Mobile robot safe path planning method based on Delaunay triangle
A mobile robot, safe path technology, applied in the field of mobile robot safe path planning based on Delaunay triangle, can solve problems such as difficult application, long time, and inability to obtain feasible paths, and achieves the effect of improving efficiency and reducing the number of nodes
Active Publication Date: 2021-06-18
TONGJI UNIV
View PDF7 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Search-based path planning method: For example, use A* algorithm, Dijkstra algorithm, etc. for path search, use each pixel point of the cost map as a node, start from a certain node to traverse the neighborhood to find the next node, and then find the path from the starting point to the end point The path can ensure that any point is reachable, and the search efficiency is high. This type of method can generally search for the shortest or close to the shortest global path. However, this method will choose to be close to the obstacle boundary when encountering obstacles during the path search process. Circumvention, the path obtained in this case is close to the boundary of the obstacle, which is neither the optimal path nor close to the optimal path, and controlling the robot to move along the boundary of the obstacle puts forward higher requirements for the motion control method of the robot. The path obtained by the method is not safe
[0004] Probability-based path planning methods: For example, path planning based on rapid search random tree algorithm (RRT), probabilistic roadmap algorithm (PRM), etc., inevitably use random operations, or random walks or initialize random points, based on random Usually, the discrete points will not be close to the obstacle boundary, and the obtained path is safer than the search path planning method, but the search efficiency of this type of method is inconsistent with the reachability of any point. If any point is reachable, the search time will be reduced. It is difficult to ensure that any point is reachable to ensure search efficiency, and the path searched by this method is not stable, and the obtained path changes with the number of searches
[0005] Path planning method based on intelligence: such as path planning based on ant colony algorithm, fish swarm algorithm, genetic algorithm, neural network, etc., mainly imitating the habits of natural creatures to establish search algorithms; heuristic methods often cannot get the current position of the mobile robot to the target position This type of method is more intelligent than the previous two methods, but its search efficiency is generally lower than other methods, it takes a long time and in many cases it is impossible to obtain the optimal path from the starting point to the end point or even a feasible path, and There are problems such as difficulty in convergence and oscillation, and it is difficult to apply to practice
Method used
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0060] Such as figure 1 Shown, the present invention relates to a kind of mobile robot safe path planning method based on Delaunay triangle, the method comprises the steps:
[0061] Step 1. Read the global cost map of the established working environment, and extract the outline of the feasible region of the global cost map based on the Canny operator.
[0062] The cost map of the working environment is a cost map (costmap) obtained by expanding the two-dimensional map of the working environment obtained through other mapping algorithms (such as the cartographer mapping algorithm, etc.). During binary segmentation, the area covered by the expansion process is considered as the obstacle area, and the contour extraction is performed taking the feasible area as the consideration area instead of the obstacle, so as to ensure that the initial points obtained by subsequent calculations are all distributed in the feasible area. The outline of the feasible region of the global cost ma...
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
Login to View More Abstract
The invention relates to a mobile robot safe path planning method based on a Delaunay triangle, which comprises the following steps of: extracting a contour of a feasible region of a global cost map of a working environment, sliding a window in the map according to a set window size and step length, and calculating a fractal dimension of a window coverage area; obtaining position distribution of initial points in each window according to the fractal dimension; constructing a Delaunay triangular network by taking the initial points in all the windows as vertexes; traversing the triangular network, calculating the gravity center of each triangle, and constructing a Delaunay triangular network again by taking the gravity centers of all triangles as vertexes; traversing the newly generated triangular network, removing vertexes in the obstacle and edges passing through the obstacle, and forming a path network by the remaining vertexes, the remaining edges and the connection relation of the remaining vertexes and the remaining edges; searching a path from the starting point to the ending point in the path network; gradually shrinking the paths until the paths before and after shrinking are the same, and obtaining an optimal path. The path planned by the method is safe and reliable, and the efficiency of path searching and pruning is greatly improved.
Description
technical field [0001] The invention relates to the technical field of path planning for mobile robots, in particular to a safe path planning method for mobile robots based on Delaunay triangles. Background technique [0002] Path planning is the basis of mobile robot movement, and it is a necessary part to ensure the correct and safe movement of mobile robot between different target points. How to quickly obtain the optimal path from the current position of the mobile robot to the target position based on the global cost is a research hotspot in the field of mobile robots. The current path planning methods can be mainly divided into: [0003] Search-based path planning method: For example, use A* algorithm, Dijkstra algorithm, etc. for path search, use each pixel point of the cost map as a node, start from a certain node to traverse the neighborhood to find the next node, and then find the path from the starting point to the end point The path can ensure that any point is...
Claims
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 Application Information
Patent Timeline
Login to View More IPC IPC(8): G05D1/02
CPCG05D1/0231G05D1/0214G05D1/0221G05D1/0276
Inventor陈启军刘志浩李树刘成菊
OwnerTONGJI UNIV