Genetic algorithm based global path planning in a static environment.

Abstract

Mobile robot global path planning in a static environment has been an important problem all along. The paper proposes a method of global path planning based on genetic algorithm. The neural network model of environmental information in the workspace for robot is constructed. The relationship between a collision-free path and the output of the model is established based on this model and the two-dimensional coding for the via-points of path is converted to one-dimensional one. Then the fitness of the collision-free path and that of a shortest distance are fused to a fitness function. The simulation results show that the proposed method is correct and effective.