Study of Evolutionary and Swarm Intelligent Techniques for Soccer Robot Path Planning

Finding an optimal path for a robot in a soccer field involves different parameters such as the positions of the robot, positions of the obstacles, etc. Due to simplicity and smoothness of Ferguson Spline, it has been employed for path planning between arbitrary points on the field in many research teams. In order to optimize the parameters of Ferguson Spline some evolutionary or intelligent algorithms are proposed in the literature. In this paper, we present a comparative study on different evolutionary and swarm algorithms as solutions to the problem of robot path planning. We optimize the parameters of Ferguson Spline and find the best path between two arbitrary points, studying Differential Evaluation (DE), Genetic Algorithm (GA), Evolutionary Strategies (ES), Artificial Bee Colony (ABC), and Particle Swarm optimization (PSO) algorithms. Firstly, a path for robot movement is describe by Ferguson splines and then these algorithms are used to optimize the parameters of splines to find an optimal path between the starting and the goal point considering the obstacles between them. The experimental results show the performance and effectiveness of the studied solutions in comparison with other swarm intelligent algorithms.