Multi-robot path planning using improved particle swarm optimization algorithm through novel evolutionary operators

Abstract

The highlight of this paper is to propose an innovative approach to compute an optimal collision free trajectory path for each robot in a known and complex environment. The problem under consideration has been solved by employing an improved version of particle swarm optimization (IPSO) with evolutionary operators (EOPs). In the present context, PSO is improved with the concept of governance in human society and two evolutionary operators such as multi-crossover inherited from the genetic algorithm, and bee colony operator to enhance the intensification capability of the IPSO algorithm. The algorithm proposed to compute the deadlock free subsequent coordinate of an individual robot from their present coordinate, in addition, to minimize the path length for each robot by maintaining a good balance between intensification and diversification. Results obtained from the proposed IPSO-EOPs have been compared with competitors such as DE and IPSO in a similar environment to substantiate the robustness and usefulness of the algorithm. It perceives from the result obtained from simulation and experimentation that IPSO-EOPs is succeeding IPSO, and DE in terms of arrival time, generating a safe optimal path, and energy utilization during the travel.