Safety-Aware Path Planning for Unmanned Surface Vehicle: An Adaptive Hybrid Collision Avoidance Operation

Abstract

An adaptive performance-enhanced path planning algorithm is proposed for unmanned surface vehicle (USV) to improve their responsiveness in dynamic maritime environments. The improved ant colony (ACO) algorithm incorporates a pheromone penalty mechanism and path smoothing to enhance search efficiency and path smoothness by removing redundant nodes and reducing excessive turning. Additionally, the dynamic window approach (DWA) is enhanced through three key modifications: optimizing overshoot, enhancing selection efficiency in candidate path, and adaptively adjusting evaluation function weights. These improvements improve the accuracy of planning and avoidance ability. Comparative analysis based on simulation data indicates that the proposed method yields a measurable improvement in path quality—characterized by reduced travel length and enhanced collision avoidance—leading to more robust navigation performance in complex marine transportation scenarios.