USING GENETIC ALGORITHMS FOR MOBILE ROBOT PATH PLANNING

In this paper, we deal with mobile robot path planning in two-dimensional continuous space in which known fined. The aim of the path planning is finding a path from a start to a goal position static polygonal obstacles are de without collisions with known obstacles minimizing an evaluation function. We investigate the possibilities of using genetic algorithms for solving this problem and describe various problem-specific genetic operators and fitness functions. We study also the ability of the proposed algorithm to adapt a previous solution to changes of start and/or goal positions and changes in the environment. Results of computational experiments are presented.