Cooperative path planning for multiple autonomous underwater vehicles using hybrid metaheuristic optimization

Path planning for collaborative multi-autonomous underwater vehicle navigation in intricate underwater environments continues to be a significant challenge due to the shortcomings of conventional techniques in high-dimensional multi-agent contexts. This paper introduces the Ant Colony A* Fusion Algorithm, a dual-level hybrid path planning approach that merges Ant Colony Optimization with the A* heuristic search tailored for autonomous underwater vehicles. At the upper tier, Ant Colony Optimization’s pheromone-driven mechanism facilitates global exploration by enhancing promising pathways, while at the lower tier, A*’s heuristic direction fine-tunes local path selection toward optimal waypoints. Adaptive parameter management flexibly balances exploration and exploitation, and a priority-based conflict resolution framework allows for real-time coordination among multiple autonomous underwater vehicles. Lyapunov stability theory ensures convergence, while the system concurrently enhances collision avoidance, path smoothness, minimal length, and energy efficiency. Simulation outcomes validate that Ant Colony A* Fusion Algorithm consistently surpasses traditional algorithms, showcasing its superior effectiveness and stability for cooperative multi-autonomous underwater vehicle navigation in challenging underwater landscapes.