Abstract:

A path planning approach based on a modified particle swarm optimization (PSO) is presented for mobile robot in known static environments. To avoid premature convergence and to update candidate solutions more efficiently in the multidimensional search space, the best position of particle’s neighborhood is substituted for the individual optimized in the velocity relation of the algorithm. In addition, the requirements for boundary constraint, obstacle avoidance and shortest path are expressed as a simple fitness function to make the optimum solution fulfill the qualifications for path planning. Simulation results show that the proposed approach is feasible and effective.

Key words: mobile robot, path planning, particle swarm optimization