Application of improved ant colony algorithm based on unevenly distributed pheromone and multi-objective optimization in unmanned vessel path planning

Objective Aiming at the difficulty of path planning for unmanned boats in complex waters, this paper proposes an improved ant colony algorithm based on uneven allocation of pheromone and multi-objective optimization. Methods Firstly, a probabilistic roadmap method is used to obtain an initial path, and based on the orientation information of the path and the end point, the ant colony algorithm is guided to unevenly distribute the initial pheromone, which improves the problem of the ants' blindness in the preliminary path search; secondly, an objective function is set up for solving the multi-objective path planning problem, and the weights are set up to balance the relationship between the safety index, the energy consumption, and the path curvature, and to adaptively adjust the increment of pheromone with the merits of the paths. Secondly, the objective function for solving the multi-objective path planning problem is established, and the weights are set to balance the relationship between safety index, energy consumption and path curvature, and the pheromone increment is adaptively adjusted according to the merit of the paths to strengthen the influence of the high-quality paths in the whole colony. Finally, the path is optimized twice to obtain the global optimal path. Results The experiments are based on two real lakes, Huangshi Xiangdao Lake and Hangzhou Qiandao Lake, which are among the “Three Thousand Island Lakes in the World”, and compared with the traditional ACO algorithm, A* algorithm, and improved ACO algorithm: this algorithm has the shortest planning paths, which is 61.71% shorter than that of the traditional ACO algorithm, the farthest distance from obstacles, and the smallest path zigzagging degree. The running time of the algorithm is also improved. Conclusion The experimental results show that the present algorithm can reduce the energy consumption of unmanned ship navigation, reduce the number of turns and turning amplitude, improve the smoothness and safety of the path, and have certain application significance to the autonomous navigation of green intelligent ships.