Mobile robot path planning method based on weighted average distance vision fish school algorithm

Abstract

The invention provides a mobile robot path planning method based on a weighted average distance vision fish school algorithm. The method comprises the steps that the population size fishnum of artificial fish, the maximum number of iterations NC, field of view visual, the largest moving step step, a crowding factor delta, the number of attempts Try_number, the number feasibility paths N and the number of path nodes n are acquired; environment modeling is carried out on the walking environment of a robot based on a grid method; and N feasibility paths are randomly generated. According to the invention, for the problems of fixed field of view, slow algorithm convergence and increased computation of a basic artificial fish school algorithm, WAD-AFSA is provided; the algorithm is applied to the path planning of the mobile robot; environment modeling is carried out through the grid method; provided WAD-AFSA and an act selection policy are used to carry out path optimization, which prevents the paths from falling into local optimum; and a corresponding simulation experiment shows that WAD-AFSA provided by the invention has a better optimization effect than the traditional artificial fish school algorithm in the aspect of mobile robot path planning.

Description

technical field [0001] The invention relates to the technical field of path planning methods, in particular to a path planning method for a mobile robot based on a weighted average distance visual fish swarm algorithm. Background technique [0002] Path planning for mobile robots is one of the hot research issues now. The path planning of mobile robot is the collision-free optimal path from the starting position to the ending position according to a certain search rule in the environment with obstacles. [0003] Robot path planning can be divided into two types: one is such as artificial potential field method, Voronoi diagram method and visualization method. The artificial potential field method has a simple structure, but there is a problem that it is easy to fall into a local optimal solution; the visual graph method can obtain the shortest path but its search efficiency is low; the Voronoi graph method has higher security but the path from the starting node to the targe...

AI Technical Summary

Problems solved by technology

Genetic algorithm applies genetic operators to the research of robots, which has a good effect on the path planning of robots, but it occupies a large storage space and has poor local optimization ability

The bee colony algorithm is fast and easy to implement, but it is easy to fall into local optimum and low search efficiency.

The disadvantage of the leapfrog algorithm is that it is easy to converge to a local optimal solution and the solution accuracy is low

The advantage of the particle swarm optimization algorithm is that it is simple and easy to implement, but it has the disadvantage of being prone to premature convergence and falling into local optimum.

Images