Figures from this paperAbstractFigures from this paperAbstractFigures from this paperAbstractFigures from this paper

Abstract

Path planning is a crucial problem for unmanned underwater vehicles (UUVs) to accomplish their missions. To address the issues of slow convergence and limited search capacity in complex 3D environments, this paper introduces an Improved Grey Wolf Optimization (IGWO) algorithm. By integrating Particle Swarm Optimization (PSO) and an elite opposition-based learning strategy (EOBL), the IGWO algorithm enhances the Grey Wolf Optimization (GWO) method's update mechanism. This improvement bolsters global search capabilities while preserving GWO’s local search strengths, increases convergence speed, and enhances robustness. To assess IGWO’s effectiveness, 23 benchmark functions are used, confirming its superior performance. Finally, IGWO is applied to UUV path planning, with simulations across varied environments demonstrating its advantages over other algorithms.