Path planning of mobile robot based on improved genetic algorithm

Abstract

In view of the shortcomings of the previous genetic algorithm in solving the problem of path planning of robot, this paper has improved it on the basis of the traditional genetic algorithm. The environment model is built by the grids and the fixed length serial number coding is used to encode. The random search method and the ascending order method are combined to generate the initial population. The preferred operator is introduced into the selection operator and this paper proposes a new adaptive adjustment formula which can automatically adjust the cross probability and the mutation probability on the basis of adaptive function value, which purpose is to avoid premature convergence. We use MATLAB to do simulation experiments. The result shows that this method make the path planning of robot more rapid and effective.