A Motion Planning of Swarm Robots Using Genetic Algorithm

Abstract

In this paper, a potential-based genetic algorithm is proposed for formation control of robot swarm. The proposed algorithm consists of a global path planner and a motion planner. The global path planning algorithm searches a path, which the center of robot swarm should follow, within a Voronoi diagram of the free space. The motion planning is a genetic algorithm based on artificial potential models. The potential functions are used as a repulsion to keep robots away from obstacles and as an attraction/repulsion to keep robot swarm within a certain distance. With Voronoi diagram and potential models, the algorithm plans safe paths efficiently and the formation of robot swarm is also maintained.