Automatic driving planning control system suitable for regional road

By introducing high-precision maps and improved A* algorithms in the autonomous driving system, combining adaptive obstacle strategies and local search optimization paths, the safety and efficiency problems of autonomous driving vehicles reaching target points on regional roads are solved, and automatic Accurate and safe arrival of vehicles and improve road safety.

CN118977733APending Publication Date: 2024-11-19ZHEJIANG UNIV CITY COLLEGE BINJIANG INNOVATION CENT
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411162583.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing autonomous driving system is difficult to effectively reduce traffic accidents caused by human errors and violations in fixed-area roads, and the path planning and control efficiency are low, resulting in insufficient safety and accuracy of vehicles reaching the target point.

Method used

An autonomous driving planning control system suitable for regional roads was designed, including DCU controller module, path planning module, motion control module and human-computer interaction module, and path planning is used to use high-precision maps, multiple sensors and improved A* algorithm for path planning. , smoothing the road data through a three-time uniform B-spline curve and rectification algorithm, combining adaptive obstacle strategies and local search optimization paths, automatic control of the vehicle is achieved.

Benefits of technology

It realizes that autonomous driving vehicles can accurately and safely reach the target point without human operation, improve road safety and driving efficiency, and reduce traffic accidents caused by human errors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118977733A_ABST
    Figure CN118977733A_ABST
Patent Text Reader

Abstract

The invention discloses an automatic driving planning control system suitable for a regional road. The automatic driving planning control system comprises a DCU controller module, and a path planning module, a motion control module, a positioning module and a man-machine interaction module which are connected with the DCU controller module, the path planning module generates a plurality of path lines connected between the target location and the current location based on the target location and the current location; and the path line with the shortest distance in the path lines is confirmed to control the motion control module to regulate and control an auxiliary steering power system and a vehicle braking electronic control system of the vehicle so as to realize automatic control. According to the method, the driving destination and the current position of the vehicle are combined through the high-precision map to perform global path planning, and then the vehicle is integrally controlled. The automatic driving vehicle automatically plans a proper path by means of an intelligent system, various sensor systems, a high-precision map, a positioning system and the like, and the controller is controlled without manual operation, so that the automatic driving vehicle accurately and safely arrives at a target point.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to an automatic driving planning and control system suitable for regional roads. Background Art

[0002] With the vigorous development of artificial intelligence, the continuous improvement of sensor technology, the continuous progress of satellite navigation technology, and the continuous updating of high-precision maps, the field of autonomous driving has also ushered in great progress. Autonomous driving vehicles have great potential in improving driving safety and road utilization, and will play a very important role in the future road traffic system. For future development, the autonomous driving system should be effectively used to achieve this goal.

[0003] According to data analysis, the proportion of traffic accidents caused by human errors, violations and other behaviors accounts for more than 80% of the total number of road accidents, so the impact of people on road safety should be minimized. In order to achieve this goal, self-driving vehicles equipped with positioning modules, path planning modules, control modules, etc. are required. On fixed area roads, the destination of the driving is combined with the current position of the vehicle through high-precision maps for global path planning, and then the vehicle is controlled as a whole. After the owner selects the destination, the self-driving vehicle relies on intelligent systems, multiple sensor systems, high-precision maps and positioning systems to automatically plan a suitable path from the current location to the destination, and control the controller without human operation, so that the self-driving vehicle can reach the target point accurately and safely. Summary of the invention

[0004] The main purpose of the present invention is to provide an automatic driving planning and control system suitable for regional roads, aiming to solve the above-mentioned technical problems.

[0005] To achieve the above objectives, the present invention provides an automatic driving planning and control system suitable for regional roads.

[0006] The automatic driving planning and control system suitable for regional roads includes a DCU controller module and a path planning module, a motion control module, a positioning module and a human-computer interaction module connected thereto; The human-computer interaction module is used to confirm the target location and the current location; The path planning module generates a plurality of path lines consisting of a plurality of series of points between the target location and the current location based on the target location and the current location; The DCU controller module confirms the shortest path among the paths and controls the motion control module to regulate the auxiliary steering power system and the vehicle braking electronic control system of the vehicle to achieve automatic control.

[0007] In one embodiment, the path planning module is configured to: Obtain the basic information data of the original path, use the cubic uniform B-spline curve to construct the structure based on the basic information data, and reconstruct the cubic uniform B-spline curve through the rectification algorithm , calculate the target path information to obtain the road map.

[0008] In one embodiment, the path planning module is configured to: The original uneven road data sequence set is evenly divided and interpolated; The interpolated data is divided equally and two control points are added to the first position to form an interpolation sequence to calculate the heading angle. as well as ; For a point Pi on the path, calculate its distance to the curve The maximum value is taken as the vertical distance ; ,in Indicate point To the curve C(u) at the parameter The distance between the

[0009] In one embodiment, the path planning module is further configured to: Use improved A* algorithm for path planning; The improved A* algorithm includes: Change the local cost function: The evaluation function of node n in the road is: Where f(n) represents the estimated path cost from the initial point s to the target point g; g(n) represents the actual cost from s to the current node; h(n) represents the estimated cost from the current node to the g node; When the distance between the current node and the end point is closer, in order to quickly increase the value of the evaluation function f(n), h(n) is rewritten as ln|h(n)+1|*h(n). The decision time will be reduced accordingly. The improved f(n) is: .

[0010] In one embodiment, the improved A* algorithm further includes: Adjust the adaptive obstacle strategy function: ; The distribution of obstacles in different road environments is different, and 1-p is set as the weight of the adaptive heuristic function s(n). p is the ratio of the sum of the areas of all obstacles in the map to the total area of ​​the map, and the range of p is [0,1]. The smaller p is, the fewer obstacles there are, and the larger 1-p is, and the larger the evaluation function f(n) is. The evaluation function is: .

[0011] In one embodiment, after the path planning module completes planning the path, determining the physical relationship between the actual position of the vehicle and the actual path; Import the target path model, globally search the position of the vehicle's current position (center of mass position) in the target path, and determine the initial node S; Local search gets the nearest node.

[0012] In one embodiment, the autonomous driving planning and control system applicable to regional roads further includes an information collection module, and the information collection module is used to collect road information; Road information is stored in the system in the form of points, and the point information includes target position coordinates, target curvature, and target heading angle.

[0013] In one embodiment, the autonomous driving planning and control system applicable to regional roads further includes a vehicle positioning module.

[0014] Beneficial effects that can be achieved by the present invention: The embodiment of the present invention proposes an automatic driving planning and control system suitable for regional roads, which combines the destination of driving with the current position of the vehicle through a high-precision map to perform global path planning, and then controls the vehicle as a whole. After the owner selects the destination, the automatic driving vehicle automatically plans a suitable path from the current position to the destination by relying on intelligent systems, multiple sensor systems, high-precision maps and positioning systems, and controls the controller without manual operation, so that the automatic driving vehicle can reach the target point accurately and safely. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic diagram of an automatic driving planning and control system of the present invention; Figure 2 Generating a flow chart for the path of the present invention; Figure 3 It is a flow chart of path planning of the present invention; Figure 4 The nearest point search strategy diagram of the present invention; Figure 5 It is a schematic diagram of a human-computer interaction module of the present invention; Figure 6 This is a schematic diagram of a positioning module of the present invention; Figure 7 It is a schematic diagram of the motion control module of the present invention.

[0016] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0017] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0018] Reference Figure 1-7 , an embodiment of the present invention provides an automatic driving planning and control system applicable to regional roads, wherein the automatic driving planning and control system applicable to regional roads comprises a DCU controller module and a path planning module, a motion control module, a positioning module and a human-computer interaction module connected thereto; The human-computer interaction module is used to confirm the target location and the current location; The path planning module generates a plurality of path lines consisting of a plurality of series of points between the target location and the current location based on the target location and the current location; The DCU controller module confirms the shortest path among the paths and controls the motion control module to regulate the auxiliary steering power system and the vehicle braking electronic control system of the vehicle to achieve automatic control.

[0019] In this application, the destination of the vehicle is combined with the current position of the vehicle through a high-precision map to perform global path planning, and then the vehicle is controlled as a whole. After the driver selects the destination, the autonomous driving vehicle automatically plans a suitable path from the current position to the destination by relying on intelligent systems, multiple sensor systems, high-precision maps and positioning systems, and controls the controller without human operation, so that the autonomous driving vehicle can reach the target point accurately and safely.

[0020] The DCU domain controller is the core of every functional domain of the car. It integrates the core functions of multiple vehicle ECUs and is the "brain" for automatic control. It mainly consists of three parts: domain master processor, operating system, and application software and algorithms.

[0021] First, road data is collected based on GPS and road features are analyzed. This is pre-processing. GPS is used to collect road information and smooth the road data. To achieve automatic vehicle control, a smooth and stable target path needs to be input. The target path data collected by GPS is recorded in the form of discrete points, and also includes target position coordinates, target curvature, and target heading angle information. Due to instability and errors in the collection process, the road curvature changes suddenly, which ultimately leads to problems such as oscillation and unevenness in the generation of the target path.

[0022] To solve the above problems, the basic information data of the original path is constructed using a cubic uniform B-spline curve, and the cubic uniform B-spline curve is reconstructed through a rectification algorithm to calculate the target path information, and finally a high-precision road map is obtained. The target path information includes the target curvature , target heading angle , target position coordinates , , the ID of the target path point.

[0023] The specific steps are as follows: The original uneven road data series set is evenly divided and interpolated to make the spacing between data points equal; The interpolated data is equally divided and two control points are added to the first position to form an interpolation sequence to calculate the heading angle; Heading Angle It refers to the angle between the direction of the object's movement and the reference axis. The heading of the path here refers to the angle formed by the direction of the extension line between the middle point and the next point and the extension line between the previous point and the middle point of the three adjacent points in the path.

[0024] Parameters are usually related to spline curves in path planning. When generating a path, adjust this value to balance the smoothness of the path and the closeness of the path to the original trajectory. Smaller epsilon values ​​will result in a path that is closer to the original trajectory; larger epsilon values ​​will produce a smoother path, but may deviate from the original trajectory.

[0025] In this application, the path consists of a series of points p0, p1, p2, p3..., pn, and a curve C(u) is obtained by the cubic b-spline method; for the point pi on the path, its vertical distance to the curve C(u) is calculated, and the largest value is selected as , the calculation formula is: ,in Indicate point To the curve C(u) at the parameter The new interpolation data is constructed by third-order B-spline, and the curvature and heading angle of the position are obtained and then interpolated and smoothed.

[0026] The processed road data is vectorized and annotated. The map is described using the information of lanes and lane networks. Secondly, the destination coordinate information is mapped to the corresponding road discrete data point set, and the ID information of the road is stored.

[0027] content describe LANE_LINK Road discrete data point set LaneID Lane ID information In_node Road entry node Out_node Road exit node SnodeID Starting node id EnodeID End node id nodeID Node ID in the road Table 1 Lane network information data description In this application, an improved A* algorithm is used for path planning.

[0028] The algorithm draws on the Dijkstra algorithm and the best-first search algorithm. The core idea is to plan a path with the minimum moving cost from the starting position to the target position in a specified map.

[0029] The traditional A* algorithm and the improved A* algorithm in the literature have poor adaptability in any map. When planning a path, there are problems such as a large number of traversed nodes, a large total turning angle, an unsmooth planned path, and a long path-finding time.

[0030] In this application, first, the local cost function is changed to reduce the robot's decision-making time; then, an adaptive obstacle distribution strategy is introduced; finally, the search path is smoothed.

[0031] The evaluation function of node n in the road is: Where f(n) represents the estimated path cost from the initial point s to the target point g; g(n) represents the actual cost from s to the current node; h(n) represents the estimated cost from the current node to the g node.

[0032] When the distance between the current node and the end point is closer, in order to quickly increase the value of the evaluation function f(n), h(n) is rewritten as ln|h(n)+1|*h(n), and the decision time will be reduced accordingly. The improved f(n) is:

[0033] Secondly, consider the obstacle distribution between the starting point and the end point, and the adaptive obstacle strategy function:

[0034] The distribution of obstacles in different road environments is different. Set 1-p as the weight of the adaptive heuristic function s(n). p is the ratio of the sum of the areas of all obstacles in the map to the total area of ​​the map, and the range of p is [0,1].

[0035] The smaller p is, the fewer obstacles there are, and the larger 1-p is, the larger the evaluation function f(n) is. s(n) can quantify map information and adaptively adjust weights according to map changes, thus reducing decision time and improving decision efficiency.

[0036] The evaluation function is:

[0037] After the path planning is completed, it is necessary to determine the physical relationship between the actual position of the vehicle and the actual path. The method for searching the nearest path point of the vehicle is as follows: 1. Import the target path model, globally search the vehicle’s current position (center of mass position) in the target path, and determine the initial node S.

[0038] 2. Local search obtains the nearest node to reduce the amount of calculation. The principle is as follows Figure 4 shown.

[0039] In addition, in the present application, the various interactive systems in the human-computer interaction module are utilized to select the desired destination on the high-precision map, the current position of the vehicle is combined for global path planning, and a suitable path is selected as the vehicle's driving trajectory.

[0040] The collected road information is recorded in the form of points. The point information includes the target position coordinates, target curvature, and target heading angle. The road curvature is calculated based on the road information obtained after smoothing. It is obtained by processing the collected road data. The control module combines the vehicle speed output by the vehicle positioning module with the road curvature information of the front preview point to control the EPS (Electrical Power Steering) auxiliary steering power system and the ESP (Electronic Stability Program) vehicle braking electronic control system to achieve trajectory tracking control.

[0041] Specifically, the touch interaction system refers to a system in which people interact with the vehicle's intelligent system by touching buttons on an LCD screen and selecting points in a high-precision map integrated in the touch LCD screen system.

[0042] The voice interaction system refers to the driver (human) interacting with the vehicle intelligent system through dialogue to make control requirements or obtain control feedback.

[0043] Multimodal interaction system refers to the interaction with the vehicle intelligent system by combining gestures, eye tracking, voice and other methods. The system must integrate multiple sensing methods and be equipped with multiple sensors, such as visual sensors (cameras), voice sensors, etc.

[0044] The positioning module is mainly composed of RTK-GPS, high-precision maps, and IMU inertial navigation. It is mainly used to determine the position of the vehicle, including its posture, heading, coordinates, etc. in the world coordinates, and provide input for the control of the vehicle on the road.

[0045] RTK-GPS is a receiver that uses high-precision positioning technology based on differential GPS, which can provide centimeter-level positioning accuracy. The RTK-GPS receiver consists of a mobile device (receiver), a base station, and a data link.

[0046] IMU inertial navigation is a device that integrates accelerometers and gyroscope sensors. It can provide accurate position and attitude information and is a key technology for achieving navigation and positioning.

[0047] The control module includes a longitudinal controller and a steering angle controller. The longitudinal controller mainly controls the motor acceleration torque and deceleration braking force, while the steering angle controller mainly controls the steering gear. The control module combines the vehicle speed and the curvature of the road ahead output by the vehicle positioning module to control the EPS (Electrical Power Steering) auxiliary steering power system and the ESP (Electronic Stability Program) vehicle braking electronic control system to achieve automatic control.

[0048] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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 system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0049] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0050] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0051] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An automatic driving planning and control system suitable for regional roads, characterized in that: The automatic driving planning and control system suitable for regional roads includes a DCU controller module and a path planning module, a motion control module, a positioning module and a human-computer interaction module connected thereto; The human-computer interaction module is used to confirm the target location and the current location; The path planning module generates a plurality of path lines consisting of a plurality of series of points between the target location and the current location based on the target location and the current location; The DCU controller module confirms the shortest path among the paths and controls the motion control module to regulate the auxiliary steering power system and the vehicle braking electronic control system of the vehicle to achieve automatic control.

2. The automatic driving planning and control system applicable to regional roads according to claim 1, characterized in that: The path planning module is configured as follows: Obtain the basic information data of the original path, use the cubic uniform B-spline curve to construct the structure based on the basic information data, and reconstruct the cubic uniform B-spline curve through the rectification algorithm , calculate the target path information to obtain the road map.

3. The automatic driving planning and control system applicable to regional roads as claimed in claim 2, characterized in that: The path planning module is configured as follows: The original uneven road data sequence set is evenly divided and interpolated; The interpolated data is divided equally and two control points are added to the first position to form an interpolation sequence to calculate the heading angle. as well as ; For a point Pi on the path, calculate its distance to the curve The maximum value is taken as the vertical distance ; ,in Indicate point To the curve C(u) at the parameter The distance between the 4. The automatic driving planning and control system applicable to regional roads according to claim 3, characterized in that: The path planning module is also configured to: Use improved A* algorithm for path planning; The improved A* algorithm includes: Change the local cost function: The evaluation function of node n in the road is: Where f(n) represents the estimated path cost from the initial point s to the target point g; g(n) represents the actual cost from s to the current node; h(n) represents the estimated cost from the current node to the g node; When the distance between the current node and the end point is closer, in order to quickly increase the value of the evaluation function f(n), h(n) is rewritten as ln|h(n)+1|*h(n). The decision time will be reduced accordingly. The improved f(n) is: 。 5. The automatic driving planning and control system applicable to regional roads according to claim 4, characterized in that: The improved A* algorithm also includes: Adjust the adaptive obstacle strategy function: ; The distribution of obstacles in different road environments is different, and 1-p is set as the weight of the adaptive heuristic function s(n). p is the ratio of the sum of the areas of all obstacles in the map to the total area of ​​the map, and the range of p is [0,1]. The smaller p is, the fewer obstacles there are, and the larger 1-p is, and the larger the evaluation function f(n) is. The evaluation function is: 。 6. The automatic driving planning and control system applicable to regional roads according to claim 1, characterized in that: After the path planning module completes the path planning, the physical relationship between the actual position of the vehicle and the actual path is determined; Import the target path model, globally search the position of the vehicle's current position (center of mass position) in the target path, and determine the initial node S; Local search gets the nearest node.

7. The automatic driving planning and control system applicable to regional roads according to claim 1, characterized in that: The automatic driving planning and control system applicable to regional roads further comprises an information collection module, wherein the information collection module is used to collect road information; Road information is stored in the system in the form of points, and the point information includes target position coordinates, target curvature, and target heading angle.

8. The automatic driving planning and control system applicable to regional roads according to claim 1, characterized in that: The automatic driving planning and control system applicable to regional roads also includes a vehicle positioning module.

Citation Information

Cited By

  • Logistics vehicle path planning method and motion control system

    CN120907571A