MOTION PLANNING OF SWARM ROBOTS USING POTENTIAL-BASED GENETIC ALGORITHM

A potential-based genetic algorithm is proposed for the motion planning of robot swarms. The proposed algorithm consists of a global path planner and a motion planner. The global path planning algorithm plans a trajectory, which the robot swarm should follow, within a Voronoi diagram of the free space. The motion planning algorithm is a genetic algorithm based on artificial potential models. The potential functions are used to keep robots away from obstacles and to keep the robot swarm within a certain distance from each other. Since the proposed approach is a hierarchical algorithm which plans the global path and local motion individually, the robot swarm moves toward the goal by sequentially traversing a sequence of positions along the Voronoi diagram. Therefore, the robot swarm can avoid becoming trapped in local minima.