Road traffic marking generation system, method and autonomous driving in-loop test system
By using vehicle virtual position sensors and projector arrays to generate road traffic markings on the drum platform, the problem of inability to simulate road traffic markings in the prior art is solved, and the intelligent connected vehicles on the drum platform is realized Perception and decision-making functional testing reduces costs and improves testing efficiency.
Patent Information
- Application Number
- CN202410417833.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-09
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-04-09
AI Technical Summary
The existing technology is difficult to effectively simulate road traffic markings on the drum platform, resulting in the inability to conduct perception and decision-making functions related to intelligent connected vehicles and road traffic markings. The existing incentive system is expensive or requires unnecessary vehicles. Improvements.
Using the vehicle virtual position sensor unit and the projector array control unit, the projector array generates road traffic markings adapted to the vehicle on the drum platform to simulate real traffic scenes, including static and dynamic traffic markings, and achieve the correctness of the traffic markings. Effective incentive of vehicle perception system.
There is no need to develop a proprietary interface or use a ring curtain system, which reduces costs and realizes simulation and perception testing of road traffic markings for intelligent connected vehicles on the drum platform, solving the problem of the inability to simulate road traffic markings in the existing technology. The problem.
Smart Images

Figure CN118294165B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of in-the-loop testing technology for intelligent connected vehicles, and specifically to a road traffic marking generation system and method and an in-the-loop testing system for autonomous driving. Background Art
[0002] Vehicle-in-the-loop testing on an indoor drum platform is very important in the development of autonomous driving technology and advanced driver assistance technology. In order to test the autonomous driving function or advanced driver assistance function of an intelligent connected vehicle on an indoor drum platform, it is necessary to simulate part or all of the traffic environment (including static traffic environment and dynamic traffic environment) for the perception system of the intelligent connected vehicle. This simulation system is also called an excitation system. Among the traffic environments simulated by the excitation system, road traffic markings are a very important static traffic environment. Existing autonomous driving systems or advanced driver assistance systems must deal with road traffic markings when making any planning decisions.
[0003] However, some of the prior art incentive systems for simulating traffic environments for intelligent connected vehicles on a rotating drum platform require the development of special interfaces, which makes the improvement of the incentive system complicated (such as the patent name of "Intelligent Driving Vehicle In-Loop Test System", application number: 2023111738117), or some of the equipment needs to be replaced or expensive systems need to be added (such as the patent name of "An Intelligent Connected Vehicle In-Loop Test System and Method", application number: 2022117289954), or some tests cannot be performed, or some of them cannot be tested on the rotating drum platform for the perception and decision-making functions related to intelligent connected vehicles and road traffic markings due to the limitations of the system itself (such as the patent name of "A Vehicle In-Loop Test System", application number: 2023115709185).
[0004] Therefore, a solution for generating road traffic markings is needed. Summary of the invention
[0005] In view of this, the embodiments of this specification provide a road traffic marking generation system, method and autonomous driving in-the-loop test system.
[0006] The embodiments of this specification provide the following technical solutions:
[0007] The embodiment of this specification provides a road traffic marking generation system, including a vehicle virtual posture sensor unit, a projector array control unit and a projector array;
[0008] The vehicle virtual posture sensor unit is used to obtain the virtual posture parameters of the test vehicle from the drum platform;
[0009] The projector array control unit is used to use the virtual body coordinate system where the virtual posture parameters are located as a reference benchmark, unify the road traffic marking range generated in the simulated traffic scene map coordinate system into a virtual body coordinate system through the projection coordinate system where the projector array is located, generate an image corresponding to the road traffic marking range of the vehicle in the virtual body coordinate system for the projector array, and transmit the image to the projector array for output;
[0010] The projector array is used to receive the image and project the traffic markings represented by the image onto the ground in front of the drum platform, so that the vehicle can perform auxiliary function testing or road traffic marking excitation according to the traffic markings on the drum platform.
[0011] The embodiments of this specification also provide an autonomous driving in-the-loop test system, which uses the road traffic marking generation system described in the above technical solution as an incentive system, and uses the incentive system or other incentive systems to expand the traffic scenario of the whole vehicle in-the-loop test system based on a rotating drum platform.
[0012] The embodiment of this specification also provides a method for generating road traffic markings, using the road traffic marking generation system as described in the above technical solution, and the road traffic marking generation method includes:
[0013] The vehicle virtual posture sensor unit obtains the virtual posture parameters of the test vehicle from the drum platform;
[0014] The projector array control unit uses the virtual vehicle body coordinate system where the virtual posture parameters are located as a reference benchmark, unifies the road traffic line range generated in the simulated traffic scene map coordinate system into a virtual vehicle body coordinate system through the projection coordinate system where the projector array is located, generates an image corresponding to the road traffic line range of the vehicle in the virtual vehicle body coordinate system for the projector array, and transmits the image to the projector array for output;
[0015] The projector array receives the image and projects the road traffic markings represented by the image onto the ground in front of the drum platform.
[0016] Compared with the prior art, the at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects:
[0017] This application is based on a rotating drum platform, and utilizes a vehicle virtual posture sensor unit, a projector array control unit, and a projector array to generate road traffic markings for the vehicle. The road traffic markings projected by the projector array appear consistent with the real road traffic markings from the perspective of the vehicle running on the rotating drum platform. By providing equipment such as a projector array control unit and a projector array, there is no need to develop a proprietary interface for the intelligent connected vehicle being tested, nor is there any need to make unnecessary improvements to the test vehicle, and there is no need to use a ring screen system to save costs. That is, compared to the prior art, through simple equipment improvements, there is no need to make too much improvement to the vehicle hardware to solve the problems of being unable to simulate road traffic markings and being unable to test the perception and decision-making functions related to intelligent connected vehicles and road traffic markings on a rotating drum platform. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0019] Figure 1 This is a schematic diagram of the road traffic marking generation system structure provided in the embodiment of this specification. Figure 1 ;
[0020] Figure 2 This is a schematic diagram of the road traffic marking generation system structure provided in the embodiment of this specification. Figure 2 ;
[0021] Figure 3 This is a schematic diagram of the application of road traffic markings in the ring test scenario provided by the embodiment of this specification. Figure 1 ;
[0022] Figure 4 This is a schematic diagram of the application of road traffic markings in the ring test scenario provided by the embodiment of this specification. Figure 2 ;
[0023] Figure 5 It is a flow chart of a method for generating road traffic markings provided in an embodiment of this specification. DETAILED DESCRIPTION
[0024] The embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0025] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.
[0026] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.
[0027] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.
[0028] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the examples can be practiced without these specific details.
[0029] The vehicle-in-the-loop test on the indoor drum platform can not only verify / evaluate the power system, execution system, perception system and decision-making system of intelligent networked vehicles at the same time, but also has the advantages of controllable experimental environment, high repeatability and consistency, and no influence from the site environment. Therefore, it has become a very important tool in the development of autonomous driving technology and advanced driver assistance technology. In order to test the autonomous driving function or advanced driver assistance function of intelligent networked vehicles on the indoor drum platform, it is necessary to simulate part or all of the traffic environment (including static traffic environment and dynamic traffic environment) for the perception system (camera, millimeter wave radar, lidar, etc.) of the intelligent networked vehicle. This simulation system is also called an excitation system.
[0030] In the traffic environment simulated by the incentive system, road traffic markings are a very important static traffic environment. Existing autonomous driving systems or advanced driver assistance systems must deal with road traffic markings when making any planning decisions. Common ADAS (Advanced Driving Assistance System) functions such as LKAS (Lane Keeping Assist System) and LDWS (Lane Departure Warning System) only provide assisted driving functions by identifying lane lines. Autonomous driving systems also need to make autonomous driving decisions by identifying various road traffic markings such as lane lines, stop lines, and crosswalks.
[0031] The existing incentive system technologies used to simulate traffic environments for intelligent connected vehicles on a rotating drum platform are mainly divided into the following three types:
[0032] The first method uses virtual simulation scenarios to directly inject into the domain controller. This technology directly injects virtual sensor data from the autonomous driving simulation system into the domain controller of the intelligent connected vehicle under test. The advantage is that it can simulate various complex dynamic traffic scenarios and static traffic scenarios (including road traffic markings). The disadvantage is that it is necessary to develop a proprietary interface for the intelligent connected vehicle under test, and bypass the perception sensors of the intelligent connected vehicle (so these sensors cannot be tested), which is not allowed in many vehicle-in-the-loop tests. For example, the patent document named Intelligent Driving Vehicle-In-the-Loop Test System, application number / patent number: 2023111738117, uses this technology.
[0033] The second type of visual system is currently the most common incentive system, used by most manufacturers, and is also a relatively mature solution. For example, this solution is used in the patent document (named A system and method for testing the whole vehicle in the loop of an intelligent connected vehicle, application number / patent number: 2022117289954). The shortcomings of this incentive system are:
[0034] A radar simulator is needed to simulate the target object, otherwise the ADAS system of the autonomous driving vehicle being tested cannot be started (in the absence of a radar simulator, the image detected by the camera and the target object detected by the radar are inconsistent)
[0035] Modern intelligent connected vehicles have multiple perception cameras distributed in all directions of the vehicle. If road traffic marking simulation is required for such intelligent connected vehicles, a ring screen system needs to be used, which is expensive and unaffordable for ordinary users.
[0036] If the smart connected car being tested also uses LiDAR and a visual system for fusion perception (which is a very common situation nowadays), and because the system cannot simulate the reflection information of the LiDAR, the autonomous driving system or ADAS system of this type of smart connected car cannot be activated on the test bench, and therefore cannot be tested.
[0037] The third type uses physical model stimulation, such as fake targets carried by autonomous mobile robots. For example, the vehicle-in-the-loop test on a rotating drum platform developed by TNO, the Netherlands National Institute for Applied Scientific Research, places a whole vehicle equipped with sensors on a rotating drum platform, and uses a robot motion platform system to simulate the relative movement of surrounding traffic participants and the tested vehicle to achieve vehicle-in-the-loop testing. For example, the patent document is called a whole vehicle-in-the-loop testing system, application number / patent number: 023115709185, and also uses physical vehicles (physical vehicle models, pedestrian models, and bicycle models) to simulate dynamic traffic flows, and also uses scene facilities (including street lights, road sign models, tree models, and speed bump models, etc.). However, this type of stimulation system can simulate dynamic traffic flows, even road traffic signs. However, neither of these two systems can simulate road traffic markings, so it is impossible to test the perception and decision-making functions of intelligent connected vehicles related to road traffic markings on a rotating drum platform.
[0038] In view of this, the inventors found that in the real world (such as closed parks or public road test scenarios), road traffic markings are stationary and the intelligent connected vehicles under test are moving; while on the drum test platform, the intelligent connected vehicles are stationary (the drum only provides road load for the intelligent connected vehicles, and the vehicle itself does not move), and the road traffic markings must move relative to the intelligent connected vehicles, so that they are stationary in the moving vehicle coordinate system (note that the moving vehicle coordinate system is virtual).
[0039] Based on this, the embodiments of this specification propose a new road traffic marking generation scheme: according to the requirements of the intelligent networked vehicle to conduct vehicle-in-the-loop testing on the drum platform, a road traffic marking generation method and system are proposed, which can simulate road traffic markings for the intelligent networked vehicle tested on the drum platform. These simulated road traffic markings are consistent with the real road traffic markings from the perspective of the vehicle running on the drum platform. This solves the shortcomings and deficiencies of the existing incentive system and realizes a new road traffic marking generation scheme.
[0040] The technical solutions provided by various embodiments of the present application are described below in conjunction with the accompanying drawings.
[0041] like Figure 1 As shown, the road traffic marking generation system provided in the embodiment of this specification includes a vehicle virtual posture sensor unit, a projector array control unit and a projector array.
[0042] Specifically, the vehicle virtual posture sensor unit is used to obtain the current six-degree-of-freedom virtual posture parameters (such as virtual position and virtual posture) of the intelligent networked vehicle under test from the drum platform. The vehicle virtual posture sensor unit can be a physical device (for example, composed of a steering wheel angle sensor, a vehicle odometer and a posture solving unit), or a software module for receiving the vehicle's steering wheel angle signal and vehicle mileage signal from the drum platform through the bus, and solving the vehicle posture. The software module can also directly receive the vehicle posture data from the drum platform. The vehicle virtual posture parameters correspond to the virtual body coordinate system.
[0043] In some embodiments, the virtual posture parameters of the test vehicle do not change in a static traffic environment, and the vehicle virtual posture sensor unit obtains the current virtual posture parameters of the vehicle that do not change. Or the virtual posture parameters of the test vehicle change in a dynamic traffic environment, and the vehicle virtual posture sensor unit obtains the current virtual posture parameters of the vehicle that change. The embodiments of this specification obtain the unchanged or changed virtual posture parameters of the vehicle according to the adaptability of the test vehicle environment scene, so as to adapt the road traffic markings later.
[0044] After receiving the virtual posture parameters of the tested intelligent connected vehicle, the projector array control unit generates an image corresponding to the range of road traffic markings for each projector in the high-dynamic projector array in the map coordinate system corresponding to the simulated traffic scene; since the virtual posture parameters of the vehicle correspond to the virtual body coordinate system and the projector array corresponds to the projection coordinate system, the image is finally adapted to the virtual body coordinate system and output by the corresponding projector in the high-dynamic projector array. In this way, the road traffic markings are consistent with the real road traffic markings from the perspective of the vehicle running on the drum platform.
[0045] In the embodiments of this specification, the virtual coordinate system of the moving vehicle is used as a reference, and the map coordinate system and the projector coordinate system of the simulated traffic scene are converted to the virtual coordinate system of the vehicle. In this way, the simulated adaptation of the vehicle road traffic marking range is achieved by unifying to the vehicle virtual coordinate system, and finally the projector array receives the image and projects the road traffic marking represented by the image to the ground in front of the drum platform. The road traffic marking range includes various road traffic markings in static and dynamic traffic scenes, such as lane lines, parking lines, pedestrian crossings, etc., and also involves the position, shape and range of road traffic markings (such as simulating a large range of road traffic markings).
[0046] The road traffic marking generation system provided in the embodiments of this specification can provide road traffic marking excitation for intelligent connected vehicles that are testing advanced driver assistance functions or autonomous driving functions on a drum platform. The road traffic markings in the embodiments of this specification appear consistent with real road traffic markings from the perspective of a vehicle running on a drum platform. There is no need to develop proprietary interfaces for the intelligent connected vehicles being tested, nor is there any need to make unnecessary improvements to the test vehicles, and there is no need to use a ring screen system, which saves improvement costs. At the same time, simple improvements compared to the prior art solve the problems of being unable to simulate road traffic markings and being unable to test the perception and decision-making functions of intelligent connected vehicles related to road traffic markings on a drum platform.
[0047] In some embodiments, the projector control unit is used to generate an image corresponding to the range of changing road traffic markings in the map coordinate system according to the changing virtual posture parameters in the virtual body coordinate system where the vehicle is located, combined with the simulated traffic scene; obtain the number and position of the projectors in the projection coordinates; and for each projector, convert the image corresponding to the range of changing road traffic markings from the map coordinate system to the projection coordinate system where the projector is located pixel by pixel for correction to obtain a corrected image; convert the corrected image from the projection coordinate system to the virtual body coordinate system to form the changing road traffic markings and transmit it to the projector array for output.
[0048] In combination with the above embodiments, the embodiments of this specification use a projector array to project road traffic markings. Since the projector array system is flexible and changeable, it can simulate arbitrarily complex road traffic markings, which saves high costs compared to the ring screen system used in the prior art.
[0049] For example, the projector array can be flexibly adapted according to its layout position and layout number, so that the road traffic marking generation system of the embodiment of this specification can also simulate a large range of road traffic markings (for example, 200 meters), expand the long-distance detection capability of the autonomous driving or advanced driver assistance system, etc.
[0050] Specifically, the projector array control unit generates an image corresponding to the range of road traffic markings adapted to the vehicle in the map coordinate system based on the virtual posture parameters in the virtual body coordinate system of the vehicle and the simulated traffic scene. In some embodiments, the projector array control unit also needs to obtain the coordinate parameters corresponding to the vehicle in the map coordinate system based on the virtual posture parameters of the vehicle to generate an image corresponding to the range of road traffic markings adapted to the vehicle in the map coordinate system. In particular, it includes generating an image corresponding to the range of changing road traffic markings.
[0051] The number and position of the projectors are obtained. Since the projector array corresponds to the projection coordinate system, in order to project the image through the projector, the image corresponding to the road traffic marking range is converted pixel by pixel from the map coordinate system to the projection coordinate system where the projector is located for correction to compensate for the installation error of the projector and the projection deformation to obtain the corrected image. Finally, the image is converted from the projector coordinate system to the virtual body coordinate system of the tested intelligent connected vehicle and output to the corresponding projector in the high-dynamic projector array.
[0052] According to the virtual posture parameters of the vehicle on the drum platform, the simulated adaptation of the vehicle road traffic marking range is achieved by unifying the virtual coordinate system of the vehicle in combination with the traffic scene to be simulated, so as to change the position and / or shape of the road traffic marking according to the dynamic traffic environment. For example, the road traffic marking can be flexibly set to a straight line, or flexibly set to a curved line (such as Figure 3 shown) etc.
[0053] In some embodiments, the projector array control unit is used to generate curved road traffic markings adapted to the vehicle according to the current virtual posture parameters of the vehicle, so that the projector array outputs the curved road traffic markings.
[0054] The vehicle-in-the-loop test procedure includes a curved road test process, and the test road consists of a straight road and a connected curved road. The existing technology of vehicle-in-the-loop testing on a drum platform cannot realize the test of curved roads.
[0055] The embodiments of this specification not only realize the curved road test, but also can flexibly set the number and position of projectors in the projector array. The vehicle under test runs on a drum platform, which allows the vehicle's power system to operate and allows the steering system to turn. The automatic driving system of the vehicle under test obtains the GNSS simulation signal and trigger signal from the GNSS simulator. Therefore, from the perspective of the automatic driving system of the vehicle under test, the vehicle is moving on a real road. After the vehicle virtual posture sensor unit obtains the virtual parameters of the vehicle under test in the current test scene, the projector array control unit calculates the road traffic marking projection screen (curved road) according to the virtual parameters, and sends it to the projector array so as to project the road markings (especially the curved road) onto the ground in front of the drum platform. In some embodiments, the projector array sets a synchronous trigger pulse unit according to its position and number, and projects the road markings onto the ground in front of the drum platform under the control of the trigger signal.
[0056] Therefore, if Figure 3 As shown in the implementation of this specification, a projector array is used to realize curved road traffic markings. From the perspective of the test vehicle in virtual motion, the performance of the road markings is consistent with the road markings on the real sports field, so that the vehicle can be sensed, identified and controlled normally, and the test of curved roads in the whole vehicle-in-the-loop test on the drum platform can be realized.
[0057] In some embodiments, the road traffic marking generation system also includes a synchronization trigger pulse unit; multiple projectors form a projector array, and the projector array is connected to the synchronization trigger pulse unit. The synchronization trigger pulse is used to send a synchronization signal to all projectors so that the projector array uses the same synchronization signal for synchronized trigger projection.
[0058] like Figure 2 As shown, the road traffic marking generation system also includes a synchronous trigger pulse unit. Multiple projectors form a projector array. The projector array is connected to the synchronous trigger pulse unit. The synchronous trigger pulse unit sends a synchronization signal to all projectors so that the projector array uses the same synchronization signal for synchronous trigger projection. Before the next pulse arrives, the projector keeps outputting the current image frame.
[0059] In other words, the high-dynamic projector and the perception system of the tested intelligent networked car use the same trigger signal for acquisition, and keep and no longer refresh after outputting the image, that is, the projector keeps outputting the current image frame before the next pulse comes. This ensures that the projected road traffic markings captured by the camera system of the intelligent networked car will not interfere with each other.
[0060] In some embodiments, the synchronous trigger pulse unit is also used to trigger the perception system of the vehicle to be tested to collect data.
[0061] The indoor drum platform provided in the embodiments of this specification is used to test the automatic driving function or advanced driving assistance function of the intelligent networked vehicle, and must be able to realize the simulation part of the intelligent networked vehicle perception system (such as camera, millimeter wave radar, laser radar, etc.). Therefore, in combination with the above embodiments, the embodiments of this specification add a synchronous trigger pulse unit, which is also used to trigger the perception system of the vehicle to be tested for data collection.
[0062] In combination with the above embodiments, the embodiments of this specification implement the vehicle-in-the-loop test of ISO-11270-Lane Keeping Assist System LKA. Specifically, the test procedure includes a "curved road test process", and the test road consists of a straight road and a connected curved road. If the method provided by the present invention is not used, it is impossible to perform the test on the drum platform with the existing technology. Using the technology provided by the present invention, the detailed test method is described as follows:
[0063] The test vehicle runs on a rotating drum platform, which allows the vehicle's power system to operate and the steering system to steer. The test vehicle's autonomous driving system obtains GNSS simulation signals and trigger signals from the GNSS simulator. Therefore, from the perspective of the test vehicle's autonomous driving system, the vehicle is moving on a real road. The vehicle's virtual position and attitude sensor unit measures the test vehicle's virtual position and virtual attitude in the current test scene. The projector array control unit calculates the road marking projection image based on the virtual position and attitude, and sends it to the projection array. Under the control of the trigger signal, the road traffic markings are projected onto the ground in front of the rotating drum platform. From the perspective of the virtually moving test vehicle, the performance of the road markings is consistent with the road markings on the real sports field, so that the vehicle can be perceived, identified and controlled normally.
[0064] The embodiments of this specification use a projector array to project road traffic markings on the ground in front of the intelligent connected vehicle drum test platform, and dynamically change the position and shape of the road traffic markings according to the current virtual posture of the tested intelligent connected vehicle, so that the perception system of the intelligent connected vehicle being tested on the drum perceives the same road traffic markings as in the open road test or the closed park test, thereby solving the problem that the existing technology incentive system cannot simulate or is difficult to simulate the important traffic environment of road traffic markings.
[0065] The embodiments of this specification also provide an autonomous driving in-the-loop test system. In combination with the above embodiments, a road traffic marking generation system is used as an incentive system, and the incentive system or other incentive systems are used to expand the traffic scenario of the vehicle in-the-loop test system based on a rotating drum platform.
[0066] The road traffic marking generation system provided in the embodiments of this specification can be used as a separate incentive system to provide traffic scene incentives for advanced driving assistance vehicle-in-the-loop tests such as LKAS (Lane Keeping Assist Systems), LDWS (Lane Departure Warning System), and AEB (Autonomous Emergency Braking). It can also be used together with other incentive systems to expand the traffic scene incentive range and capabilities of the vehicle-in-the-loop test system based on a drum platform.
[0067] In some embodiments, the autonomous driving in-the-loop test system further includes robot-controlled targets disposed around the rotating drum platform, wherein the targets are used in conjunction with traffic markings to enable the vehicle to perform complex autonomous driving tests on the rotating drum platform based on the vehicle's motion position and posture.
[0068] The target object is arranged at the front, two sides or the rear of the drum platform.
[0069] In the embodiment of this specification, more robot-controlled targets are added around the drum platform (in front, on the side, and even behind), and these targets also move synchronously according to the movement position and posture of the vehicle. Combined with the projected road markings on the ground generated by the present invention, more complex L3 level autonomous driving tests (such as Figure 4 shown).
[0070] In combination with the above embodiments, the embodiments of this specification also provide a method for generating road traffic markings, such as Figure 5 As shown, the road traffic marking generation method includes: steps S501 to S503. In step S501, the vehicle virtual posture sensor unit obtains the virtual posture parameters of the test vehicle from the drum platform. In step S502, the projector array control unit uses the virtual body coordinate system where the virtual posture parameters are located as a reference benchmark, and unifies the road traffic marking range generated in the simulated traffic scene map coordinate system into a virtual body coordinate system through the projection coordinate system where the projector array is located, and generates an image corresponding to the vehicle road traffic marking range in the virtual body coordinate system for the projector array, and transmits the image to the projector array for output. In step S503, the projector array receives the image and projects the road traffic marking represented by the image to the ground in front of the drum platform.
[0071] Specifically, in step S501, the test vehicle performs an in-loop test process on a drum platform. In the real world, the road traffic markings are stationary, and the test vehicle is moving. When uploading the test on the drum platform, the vehicle is stationary (the drum platform only provides road load for the vehicle, and the vehicle itself does not move), so that the road traffic markings move relatively, and the vehicle is stationary in the moving vehicle coordinate system (note that the moving vehicle coordinate system is virtual). Therefore, the vehicle virtual posture sensor unit obtains the virtual posture parameters of the test vehicle from the drum platform, such as the current virtual position and virtual posture of the vehicle in six degrees of freedom, so as to subsequently generate road traffic markings according to the above virtual posture parameters. The vehicle virtual posture parameters correspond to the virtual vehicle body coordinate system. The embodiment of this specification obtains the unchanged or changed virtual posture parameters of the vehicle according to the adaptability of the test vehicle environment scene, so as to adapt the road traffic markings later.
[0072] In step S502, after the projector array control unit receives the virtual posture parameters of the tested intelligent networked vehicle, it generates an image corresponding to the range of road traffic markings for each projector in the high dynamic projector array in the map coordinate system corresponding to the simulated traffic scene; since the virtual posture parameters of the vehicle correspond to the virtual body coordinate system, and the projector array corresponds to the projection coordinate system, the image is finally adapted to the virtual body coordinate system and output by the corresponding projector in the high dynamic projector array. In this way, the road traffic markings are consistent with the real road traffic markings from the perspective of the vehicle running on the drum platform.
[0073] According to the obtained vehicle virtual posture parameters, such as virtual position and virtual posture, and according to the simulated traffic scene pre-set by the drum platform, the range of the road traffic markings to be projected is calculated, and the map coordinate system and the projector coordinate system of the simulated traffic scene are converted to the virtual coordinate system of the vehicle with the virtual coordinate system of the moving vehicle as a reference, so that the simulation adaptation of the range of the vehicle's road traffic markings is achieved by unifying to the vehicle's virtual coordinate system, and a corresponding image is generated for each projector according to the number and position of the projectors in the high-dynamic projector array. The road traffic markings include straight lines, curved lines, etc., which are suitable for various road traffic markings in simulated traffic scenes.
[0074] In step S503, the projector array receives the image and projects the road traffic markings represented by the image onto the ground in front of the drum platform.
[0075] The relative moving road traffic markings are generated according to their positions and quantities, and finally the projector array receives the image and projects the road traffic markings represented by the image onto the ground in front of the drum platform. Each projector keeps outputting the current image frame until the next pulse image arrives.
[0076] In some embodiments, the road traffic marking generation method also includes: the projector array control unit generates an image corresponding to the range of changing road traffic markings in the map coordinate system according to the virtual posture parameters that change in the virtual body coordinate system where the vehicle is located, combined with the simulated traffic scene; obtains the number and position of the projectors in the projection coordinate system; and for each projector, converts the image corresponding to the range of changing road traffic markings from the map coordinate system to the projection coordinate system where the projector is located pixel by pixel for correction to obtain a corrected image; converts the corrected image from the projection coordinate system to the virtual body coordinate system to form the changing road traffic markings and transmits it to the projector array for output.
[0077] Specifically, the road traffic marking range to be projected is calculated based on the simulated traffic scene pre-set by the drum platform and the current virtual position of the intelligent connected vehicle.
[0078] In some embodiments, the projector array control unit also needs to obtain the coordinate parameters corresponding to the vehicle in the map coordinate system according to the virtual posture parameters of the vehicle to generate an image corresponding to the range of road traffic markings adapted to the vehicle in the map coordinate system, especially including generating an image corresponding to the range of changing road traffic markings.
[0079] The number and position of the projectors are obtained. Since the projector array corresponds to the projection coordinate system, in order to project the image through the projector, the image corresponding to the road traffic marking range is converted pixel by pixel from the map coordinate system to the projection coordinate system where the projector is located for correction to compensate for the installation error of the projector and the projection deformation to obtain the corrected image. Finally, the image is converted from the projector coordinate system to the virtual body coordinate system of the tested intelligent connected vehicle and output to the corresponding projector in the high-dynamic projector array.
[0080] In some embodiments, under the control of the synchronous trigger pulse unit, the high dynamic projector array projects the corresponding images from the control unit onto the ground in front of the drum platform. The synchronous trigger pulse unit is also used to trigger the data collection of the perception system of the tested intelligent networked vehicle. Before the next pulse comes, the projector keeps outputting the current image frame.
[0081] The method for generating road traffic markings in the embodiments of this specification requires almost no modification to the test vehicle itself, and uses a projection system to generate traffic road markings, thereby saving costs. Not only can any complex road traffic markings be realized, but also the same trigger signal is used to maintain and no longer refresh the image output by the projector, thereby ensuring that the projected road traffic markings captured by the camera system of the intelligent connected vehicle will not interfere with each other.
[0082] The same or similar parts between the various embodiments in this specification can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the product embodiment described later, since it corresponds to the method, the description is relatively simple, and the relevant parts can be referred to the partial description of the system embodiment.
[0083] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A road traffic marking generation system, characterized in that: It includes a vehicle virtual posture sensor unit, a projector array control unit and a projector array; The vehicle virtual posture sensor unit is used to obtain the virtual posture parameters of the test vehicle from the drum platform; The projector array control unit is used to use the virtual body coordinate system where the virtual posture parameters are located as a reference benchmark, unify the road traffic marking range generated in the simulated traffic scene map coordinate system into a virtual body coordinate system through the projection coordinate system where the projector array is located, generate an image corresponding to the road traffic marking range of the vehicle in the virtual body coordinate system for the projector array, and transmit the image to the projector array for output; The projector array is used to receive the image and project the traffic markings represented by the image onto the ground in front of the drum platform, so that the vehicle can perform auxiliary function testing or road traffic marking excitation according to the traffic markings on the drum platform; The projector array control unit is used to generate an image corresponding to the range of the changing road traffic markings in the map coordinate system according to the virtual posture parameters that change in the virtual body coordinate system where the vehicle is located, combined with the simulated traffic scene; Obtain the number and position of the projectors; and for each projector, convert the image corresponding to the range of the changed road traffic markings from the map coordinate system to the projection coordinate system where the projector is located pixel by pixel for correction to obtain a corrected image; The corrected image is converted from the projection coordinate system to the virtual vehicle body coordinate system to form a changed road traffic marking and transmitted to the projector array for output.
2. A road traffic marking generation system according to claim 1, characterized in that: The projector array control unit is used to generate curved road traffic markings adapted to the vehicle according to the current virtual posture parameters of the vehicle, so that the projector array outputs the curved road traffic markings.
3. A road traffic marking generation system according to claim 1, characterized in that: The road traffic marking line generation system also includes a synchronous trigger pulse unit; A plurality of projectors form the projector array, and the projector array is connected to the synchronization trigger pulse unit. The synchronization trigger pulse unit is used to send a synchronization signal to all projectors so that the projector array uses the same synchronization signal to perform synchronization trigger projection.
4. A road traffic marking generation system according to claim 3, characterized in that: The synchronous trigger pulse unit is also used to trigger the perception system of the vehicle to be tested to collect data.
5. An autonomous driving in-the-loop test system, characterized in that: The road traffic marking generation system as described in any one of claims 1 to 4 is used as an excitation system, and the excitation system or other excitation systems are used to expand the traffic scenario of the vehicle-in-the-loop test system based on the drum platform.
6. The autonomous driving in-the-loop test system according to claim 5, characterized in that: The autonomous driving in-the-loop test system also includes robot-controlled targets set around the drum platform, which are used to form new traffic scenes in combination with traffic markings so that the vehicle can perform complex autonomous driving tests on the drum platform based on the vehicle's movement position and posture.
7. The automatic driving in-the-loop test system according to claim 6, characterized in that: The target object is arranged at the front, two sides or the rear of the drum platform.
8. A method for generating road traffic markings, characterized in that: Using the road traffic marking generation system according to any one of claims 1 to 4, the road traffic marking generation method comprises: The vehicle virtual posture sensor unit obtains the virtual posture parameters of the test vehicle from the drum platform; The projector array control unit uses the virtual vehicle body coordinate system where the virtual posture parameters are located as a reference benchmark, unifies the road traffic line range generated in the simulated traffic scene map coordinate system into a virtual vehicle body coordinate system through the projection coordinate system where the projector array is located, generates an image corresponding to the road traffic line range of the vehicle in the virtual vehicle body coordinate system for the projector array, and transmits the image to the projector array for output; The projector array is used to receive the image and project the traffic markings represented by the image onto the ground in front of the drum platform.
9. The method for generating road traffic markings according to claim 8, characterized in that: The road traffic marking generation method also includes: The projector array control unit generates an image corresponding to the range of the changed road traffic markings in the map coordinate system according to the changed virtual posture parameters in the virtual body coordinate system where the vehicle is located, combined with the simulated traffic scene; The number and position of the projectors in the projection coordinate system are obtained; and for each projector, the image corresponding to the range of the changed road traffic markings is converted pixel by pixel from the map coordinate system to the projection coordinate system where the projector is located for correction to obtain a corrected image; The corrected image is converted from the projection coordinate system to the virtual vehicle body coordinate system to form a changing road traffic marking and transmitted to the projector array for output.
Citation Information
Patent Citations
Development and test system and method for whole vehicle in-the-loop automatic driving in laboratory
CN112987703A
