirements of the autonomous driving system to be tested, control the brightness adjustment structure to adjust the brightness according to preset test rules, and control the weather simulation structure to simulate the weather to form multiple simulated test scenes; and receive recognition results of the test target objects in each of the simulated test scenes by the autonomous driving system to be tested through image recognition functions and lidar cloud map recognition functions, and determine the score of the autonomous driving system to be tested according to preset scoring rules.

2. The autonomous driving system fusion perception test device according to claim 1, characterized in that: The road simulation site includes urban simulation roads, highway simulation roads, rural simulation roads, mountain simulation roads and construction simulation roads. The urban simulation roads include intersections, crosswalks and buildings. The highway simulation roads include lane lines, overpasses and billboards. The rural simulation roads include narrow roads, winding roads, farmlands and trees. The construction simulation roads include construction roads and construction equipment.

3. The automatic driving system fusion perception test device according to claim 2, characterized in that: The test targets include non-semantic obstacles and semantic targets. The non-semantic obstacles include cones and temporary roadblocks. The semantic targets include signboards and traffic lights. At least one of the test targets is arranged in each simulated road.

4. The autonomous driving system fusion perception test device according to claim 1, characterized in that: It also includes a rotating platform disposed on each of the simulated roads, and the rotating platform is used to place the test target object; The rotating platform is electrically connected to the control device, and the control device is used to control the rotation of the rotating platform according to a preset test rule to adjust the viewing angle of the test target relative to the vehicle to be tested.

5. The automatic driving system fusion perception test device according to claim 4, characterized in that: It also includes a slideway arranged on each of the simulated roads, the slideway is used to slide along each of the simulated roads to adjust the distance relative to the vehicle to be tested, and the rotating platform is arranged on the slideway.

6. A method for testing fusion perception of an autonomous driving system, using the fusion perception testing device of an autonomous driving system as claimed in any one of claims 1 to 5, characterized in that: The test method includes: The vehicle to be tested moves to the target simulated road; Obtain the test requirements of the autonomous driving system to be tested and determine the test target; According to the test requirements of the autonomous driving system to be tested and the test target, different simulation test scenarios are formed according to preset test rules; Obtaining recognition results of the test target object in each of the simulated test scenarios by the automatic driving system to be tested; A score of the autonomous driving system to be tested is determined according to the recognition result and preset scoring rules.

7. The method for testing the fusion perception of an autonomous driving system according to claim 6, characterized in that: The simulated test scenes include lighting test scenes, weather test scenes, viewing angle test scenes and distance test scenes; the brightness values ​​of the lighting test scenes are different, the weather test scenes include but are not limited to sunny scenes, rainy scenes, foggy scenes and snowy scenes, the viewing angles of the viewing angles of the viewing angles relative to the test targets are different, and the distances of the distance test scenes relative to the test targets are different.

8. The method for testing the fusion perception of an autonomous driving system according to claim 7, characterized in that: Each of the simulated test scenarios includes at least one test scenario and at least one target object to be tested.

9. The method for testing the fusion perception of an autonomous driving system according to claim 6, characterized in that: Determining the score of the autonomous driving system to be tested according to the recognition result and the preset scoring rules includes: Determine that the automatic driving system to be tested recognizes the i The test target in the simulated test scenario is scored n i =1; Determine that the autonomous driving system under test does not recognize the i The test target in the simulated test scenario is scored n i =0; After the test is completed, the score of the autonomous driving system to be tested is calculated according to the following formula; in, P For rating, w A weighting coefficient for each corresponding test scene and the test target object in the simulated test scene.

10. The method for testing the fusion perception of the autonomous driving system according to claim 9, characterized in that: The calculation formula of the weighting coefficient is as follows: w = S + V + C + R + E in, S Indicates the degree of shape distinctness of the test object, S The value range is 0-a. V Indicates the volume of the target to be measured, V The value range is bc, C Indicates the color brightness of the target object to be measured, C The value range of is de, R represents the reflectance or retroreflectance of the target object to be measured, R The value range is 0-f, E Indicates the difficulty of the test scenario, E The value range is gh.

Images