Robot walking path planning method based on genetic algorithm and artificial potential field method

Abstract

The invention relates to a robot walking path planning method based on a genetic algorithm and an artificial potential field method. The method, an optimized path being obtained by combining a Maklinkgraph and an artificial potential field method, and selecting nodes on the link line, obtaining a shortest path from a starting point to an end point through a Dijkstra algorithm to serve as a pre-planned path of the artificial potential field method, and sequentially taking each intermediate node in the path as a target gravitation traction point of the artificial potential field method. A genetic algorithm is used for iterative optimization, finally, a smooth and high-safety shortest path can be obtained in a target region containing a concave polygon, a limitation problem of an artificialpotential field method can be solved, falling into an extreme point is avoided, and an oscillation point is eliminated.

Description

Technical field [0001] The invention relates to a robot walking path planning method based on genetic algorithm and artificial potential field method. Background technique [0002] With the improvement of the automation level of the power system, the number of substations is increasing, and the inspection workload is increasing. The traditional inspection method is generally manual inspection, and inspection personnel are usually required to regularly inspect the substation or power distribution room. Such inspection methods are not only arduous and inefficient, but also the staff are also faced with the complex environment and the harm caused by electromagnetic radiation. At the same time, in bad weather, the condition of substation equipment cannot be inspected in time, and it is difficult to meet the quality of power supply. Increasing requirements. In this case, the role of the intelligent substation inspection robot is particularly important, and path planning is one of th...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a robot walking path planning method based on genetic algorithm and artificial potential field method, combine the Maklink graph and artificial potential field method to obtain the optimized path, and then use genetic algorithm to iteratively optimize, finally can be in the concave polygon A smooth and safe shortest path can be obtained in the working area of ​​the substation, which can solve the limitations of the artificial potential field method itself, avoid falling into extreme points and eliminate oscillation points

Images