Physical Consistent Path Planning for Unmanned Surface Vehicles under Complex Marine Environment

Abstract

The increasing demand for safe and efficient maritime transportation has underscored the necessity of developing effective path-planning algorithms for Unmanned Surface Vehicles (USVs). However, the inherent complexities of the ocean environment and the non-holonomic properties of the physical system have posed significant challenges to designing feasible paths for USVs. To address these issues, a novel path planning framework is elaborately designed, which consists of an optimization model, a meta-heuristic solver, and a Clothoid-based path connector. First, by encapsulating the intricate nature of the ocean environment and ship dynamics, a multi-objective path planning problem is designed, providing a comprehensive and in-depth portrayal of the underlying mechanism. By integrating the principles of the candidate set random testing initialization and adaptive probability set, an enhanced genetic algorithm is devised to fully exploit the underlying optimization problem in constrained space, contributing to the global searching ability. Accounting for the non-holonomic constraints, the fast-discrete Clothoid curve is capable of maintaining and improving the continuity of the path curve, thereby promoting strong coordination between the planning and control modules. A thorough series of simulations and comparisons conducted in diverse ocean scenarios has conclusively demonstrated the effectiveness and superiority of the proposed path planning framework.