An intersection vehicle-road coordination roadside sensor deployment method, system and medium

Abstract

The application relates to a kind of intersection vehicle road cooperation roadside sensor deployment method, system and medium, the deployment method includes S1.Vehicle travels in intersection, based on vehicle GPS and high-precision map, the positioning data information of vehicle is acquired in real time and the driving track of vehicle, the driving track of vehicle is input vehicle collision point simulation test algorithm, and vehicle collision point and driving track with collision point are output;S2.The driving track with collision point and the vehicle collision point are input collision point limit algorithm, and collision limit range is output;S3.In the collision limit range, according to the coverage range of sensor, sensor deployment is completed.The application not only improves the efficiency of intersection vehicle traffic, but also further improves the safety of vehicle driving.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sensor deployment, in particular to a crossroad vehicle-road cooperation roadside sensor deployment method, system and medium. BACKGROUND

[0002] Vehicle-road cooperation is to use advanced wireless communication and new generation Internet technology, to implement vehicle-vehicle and vehicle-road dynamic real-time information interaction in all directions, and to develop vehicle active safety control and road cooperative management on the basis of full-time and space dynamic traffic information collection and fusion, to fully realize the effective cooperation of man, vehicle and road, to ensure traffic safety and improve traffic efficiency, so as to form a safe, efficient and environmentally friendly road traffic system. As the most complex scene of traffic, the safety of vehicle driving cannot be guaranteed, and the efficiency of vehicle passing is not high. Therefore, how to solve the deployment of crossroad vehicle-road cooperation roadside sensors has become a problem we need to solve. SUMMARY

[0003] In view of the above problems, the present application provides a crossroad vehicle-road cooperation roadside sensor deployment method, system and medium, which not only improves the efficiency of crossroad vehicle passing, but also further improves the safety of vehicle driving.

[0004] In order to achieve the above-mentioned purpose and other related purposes, the technical scheme provided by the present application is as follows:

[0005] A crossroad vehicle-road cooperation roadside sensor deployment method, the method comprising:

[0006] S1. The vehicle drives at the crossroad, and based on the vehicle-mounted GPS and high-precision map, the positioning data information of the vehicle and the driving track of the vehicle are obtained in real time, the driving track of the vehicle is input into the vehicle collision point simulation test algorithm, and the vehicle collision point and the driving track with the collision point are output;

[0007] S2. The driving track with the collision point and the vehicle collision point are input into the collision point limit algorithm, and the collision limit range is output;

[0008] S3. In the collision limit range, the sensor is deployed according to the coverage range of the sensor.

[0009] Further, in step S2, the collision point limit algorithm comprises:

[0010] S21. According to the driving track with the collision point, the turning start point coordinates M (x1, y1) of the vehicle and the center coordinate point (x r , y r ) of the circular arc track made at the time of turning are determined, so as to obtain the turning radius R,

[0011]

[0012] S22. Based on the turning radius R and the vehicle collision point, the time taken by the vehicle to pass the collision point is obtained as T,

[0013]

[0014] where v is the real-time speed of the vehicle, (x p , y p ) is the coordinate of the vehicle collision point, T mbk is the deceleration time when braking appropriately, T brt is the vehicle braking reaction time, T plt is the preliminary prediction time.

[0015] S23. Based on the time T taken by the vehicle collision point, the collision limit range G is obtained,

[0016] L max = v max T

[0017]

[0018] where v max is the maximum speed of the vehicle, (x p , y p ) is the coordinate of the vehicle collision point, and L max is the distance of the vehicle passing the collision point.

[0019] Further, in step S22, the preliminary prediction time T plt is:

[0020] T plt = T com + T cpt , where T com is the transmission delay, and T cpt is a constant parameter between 150-220 ms.

[0021] Further, in step S3, the determination of the coverage range of the sensor includes:

[0022] S31. Calculation of the field of view angle: confirm the horizontal field of view angle of the sensor according to the lane width, and calculate the vertical field of view angle of the sensor according to the way of blind spot filling in the opposite direction of the sensor deployment;

[0023] S32. Detection distance calculation: according to the maximum distance between the installation position of the device and the boundary of the coverage range;

[0024] S33. According to the sensor clustering and deep learning algorithm to identify objects, confirm the pedestrians identifying the road zebra crossing and the small vehicles identifying the farthest range.

[0025] Further, in step S33, the sensor clustering and deep learning algorithm identifies the object and fuses the object in real time and transmits the object to the RSU device.

[0026] Further, in step S1, the vehicle collision point simulation test algorithm comprises:

[0027] S11. Obtain the driving trajectory of the vehicle, divide the driving trajectory of the vehicle at equal time intervals, and output the equal-interval divided trajectory data information;

[0028] S12. Based on the equal-interval divided trajectory data information, perform a partial derivative operation on each trajectory, and output the slope data information of each trajectory;

[0029] S13. Based on the slope data information of each trajectory, set a first preset threshold and a second preset threshold, and if the slope data information of each trajectory is between the first preset threshold and the second preset threshold, output the vehicle collision point.

[0030] Further, the first preset threshold and the second preset threshold take any real number between 0 and 1, including 0 and 1.

[0031] To achieve the above object and other related objects, the present application also provides an intersection vehicle-road cooperation road side sensor deployment system, comprising a computer device programmed or configured to perform the steps of any one of the intersection vehicle-road cooperation road side sensor deployment methods.

[0032] To achieve the above object and other related objects, the present application also provides a computer readable storage medium, characterized in that the computer readable storage medium stores a computer program programmed or configured to perform any one of the intersection vehicle-road cooperation road side sensor deployment methods.

[0033] The present application has the following positive effects:

[0034] 1. The present application works by multiple sensors in cooperation and transmits data to the RSU device in real time, which not only provides safety data information to the vehicle in time, but also further improves the safety of the vehicle.

[0035] 2. The present application increases the effectiveness of sensor deployment, which can improve the driving efficiency and safety of the vehicle.

[0036] 3. The present application deploys sensors reasonably by giving the limit range of vehicle collision and the range covered by sensors, selects a reasonable number and performance sensors, and reduces the cost of sensors. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 A flowchart of the method of the present application is shown in the figure;

[0038] Figure 2 A schematic diagram of the vehicle collision point of the present application is shown in the figure;

[0039] Figure 3 A schematic diagram of data transmission between the sensor and the RSU device of the present application is shown in the figure. DETAILED DESCRIPTION

[0040] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, which should be considered in a descriptive sense only. Thus, it will be apparent to those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0041] Embodiment 1: As shown in Figure 1 or Figure 2 A crossroad vehicle-road cooperation roadside sensor deployment method, the method comprising:

[0042] S1. The vehicle travels at the intersection, and based on the vehicle-mounted GPS and high-precision map, real-time acquisition of the positioning data information of the vehicle and the driving trajectory of the vehicle, inputting the driving trajectory of the vehicle into the vehicle collision point simulation test algorithm, and outputting the vehicle collision point and the driving trajectory with the collision point;

[0043] S2. Inputting the driving trajectory with the collision point and the vehicle collision point into the collision point limit algorithm, and outputting the collision limit range;

[0044] S3. Within the collision limit range, according to the coverage range of the sensor, the sensor deployment is completed.

[0045] In this embodiment, in step S2, the collision point limit algorithm comprises:

[0046] S21. According to the driving trajectory with the collision point, determining the turning start point coordinates M(x1, y1) of the vehicle and the center coordinate point(x r , y r ) of the circular arc trajectory made when turning, so as to obtain the turning radius R,

[0047]

[0048] S22. Based on the turning radius R and the vehicle collision point, the time taken by the vehicle to pass through the collision point is T,

[0049]

[0050] Where v is the real-time speed of the vehicle, (x p y p T represents the coordinates of the vehicle collision point. mbk T is the deceleration time during moderate braking. brt T is the vehicle braking reaction time. plt This is a preliminary time estimate;

[0051] S23. Based on the time T spent at the vehicle collision point, the collision limit range G is obtained.

[0052] L max =v max T

[0053]

[0054] Where v max For the maximum speed of the vehicle, (x) p y p L represents the coordinates of the vehicle collision point. max This represents the distance the vehicle travels through the point of collision.

[0055] In this embodiment, in step S22, the preliminary prediction time T plt for:

[0056] T plt =T com +T cpt T com For transmission delay, T cpt It is a constant parameter between 150 and 220 ms.

[0057] Example 2: Based on the method for deploying roadside sensors for vehicle-road cooperation at intersections in Example 1, the present invention will be further described and explained below.

[0058] like Figure 3 As shown, based on a camera sensor, road image data is acquired in real time, and YOLOv3 is used for real-time detection to output the target category and location. Based on a lidar sensor, road point cloud data is acquired in real time, and the road point cloud data is received and parsed in multiple threads to output point cloud clustering data and tracking information. Based on a radar sensor, radar data is acquired in real time, and the radar data, target category and location, point cloud clustering data and tracking information are fused together. The fused data is then transmitted to the RSU device in real time.

[0059] Determining the coverage area of ​​the sensor includes:

[0060] S31. Calculation of field of view: Determine the horizontal field of view of the sensor based on the lane width, and calculate the vertical field of view of the sensor based on the sensor deployment method of opposing blind spot filling;

[0061] S32. Detection distance calculation: Based on the maximum distance between the location where the equipment can be installed and the boundary of the coverage area;

[0062] S33. Based on sensor clustering and deep learning algorithms, identify objects, confirm pedestrians at road zebra crossings and identify small vehicles at the furthest distance.

[0063] In this embodiment, in step S33, the sensor clustering and deep learning algorithm identifies objects and fuses the objects, transmitting them to the RSU device in real time.

[0064] In this embodiment, in step S1, the vehicle collision point simulation test algorithm includes:

[0065] S11. Obtain the vehicle's driving trajectory, divide the vehicle's driving trajectory into equal time intervals, and output the equally divided trajectory data information;

[0066] S12. Based on the equally spaced trajectory data information, perform partial derivative calculations on each trajectory segment and output the slope data information of each trajectory segment;

[0067] S13. Based on the slope data of each trajectory segment, set a first preset threshold and a second preset threshold. If the slope data of each trajectory segment is between the first preset threshold and the second preset threshold, then output the vehicle collision point.

[0068] In this embodiment, the first preset threshold and the second preset threshold are any real numbers between 0 and 1, including 0 and 1.

[0069] To achieve the above and other related objectives, the present invention also provides a vehicle-road cooperative roadside sensor deployment system for intersections, including a computer device programmed or configured to perform the steps of any of the vehicle-road cooperative roadside sensor deployment methods for intersections.

[0070] To achieve the above and other related objectives, the present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program programmed or configured to perform any of the described methods for deploying vehicle-road cooperative roadside sensors at intersections.

[0071] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0072] In summary, this invention not only improves the efficiency of vehicle traffic at intersections, but also further enhances vehicle driving safety.

[0073] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for deploying roadside sensors for vehicle-road cooperation at intersections, characterized in that, The method includes: S1. When a vehicle is driving at an intersection, the vehicle's location data and driving trajectory are obtained in real time based on the vehicle's GPS and high-precision map. The vehicle's driving trajectory is input into the vehicle collision point simulation test algorithm, and the vehicle collision point and the driving trajectory with the collision point are output. S2. Input the driving trajectory with the collision point and the vehicle collision point into the collision point limit algorithm, and output the collision limit range; S3. Within the collision limit range, the sensors are deployed according to their coverage area; In step S2, the collision point limit algorithm includes: S21. Based on the driving trajectory with the collision point, determine the coordinates of the vehicle's turning starting point M(x1, y1) and the coordinates of the center point (x1, y1) of the circular arc trajectory made during the turn. r y r Thus, the turning radius R is obtained. ； S22. Based on the turning radius R and the vehicle collision point, the time T taken for the vehicle to pass the collision point is obtained. ， Where v is the real-time speed of the vehicle, (x p y p T represents the coordinates of the vehicle collision point. mbk T is the deceleration time during moderate braking. brt T is the vehicle braking reaction time. plt This is a preliminary time estimate; S23. Based on the time T spent at the vehicle collision point, the collision limit range G is obtained. ， ， Among them, v max For the maximum speed of the vehicle, (x) p y p L represents the coordinates of the vehicle collision point. max This represents the distance the vehicle travels through the point of collision.

2. The method for deploying vehicle-road cooperative roadside sensors at intersections according to claim 1, characterized in that, In step S22, the preliminary prediction time T plt for: T plt =T com +T cpt T com For transmission delay, T cpt It is a constant parameter between 150 and 220 ms.

3. The method for deploying vehicle-road cooperative roadside sensors at intersections according to claim 1, characterized in that, In step S3, determining the coverage area of ​​the sensor includes: S31. Calculation of field of view: Determine the horizontal field of view of the sensor based on the lane width, and calculate the vertical field of view of the sensor based on the sensor deployment method of opposing blind spot filling; S32. Detection distance calculation: Based on the maximum distance between the location where the equipment can be installed and the boundary of the coverage area; S33. Based on sensor clustering and deep learning algorithms, identify objects, confirm pedestrians at road zebra crossings and identify small vehicles at the furthest distance.

4. The method for deploying vehicle-road cooperative roadside sensors at intersections according to claim 3, characterized in that, In step S33, the sensor clustering and deep learning algorithm identifies objects and fuses the objects, transmitting them to the RSU device in real time.

5. The method for deploying vehicle-road cooperative roadside sensors at intersections according to claim 1, characterized in that, In step S1, the vehicle collision point simulation test algorithm includes: S11. Obtain the vehicle's driving trajectory, divide the vehicle's driving trajectory into equal time intervals, and output the equally divided trajectory data information; S12. Based on the equally spaced trajectory data information, perform partial derivative calculations on each trajectory segment and output the slope data information of each trajectory segment; S13. Based on the slope data of each trajectory segment, set a first preset threshold and a second preset threshold. If the slope data of each trajectory segment is between the first preset threshold and the second preset threshold, then output the vehicle collision point.

6. The method for deploying vehicle-road cooperative roadside sensors at intersections according to claim 5, characterized in that: The first preset threshold and the second preset threshold are any real numbers between 0 and 1, including 0 and 1.

7. A vehicle-road cooperative roadside sensor deployment system for intersections, comprising computer equipment, characterized in that, The computer device is programmed or configured to perform the steps of the intersection vehicle-road cooperative roadside sensor deployment method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is programmed or configured to perform the intersection vehicle-road cooperative roadside sensor deployment method according to any one of claims 1 to 6.

Images