Vehicle path planning method based on storage unmanned vehicle

A vehicle path and local path planning technology, applied in vehicle position/route/height control, motor vehicles, two-dimensional position/channel control, etc., can solve the problem of inability to solve optimization and obstacle avoidance at the same time, difficult positioning, flexible Poor performance and other problems, achieve the effect of short running distance, optimize topology nodes, and improve work efficiency

Inactive Publication Date: 2017-08-11
NANJING UNIV OF SCI & TECH
0 Cites 57 Cited by

AI-Extracted Technical Summary

Problems solved by technology

However, such methods usually have a large amount of calculation and high positioning difficulty, and the single use of global path plannin...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Method used

The present invention combines global path planning with local path planning, can carry out local obstacle avoidance while searching for optimal path, makes the oper...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Abstract

The invention discloses a vehicle path planning method based on a storage unmanned vehicle. The method comprises steps of firstly determining the operation node of an unmanned vehicle in a storage environment, and making a topological map based on the environment; then through the improvement of the traditional A* algorithm, calculating the shortest path from a starting point to a target point of the unmanned vehicle in an offline way; in the process of tracking the path of the unmanned vehicle, detecting whether there are obstacles on the path by a self-brought sensor, if there are obstacles and the obstacles do not completely obstruct the path, then switching to the artificial potential field method to perform online real-time obstacle avoidance; and if the obstacles completely obstruct the path, switching to the A* algorithm to replan the path until the unmanned vehicle reaches the target point. This method not only can make full use of known information to generate the global optimal path, but also can effectively avoid the random moving obstacle on the path.

Application Domain

Technology Topic

Potential fieldObstacle avoidance +5

Image

  • Vehicle path planning method based on storage unmanned vehicle
  • Vehicle path planning method based on storage unmanned vehicle
  • Vehicle path planning method based on storage unmanned vehicle

Examples

  • Experimental program(1)

Example Embodiment

[0057] Example
[0058] Combine figure 1 , The present invention is based on the vehicle path planning method of unmanned storage vehicles, and the specific implementation steps are as follows:
[0059] Step 1. Make a topological map of the storage environment, such as figure 2 Shown is a schematic map of the storage environment. The rectangles in the figure represent shelves. Collect the relative positions of the unmanned vehicles' feasible paths and the shelves in the storage environment. According to the collected information, set the nodes that the unmanned vehicles can reach, and then create a base based on the node information. The adjacency matrix of the topological map;
[0060] Step 1-1, such as image 3 As shown, the environmental map information is collected, and each intersection in the environmental map and the point where the unmanned vehicle needs to stop is used as a topological node, and the road connected to the topological node is used as a topological edge. Therefore, the environmental map can be abstracted as a topology A topological map composed of nodes and topological edges. The topological map can be represented by symbols as G=(V, E), where V is a set of nodes and E is a set of edges connecting nodes. In this storage environment, you can set as image 3 A total of 15 topological nodes from A to O are shown, namely the matrix
[0061] V=[0.5,0.5; 2.5,0.5; 4.5,0.5; 0.5,2.5; 2.5,2.5; 4.5,2.5; 5.5,2.5; 0.5,4.5; 2.5,4.5; 4.5,4.5; 5.5,4.5; 0.5,6.5 ; 2.5,6.5; 4.5,6.5; 5.5,0.5];
[0062] Step 1-2, in order to facilitate the preservation and search of the topological graph, the adjacency matrix is ​​used to represent the relationship between the nodes. If there are n topological nodes in the topological map v 1 , V 2 ,..., v n , The adjacency matrix is ​​an n×n matrix, and the attributes of each edge are assigned to distinguish the passable path and the impassable path. Here, the weight attribute of the passable path is set to 1, and the weight of the impassable path The attribute is set to 0. Furthermore, the (i, j)th element in the adjacency matrix can be expressed as
[0063]
[0064] In the topological map n=15, the adjacency matrix is ​​a 15×15 matrix, expressed as
[0065]
[0066] Step 2. Perform global path planning offline, that is, use the improved A* algorithm to calculate the optimal path from the starting point to the target point in an offline manner, such as Figure 4 Shown is the flow chart of global path planning;
[0067] Step 2-1. Using the A* algorithm, design an evaluation function for each road node, as shown in the following formula:
[0068] f(s)=g(s)+h(s)
[0069] In the formula, f(s) represents the estimated length from the start node to the target node through node s, g(s) represents the path length from the start node to the current node, h(s) is the heuristic function, which is the current node to Estimated value of the target node;
[0070] Step 2-1-1, record the path length from the starting node to the current node and design it as g(s);
[0071] Step 2-1-2, h(s) is the heuristic function, which is the estimated value from the current node to the target node. A* algorithm must be able to search for the preconditions of the optimal path:
[0072] h(s)≤cost*(s,s goal )
[0073] Where cost*(s,s goal ) Is the optimal distance from the current node to the target node. The larger the h(s) value that satisfies the above formula, the fewer the expansion nodes. In order to ensure the optimality of the search path, this method uses Euclidean distance as the heuristic function. For the given two position coordinates (x i , Y i ) And (x j , Y j ), their Euclidean distance d e As shown in the following formula:
[0074]
[0075] Step 2-2. Create two sets OPEN and CLOSED to manage road nodes. OPEN stores the child nodes of the expanded road node. They belong to the nodes to be expanded. CLOSED stores the expanded node;
[0076] Step 2-3: Start global path planning, and select the node s with the smallest value of f(s) from OPEN to expand each time. The child node to which node s is expanded is stored in OPEN. After node s is expanded, it moves from OPEN to CLOSED. Repeat the above process until it extends to the target node or when OPEN is empty, terminate the algorithm and record the planned path. Such as Figure 5 Shown is the result of global path planning.
[0077] Step 3. Path tracking, that is, the unmanned vehicle locates the unmanned vehicle relative to the storage environment through its own tracking module and pre-set markers in the storage environment, so as to realize the tracking of the planned global path. Such as Image 6 As shown by the medium thick solid line, direct tracking is performed on the road section without obstacles, which reduces the positioning cost.
[0078] Step 4. Detect and collect random obstacle information, judge the path environment, and switch between the two algorithms of global path planning and local path planning;
[0079] Step 4-1. The unmanned vehicle detects random obstacles on the path in real time through its own ultrasonic module, and generates information such as obstacle boundaries and relative positions;
[0080] Step 4-2. Judge the road environment based on the obstacle information collected by the sensor, and switch between global road strength planning and local path planning algorithms according to the judgment results;
[0081] Step 4-3. Design the safety distance between the unmanned vehicle and the obstacle. The storage model sets the safety distance to 0.3 units. If the distance between the boundary of the obstacle and the wall is less than the safety distance, it is considered that the unmanned vehicle cannot pass. Such as Figure 7 As shown, the topological node where the current unmanned vehicle is located is the starting point, and the topological edge between the topological node and the next node is set as impassable, the adjacency matrix is ​​updated, and the adjacency matrix is ​​updated to:
[0082]
[0083] Go back to step 2 to re-plan the global path. The re-planned path is as follows Figure 7 Shown by the thick solid line;
[0084] Step 4-4, such as Image 6 As shown, if the distance between the boundary of the obstacle and the wall is greater than the safe distance designed in step 4-3, the local path planning algorithm is switched to avoid obstacles.
[0085] Step 5. Avoid random obstacles, that is, use the artificial potential field method to perform online local path planning to achieve the purpose of local obstacle avoidance. The effect is as follows Image 6 As shown, the artificial potential field method is switched to local obstacle avoidance in the road section with obstacles.
[0086] Step 5-1. Establish the starting point and ending point of the local path planning. This method uses the current node of the unmanned vehicle as the starting point and the next node end point of the node in the global path planning. In the storage model, it is L Point and M point are the start and end points of local path planning;
[0087] Step 5-2. Determine the scope of the obstacle according to the size of the unmanned vehicle;
[0088] Step 5-3. Establish the gravitational potential field function and the repulsive potential field function of the artificial potential field method, and switch to the A* algorithm for local obstacle avoidance;
[0089] Step 5-3-1. Establish the gravitational potential field function, the formula is as follows:
[0090]
[0091] Where: K a Is the gravitational potential field constant, Q c Is the position vector of the unmanned vehicle earth coordinate system, Q g Is the position vector of the target point in the earth coordinate system. In this method, the gravitational potential field constant is set to 1, (Q c -Q g ) 2 Is the Euclidean distance between the unmanned vehicle and the target point, updated at any time with the movement of the unmanned vehicle, the final gravitational potential field function is
[0092]
[0093] Step 5-3-2, establish the repulsion potential field function, the formula is as follows:
[0094]
[0095] Where: K r Is the repulsive potential field constant, ρ(Q c ,Q obs ) Is the relative distance between the unmanned vehicle and the obstacle, and D is the safe distance. In this method, the repulsive force field constant is set to 1, ρ(Q c ,Q obs ) With the real-time update of the motion of the unmanned vehicle, D is set to 0.3, then the repulsion potential field function is
[0096]
[0097] The present invention combines global path planning with local path planning, and can perform local obstacle avoidance while searching for the optimal path, making the operation of unmanned vehicles more flexible, shorter running distance when encountering obstacles, and improving storage The work efficiency of people and vehicles.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Similar technology patents

Video image target tracking processing method and system

ActiveCN103489199AGood video object tracking processing performanceSmall amount of calculationImage analysisAdaptive capacityHistogram
Owner:CRSC COMM & INFORMATION GRP CO LTD

Classification and recommendation of technical efficacy words

Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products