Dynamic path planning for unmanned surface vessels based on an Improved Genetic Algorithm and proportional navigation

To address the problem of autonomous path planning for unmanned surface vessels（ USVs） in complex navigational environments, a hybrid path-planning method integrating an Improved Genetic Algorithm（ IGA） with Proportional Navigation（ PN） is proposed. First,the improved IGA is utilized to perform global path optimization,and a bidirectional Floyd smoothing strategy is incorporated to generate more reasonable and navigable routes. Subsequently,a geometric collision-domain model is introduced,and the PN algorithm is extended to dynamic collision avoidance scenarios,enabling the USV to avoid moving obstacles in real time while maintaining adherence to the globally optimal path.Simulation results demonstrate that the proposed method outperforms the conventional A^*-Artificial Potential Field（ APF）approach in terms of path length and trajectory smoothness. Moreover,the method exhibits strong stability and robustness in continuous multi-obstacle avoidance scenarios,highlighting its effectiveness and engineering applicability in complex dynamic environments.