Vehicle-road cooperation test device and system based on sand table

Abstract

The invention discloses a sand table-based vehicle-road cooperation test device and system, and belongs to the technical field of traffic control and intelligent driving. Comprising a three-dimensional data generation module, a driving control module, a traffic flow control module, a vehicle monitoring module, a central control module and a display module. The three-dimensional data generation module is used for acquiring and generating three-dimensional point cloud information; the central control module generates a corresponding control instruction by using the three-dimensional point cloud information; the driving control module is used for receiving a control instruction to control the trolley to drive; the traffic flow control module is used for receiving a control instruction to adjust traffic light duration, the vehicle monitoring module is used for monitoring the state of a trolley, and the display module is used for displaying trolley information. According to the method, automatic driving simulation of the vehicle can be realized, and the method is more universal.

Description

Technical Field

[0001] The present invention relates to the field of traffic control and intelligent driving technology, and in particular to a vehicle-road collaboration testing device and system based on a sandbox. Background Art

[0002] At present, there are two main testing methods in the field of unmanned driving, namely simulation testing and real vehicle testing. Simulation testing is to use software in a computer to simulate the test environment, so as to achieve the test effect of the functions in intelligent driving. Real vehicle testing is to install the intelligent driving functions to be tested on the real vehicle and test the functions of intelligent driving in real scenes. In the simulation of the test environment, some variables need to be ignored or idealized in the simulation experiment, and it is impossible to restore the driving environment of the vehicle in reality more comprehensively. At the same time, simulation testing requires computer support, so the computing power of the computer will also limit the degree of restoration of the simulation test to the actual test situation. The cost of real vehicle testing is relatively high: first, the test needs to be equipped with a real vehicle to carry out; second, the test also requires the support of the corresponding venue. At the same time, there are certain safety hazards in real vehicle testing. Since some real vehicle tests will be carried out in an open road environment, safety issues may arise. In view of the above situation, it is urgent to design a system to solve the problems of low accuracy of computer simulation testing, high traffic cost of real vehicle testing, and great safety hazards in the existing technology.

[0003] Therefore, it is an urgent problem for those skilled in the art to propose a sandbox-based vehicle-road cooperative testing device and system to solve the problems existing in the prior art. Summary of the invention

[0004] In view of this, the present invention provides a vehicle-road collaboration testing device and system based on a sandbox, which can achieve an effective control effect.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A vehicle-road collaboration test device based on a sandbox includes a traffic road sandbox and a central control device.

[0007] In the above device, optionally, the traffic road sand table includes a traffic road sand table scene and a car;

[0008] The traffic road sandbox scene includes simulated traffic lights, toll booths, parking lots, roads, magnetic lines, identification point devices, laser radars, millimeter-wave radars, and motion capture cameras;

[0009] The car is equipped with a detection device for identifying road magnetic lines and identification points, an industrial camera and a vehicle body status detection device.

[0010] The above-mentioned device, optionally, the central control equipment includes an intelligent traffic simulation supervision cloud platform and a control device; the intelligent traffic simulation supervision cloud platform displays multiple interfaces, and the control device controls the movement of the car.

[0011] A sandbox-based vehicle-road collaboration test system, which implements any of the above-mentioned sandbox-based vehicle-road collaboration test devices, comprises: a three-dimensional data generation module, a driving control module, a vehicle flow control module, a vehicle monitoring module, a central control module and a display module;

[0012] A three-dimensional data generation module is connected to the input end of the central control module and is used to obtain and generate three-dimensional point cloud information;

[0013] The central control module is used to generate corresponding control instructions using the received three-dimensional point cloud information;

[0014] A driving control module is connected to the first output terminal of the central control module and is used to receive control instructions to control the driving of the vehicle;

[0015] A vehicle flow control module is connected to the second output terminal of the central control module and is used to receive control instructions to adjust the duration of the traffic light;

[0016] The vehicle monitoring module and the display module are connected to the third output terminal of the central control module. The vehicle monitoring module is used to monitor the state of the vehicle itself, and the display module is used to display the vehicle information.

[0017] Optionally, in the above system, in the three-dimensional data generation module, laser radar and millimeter wave radar are used to generate three-dimensional point cloud information, and the images obtained by the motion capture camera are combined for feature extraction to generate a 3D image.

[0018] The above system, optionally, the driving control module is based on a detection device for identifying road magnetic lines, identification points and an industrial camera, including an automatic tracking unit and an image detection unit.

[0019] In the above system, optionally, the vehicle monitoring module includes a posture control unit and a state monitoring unit;

[0020] The posture control unit is used to control and adjust the posture of the car;

[0021] The status monitoring unit is used to monitor the vehicle information, including battery status, network status and vehicle ID.

[0022] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides a sandbox-based vehicle-road collaborative testing device and system, which has the following beneficial effects: 1) Compared with traditional computer simulation testing, the present invention is closer to the actual application scenario and has a better demonstration effect; 2) Compared with real vehicle simulation, the present invention can control the cost within a lower range and has less safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0024] Figure 1 It is a schematic diagram of a vehicle-road collaboration test device based on a sandbox disclosed in the present invention;

[0025] Figure 2 A block diagram of a vehicle-road cooperative test system based on a sandbox disclosed in the present invention;

[0026] Figure 3 This is a schematic diagram of a sandbox-based vehicle-road collaborative testing system disclosed in the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0028] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0029] The invention discloses a vehicle-road collaboration test device based on a sandbox, comprising a traffic road sandbox and a central control device.

[0030] Furthermore, the traffic road sandbox includes a traffic road sandbox scene and a car;

[0031] The traffic road sandbox scene includes simulated traffic lights, toll booths, parking lots, roads, magnetic lines, identification point devices, laser radars, millimeter wave radars, and motion capture cameras;

[0032] The car is equipped with a detection device for identifying road magnetic lines and identification points, an industrial camera and a vehicle body status detection device.

[0033] Furthermore, the traffic road sand table is scaled down in proportion to the actual road, with traffic lights, toll booths, parking lots, magnetic lines and identification point devices as road facilities, and the road includes intersections, loops, viaducts, U-turns, S-turns and other terrains.

[0034] Further, see Figure 1 As shown, the central control equipment includes an intelligent traffic simulation supervision cloud platform and a control device; the intelligent traffic simulation supervision cloud platform displays multiple interfaces, and the control device controls the movement of the car.

[0035] Specifically, the intelligent traffic simulation supervision cloud platform also includes a vehicle status display interface, an interface for the number and status of street lights on the road, and a network status interface.

[0036] The present invention also discloses a sandbox-based vehicle-road collaboration test system, which implements any of the sandbox-based vehicle-road collaboration test devices described above, and the implementation method is as follows: Figure 2 and Figure 3 As shown, it includes: a three-dimensional data generation module, a driving control module, a vehicle flow control module, a vehicle monitoring module, a central control module and a display module;

[0037] A three-dimensional data generation module is connected to the input end of the central control module and is used to obtain and generate three-dimensional point cloud information;

[0038] The central control module is used to generate corresponding control instructions using the received three-dimensional point cloud information;

[0039] A driving control module is connected to the first output terminal of the central control module and is used to receive control instructions to control the driving of the vehicle;

[0040] A vehicle flow control module is connected to the second output terminal of the central control module and is used to receive control instructions to adjust the duration of the traffic light;

[0041] The vehicle monitoring module and the display module are connected to the third output terminal of the central control module. The vehicle monitoring module is used to monitor the state of the vehicle itself, and the display module is used to display the vehicle information.

[0042] Furthermore, in the three-dimensional data generation module, laser radar and millimeter-wave radar are used to generate three-dimensional point cloud information, and the images obtained by the motion capture camera are combined for feature extraction to generate 3D images.

[0043] Specifically, lidar, millimeter-wave radar and motion capture camera are used for initial environmental monitoring. Lidar is the most commonly used sensor for detecting objects. It has the advantages of high precision, high resolution, long distance and wide scanning area. It can quickly and in real time obtain the three-dimensional spatial information of the measured object, and further obtain the lidar point cloud. The millimeter-wave radar sensor is robust to the environmental impact of bad light and weather conditions, and can identify targets in complex scenes. Further obtain the millimeter-wave radar point cloud. By comparison, the point cloud obtained by the millimeter-wave radar is very sparse and uneven; while the lidar point cloud is dense and uniform. Combined with the camera to obtain pictures, multi-sensor fusion can be used to optimize and obtain more accurate information. The steps include dividing the detection into two stages, using the first-stage visual detection results to associate millimeter-wave features for feature fusion and performing secondary corrections on the first-stage results. First, a first-stage prediction of the target is generated, and then the radar point cloud is expanded vertically to a long cylinder on the ground to achieve end-to-end clutter filtering and modal alignment. Finally, the multi-modal features are used to correct the first-stage results.

[0044] Furthermore, the driving control module is based on a detection device for identifying road magnetic lines, identification points and an industrial camera, including an automatic tracking unit and an image detection unit.

[0045] Specifically, when the car is moving, it is necessary to predict the vehicle trajectories of the vehicles around the car. When the car is driving in a simulated sandbox, the automatic tracking unit contains a magnetic sensor for detecting the magnetic lines laid on the road for automatic tracking. The image detection unit includes an industrial camera for detecting the indication signals of the identification points for corresponding driving, including left turns, right turns, U-turns, parking and speed limits.

[0046] Further, the image detection unit operates as follows:

[0047] 1. Visual processing: convert the image read by the camera, adjust it to a grayscale image, dilate it with a 10x10 rectangle (dilation of white is equivalent to corroding the black part including the lane line) to remove black noise, then perform an inverse threshold transformation, and then perform a perspective transformation to convert it into a bird's-eye view. Next, extract the lane lines from the bird's-eye view;

[0048] 2. Count the number of white dots in the x-direction of half the size, consider the x-coordinate of the maximum value as the starting point of the lane line, and then use the sliding window method to include the pixel coordinate distribution of the lane line. Process the coordinate distribution with a quadratic curve fitting, and determine whether the identified lane line is the left lane or the right lane based on the intersection of the quadratic curve with the parallel line of the vehicle head in the real coordinate system (a coordinate system parallel to the ground established with the camera as the coordinate origin). This way, all the geometric information of the required lane line is obtained.

[0049] Furthermore, in the sandbox simulation, the traffic flow control module needs to control the traffic lights in the sandbox.

[0050] Specifically, the central control module obtains the actual current traffic situation in the sandbox based on the above-mentioned data, and controls the traffic control system to coordinate the traffic signals at single-point intersections and traffic signals at complex road network intersections. When there are many vehicles traveling and congestion occurs, the duration of the traffic lights is adjusted to lengthen the green light time on the road section with congested vehicles, so that the cars can pass through the congested section as soon as possible.

[0051] Further, the vehicle monitoring module includes a posture control unit and a state monitoring unit;

[0052] The posture control unit is used to control and adjust the posture of the car;

[0053] The status monitoring unit is used to monitor the vehicle information, including battery status, network status and vehicle ID.

[0054] Specifically, the posture control unit adopts PID control, including:

[0055] Proportional link: It reflects the deviation signal e(t) of the control system in real time and proportionally. Once the deviation occurs, the controller immediately takes control action to reduce the error. When the deviation e=0, the control action is also 0. Therefore, proportional control is regulated based on the deviation, that is, differential regulation.

[0056] Integral link: It can memorize the error and is mainly used to eliminate static error and improve the system's zero-error degree. The strength of the integral effect depends on the integral time constant Ti. The larger Ti is, the weaker the integral effect is, and vice versa.

[0057] Differential link: It can reflect the changing trend (rate of change) of the deviation signal and introduce an effective early correction signal into the system before the deviation signal value becomes too large, thereby speeding up the system's action speed and reducing the adjustment time.

[0058] In a specific embodiment, the car information is captured by a motion capture camera, and automatic driving between specific locations on the road is achieved through laser radar, millimeter wave radar, and detection devices, and the information on the sandbox is transmitted in real time to the intelligent traffic simulation supervision cloud platform for storage and recording.

[0059] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0060] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle-road collaboration test device based on a sandbox, characterized in that: Including traffic road sand table and central control equipment.

2. The vehicle-road collaboration test device based on a sandbox according to claim 1, characterized in that: The traffic road sandbox includes traffic road sandbox scenes and cars; The traffic road sandbox scene includes simulated traffic lights, toll booths, parking lots, roads, magnetic lines, identification point devices, laser radars, millimeter-wave radars, and motion capture cameras; The car is equipped with a detection device for identifying road magnetic lines and identification points, an industrial camera and a vehicle body status detection device.

3. The vehicle-road cooperative testing device based on a sandbox according to claim 1, characterized in that: The central control equipment includes an intelligent traffic simulation supervision cloud platform and control devices; The intelligent traffic simulation supervision cloud platform displays multiple interfaces, and the control device controls the movement of the car.

4. A sandbox-based vehicle-road collaboration test system, characterized in that: A vehicle-road cooperative test device based on a sandbox for implementing any one of claims 1 to 3, comprising: a three-dimensional data generation module, a driving control module, a vehicle flow control module, a vehicle monitoring module, a central control module and a display module; A three-dimensional data generation module is connected to the input end of the central control module and is used to obtain and generate three-dimensional point cloud information; The central control module is used to generate corresponding control instructions using the received three-dimensional point cloud information; A driving control module is connected to the first output terminal of the central control module and is used to receive control instructions to control the driving of the vehicle; A vehicle flow control module is connected to the second output terminal of the central control module and is used to receive control instructions to adjust the duration of the traffic light; The vehicle monitoring module and the display module are connected to the third output terminal of the central control module. The vehicle monitoring module is used to monitor the state of the vehicle itself, and the display module is used to display the vehicle information.

5. The vehicle-road cooperative testing system based on a sandbox according to claim 4, characterized in that: In the three-dimensional data generation module, laser radar and millimeter-wave radar are used to generate three-dimensional point cloud information, and the images obtained by the motion capture camera are combined for feature extraction to generate 3D images.

6. The vehicle-road cooperative testing system based on a sandbox according to claim 4, characterized in that: The driving control module is based on a detection device for identifying road magnetic lines, identification points and an industrial camera, and includes an automatic tracking unit and an image detection unit.

7. The vehicle-road cooperative testing system based on a sandbox according to claim 4, characterized in that: The vehicle monitoring module includes a posture control unit and a state monitoring unit; The posture control unit is used to control and adjust the posture of the car; The status monitoring unit is used to monitor the vehicle information, including battery status, network status and vehicle ID.

Images