Abstract: To address the challenges of path planning for unmanned surface vessels (USVs) in complex environments and the relatively low efficiency of existing algorithms, this paper proposes a novel path planning method that integrates the artificial potential field (APF) approach with the rapidly-exploring random tree star (RRT*) algorithm—referred to as the bidirectional APF-RRT algorithm. The proposed method first introduces a goal-biased strategy, guiding newly generated nodes to expand preferentially toward the target direction. Additionally, a bidirectional search mechanism is adopted to drive two random trees toward each other, thereby accelerating the convergence speed of the algorithm. During node expansion, the attractive force from the artificial potential field guides the expansion toward the target, while the repulsive force enables effective obstacle avoidance. Finally, simulation experiments are conducted on the MATLAB platform to compare the proposed algorithm with traditional RRT* and APF-RRT* algorithms. Experimental results demonstrate that the bidirectional APF-RRT* algorithm outperforms the others in terms of the number of path nodes, path length, and planning efficiency across multiple typical scenarios, indicating superior planning performance and environmental adaptability.

Key words: unmanned surface vessel (USV), artificial potential field (APF), RRT* algorithm, path planning

摘要： 为解决无人船在复杂水面环境中路径规划困难且算法效率较低的问题,该文提出了一种融合人工势场（artificial potential field,APF）法与RRT*（rapidly-exploring random tree star）算法的路径规划方法——双向APF-RRT*算法。该方法首先引入目标偏置策略,使新生成节点更倾向于朝目标方向扩展;同时采用双向搜索机制,驱动两棵随机树相互靠近,以加快算法收敛速度。在节点扩展过程中,利用APF法中的引力引导节点朝目标点扩展,利用斥力实现有效避障。最后,在Matlab平台开展仿真实验,将该文算法同传统RRT*算法和APF-RRT*算法进行对比分析。实验结果表明：在多种典型场景下,双向APF-RRT*算法较上述算法在路径节点数量、路径长度及规划效率等方面均表现更优,展现出更高的规划性能与环境适应能力。

关键词: 无人船, 人工势场法, RRT*算法, 路径规划