Path planning of underwater swarm robots using genetic algorithm

Abstract

Path planning is one of the most exciting challenges in building autonomous swarm robots. It consists on finding a route from the origin of the robot to its target destination. It becomes more difficult when some obstacles are added to the environment. This paper consists of multiple obstacles: the robots and their possible path. This paper will present the path planning of underwater swarm robot based on genetic algorithm. Swarm robots will determine the position of pre-defined object and genetic algorithm generates shortest path for each robot to reach the object without collision to one another. The xyz coordinates of possible path of robot are randomly generated and they are encoded into chromosome and their fitness is defined by the summation of their displacement using Euclidian distance formula for 3-dimensional plane. The simulation results demonstrated that proposed algorithm is able to plan safe collision free paths for swarm robots. It also shown that using more population, the optimum path will be obtained. The implementation of genetic algorithm is done using computer simulation and explains the process in section two of this paper.