Path Planning for Mobile Robots in Dynamic Environments Using Particle Swarm Optimization

This paper presents a particle swarm optimization (PSO) planner that is able to swiftly determine optimal solution for mobile robot path planning problems in dynamic environments. Obstacles of different shapes (convex, concave and curved) with varying velocities are considered. The method uses only valid particles (feasible paths form start to target without interfering obstacles) in the population, obviating the need to search the invalid particles and hence penalty function evaluation design, as in earlier evolutionary approaches. The generated valid paths are subjected to PSO algorithm to get global optimal paths. The proposed algorithm also gives the velocity of the robot for each path segment depending upon the path length and or travel time optimization. The effectiveness and efficiency of the proposed algorithm is demonstrated by simulation studies.