Autonomous mobile robot path planning using hybridization of particle swarm optimization and Tabu search

Designing path planning algorithms for robots in Robotics extensively used meta-heuristic algorithms like genetic algorithm, ant colony algorithm, gravitational search, simulated annealing etc in past. But these algorithms were not adaptive and were not efficient in complex situations. This paper proposes a hybridized method for multi-robot path planning in a cluttered environment. Here we have used the hybridization of Particle swarm Optimization (PSO) with Tabu Search (TABU). This new approach of PSO-TABU finds out an optimized path and also explores the search area for the solution. PSO has been proved to be a useful technique in robot path planning in dynamic environment where multiple mobile obstacles are present. Tabu Search is a neighborhood look strategy which begins from an underlying arrangement. It uses greedy algorithm and then iteratively improves the current solution around an appropriately defined neighborhood. The Objective of this paper is to optimize the path length so that all the robots can arrive at their destination in minimum number of steps taking minimum time. By using PSO-TABU hybridization algorithm we calculate the best solution after each iteration of PSO and after that we search for the best neighbourhood position using Tabu Search. Finally simulation is done and results are compared between PSO, TS and hybrid PSO-TABU. The result shows that the hybrid PSO-TABU is efficient than the PSO and TABU in terms of optimized path length.