A comparative study of meta-heuristics for local path planning of a mobile robot

Recent trends in path planning have led to a proliferation of studies that find solutions to the path planning problems in an unknown cluster environment. This study aims to find an optimum impact-free path length for a mobile robot with a multi-objective optimization approach. The multi-objective optimization problem is formulated by using path length and a safety aspect as the two objectives. A hybrid population-based optimization algorithm, i.e. the hybrid particle swarm and chemical reaction optimization (HPCRO) algorithm, has been used to obtain a smooth path for the robot in an unknown environment with circular and/or polygonal obstacles. The results of the HPCRO algorithm are then compared with those of genetic algorithms, chemical reaction optimization and particle swarm optimization. Some statistical tests are performed to illustrate the superiority and potential applicability of the hybrid algorithm. The results of the hybrid algorithm are encouraging in terms of cost function value and computational cost.