An enhanced heuristic ant colony optimization for mobile robot path planning

To realize a fast and efficient path planning for mobile robot in complex environment, an enhanced heuristic ant colony optimization (EH-ACO) algorithm is proposed. Four strategies are introduced to accelerate the ACO algorithm and optimize the final path. Firstly, the heuristic distance in the local visibility formula is improved by considering the heuristic distance from ant’s neighbor points to target. Secondly, a new pheromone diffusion gradient formula is designed, which emphasizes that pheromones left the path would spread into a region and the pheromone density would present a gradient distribution in the region. Thirdly, backtracking strategy is introduced to enable ants to find new path when their search is blocked. Finally, path merging strategy is designed to further obtain an optimal path. Simulations are carried out to verify each individual strategy, and comparisons are made with the state-of-the-art algorithms. The results show our proposed EH-ACO algorithm outperforms other algorithms in both optimality and efficiency, especially when the map is large and complex.