Path planning system and path planning method

Abstract

The invention relates to a path planning system and a path planning method, belonging to the technical field of robot navigation. The path planning system includes at least two levels of planners, and the planning scope of each level of planners is different; the first level of planners is responsible for planning from a starting point to an end point; The remaining levels of planners are responsible for planning from the starting point to their respective planning ranges. The planning accuracy and planning frequency of the planners are inversely proportional to the planning range. In this path planning method, the paths planned by each level of planners are taken, and the planning of adjacent two-level planners The path difference is set to obtain the segmented path; the final path is obtained by the union of the segmented path and the planned path of the planner of the highest level. According to the actual needs of robot navigation, the invention reduces unnecessary consumption of long-distance planning of the robot, not only can obtain an effective and stable path, but also enhance the response ability of the robot in navigation, enhance the real-time performance of robot navigation, and improve the understanding of real-time obstacles. Response speed, and can reduce the waste of resources in planning.

Description

technical field [0001] The invention relates to the technical field of robot navigation, in particular to a path planning system and a path planning method. Background technique [0002] The existing path planning algorithms mainly include: Dijkstra algorithm, A* algorithm, D* path search algorithm, PRM, RRT path planning algorithm and artificial potential field method. [0003] Dijkstra's algorithm is an earlier path planning algorithm and a classic breadth-first state space search algorithm, that is, the algorithm searches the entire free space layer by layer from the initial point until it reaches the target point. Dijkstra's algorithm will make a lot of useless calculations in the planning process. [0004] The A* algorithm adds heuristics on the basis of Dijkstra, reducing a lot of unnecessary searches. The A* algorithm has been widely used in mobile robot navigation. Although A* effectively reduces the unnecessary search amount in the planning process, it still does...

AI Technical Summary

Problems solved by technology

In some cases, the artificial potential field method will fall into the local minimum trap, resulting in the inability to complete the planning task and not being stable enough

[0009] Existing path planning algorithms have a common defect: they do not distinguish the scope of planning when planning, and plan with the same accuracy, resulting in unnecessary calculations and reducing the frequency of planning

It is not suitable for large-scale planning, or in scenes with large calculations such as three-dimensional space

Images