Rapid path planning method and enhancement method for random route map

Abstract

The invention relates to the field of motion planning and provides a rapid path planning method and an enhancement method for a random route map. The planning method comprises the following steps of: randomly generating free nodes in a planning space region; processing a difficult region by adopting the enhancement method; generating a route map according to the preset strategy; and querying an optimized path according to motion planning requirement. The invention has the advantages of a general PRM method, the complexity of implementing the method is basically unrelated to the complexity of the whole planning environment and the dimensionality of planning control, the problem that the general PRM method completely and uniformly distributes the free nodes with equal probability to cause insufficient number of the distributed free nodes in the difficult region is solved, the enhancement method is adopted for performing related processing on the difficult region so as to increase the number of the free nodes in the difficult region, the completeness is higher, and the probability of omitting some feasible paths in the difficult region is reduced.

Description

technical field [0001] The invention relates to the field of motion planning, in particular to a fast path planning method and an enhancement method of a random roadmap. Background technique [0002] Path planning is an important branch in the field of motion planning. The general path planning method is obviously insufficient in dealing with complex environments, and is easily affected by the dimension of the environment space, the complexity of the actual environment, and the amount of information to be processed. If it is necessary to deal with motion planning in complex environments, such as the realization of the optimal route in unmanned aircraft navigation, it often requires the support of supercomputers, which have high requirements for computer computing speed. [0003] In recent years, some excellent motion planning methods have been proposed one after another. Today, the completeness of various methods is still to be discussed, but its operability and practicalit...

AI Technical Summary

Problems solved by technology

Since the general PRM method is to generate free nodes uniformly with equal probability, it is easy to make the number of random free nodes generated in area A insufficient, resulting in the incompleteness of the road map; and the distribution of free nodes in area B is not ideal, resulting in some feasible paths omission

In short, with the general PRM method, the number of free nodes in the difficult area in the planning space is not distributed enough, and the feasible path through the difficult area cannot be searched well, and some feasible paths are easily missed, which leads to pathfinding failure and other problems.

Images