Abstract:

 Aimed at the path planning problem of a mobile robot, a novel fixed-length real number encoding mechanism was proposed. The first step was to make a new map between starting-point and goal-point through coordinate system transferring. Then the encoding mechanism was introduced to search for an optimized path in which the robot gets close to the target. Then a valid region for the robot was mapped out according to the location of obstacles, which could reduce the search space and further improve the efficiency. An immune simulated annealing algorithm by combining an immune optimization algorithm with simulated annealing algorithm was developed. The simulation result demonstrated that the proposed algorithm had strong global and local search ability, which could help  the robot to quickly find the optimized path.

Key words: mobile robot, path planning, valid region, fixed-length real number encoding