Collision-free optimal paths for multiple robot systems using a new dynamic distributed particle swarm optimization algorithm

Abstract

One of the main areas of artificial intelligence is the field of robotics, where Multiple Robot Systems (MRS) are one of the most advanced artificial intelligence resolutions to the problems faced by humans. However, the control of the MRS becomes unreliable and even infeasible if the number of robots augments. This paper tries to find a solution for the problem of multi robots path planning considering the collision risks. A new Dynamic Distributed Particle Swarm Optimization (D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> PSO) algorithm is proposed. It consists in calculating two Local Optima Detectors. We apply a restriction rule for particles that are not contributing in optimization process and so causing a stagnation issue. Experiments of the strategy on the motion and evaluation of the results will be presented to prove the efficacy of such approach.