针对无人船在障碍物环境中路径规划效率低、路径冗余大、平滑性差等问题，提出一种融合人工势场法的改进RRT*算法（Artificial Potential Field Rapidly-exploring Random Tree*，APF-RRT*）。该算法以人工势场模型为引导机制，构建包含信息激励势场、引力势场和斥力势场的复合势能函数，从而有目的性地引导采样点朝向目标区域并远离障碍物，提高算法采样效率；同时引入动态步长策略加快扩展速度，最后结合贪心剪枝和路径平滑机制优化初始路径。在2种典型环境下进行仿真对比实验，结果表明文中改进RRT*算法在规划效率、路径长度、平滑度以及稳定性方面优于传统算法，平均规划时长、路径长度、初始路径节点数与改进前相比分别减少了50.88%、6.24%、30.29%。改进算法为无人船在障碍物环境下生成安全、高效的航行路径提供了有力保障。
Aiming at the problems of low path planning efficiency, large path redundancy and poor smoothness of unmanned ships in obstacle environments, an improved RRT* algorithm integrating artificial potential field rapidly-exploring random tree* (APF-RRT*) is proposed. This algorithm takes the artificial potential field model as the guiding mechanism to construct a composite potential energy function including the information excitation potential field, the gravitational potential field and the repulsive potential field, thereby purposefully guiding the sampling points towards the target area and away from obstacles, and improving the sampling efficiency of the algorithm. Meanwhile, a dynamic step size strategy is introduced to accelerate the expansion speed. Finally, the initial path is optimized by combining greedy pruning and path smoothing mechanisms. Simulation comparison experiments were conducted in two typical environments. The results show that the improved RRT* algorithm proposed in this paper is superior to the traditional algorithm in terms of planning efficiency, path length, smoothness and stability. The average planning duration, path length and the number of initial path nodes are reduced by 50.88%, 6.24% and 30.29% respectively compared with those before the improvement. The improved algorithm provides a strong guarantee for unmanned ships to generate safe and efficient navigation paths in obstacle environments.
2026,48(5): 151-157 收稿日期：2025-7-1
DOI：10.3404/j.issn.1672-7649.2026.05.024
分类号：U674；TP18
基金项目：辽宁省教育厅科学研究项目（DL202004）；辽宁省自然科学基金计划项目（2023-BSBA-020）；设施渔业教育部重点实验室（大连海洋大学）资助（202320）
作者简介：陈小龙(2001-),男,硕士研究生,研究方向为无人船路径规划
参考文献：
[1] 赵亮, 王芳, 白勇. 水面无人艇路径规划的现状与挑战[J]. 船舶工程, 2022, 44(4): 1-7+48
ZHAO L, WANG F, BAI Y. Current situation and challenges of path planning for surface unmanned craft[J]. Ship Engineering, 2022, 44(4): 1-7+48
[2] 胡耀炜, 汤萍萍, 张晖, 等. 复杂动态环境中移动机器人双层路径规划方法[J/OL]. 控制与决策, 1-10.
HU Y W, TANG P P, ZHANG H, et al. Double-layer path planning method for mobile robots in complex dynamic environments [J/OL]. Control and Decision, 1-10.
[3] 焉晓贞, 周新悦, 罗清华. 改进A-star算法的无人船动态路径规划[J/OL]. 系统工程与电子技术, 1-20.
YAN X Z, ZHOU X Y, LUO Q H. Dynamic path planning of unmanned ship based on improved a-star algorithm [J/OL]. Systems Engineering and Electronics Technology, 1-20.
[4] 陈宇文, 徐照. 基于混合蚁群算法的无人船航行路径自主规划[J]. 舰船科学技术, 2023, 45(22): 93-96
CHEN Y W, XU Z. Autonomous navigation path planning of unmanned ships based on hybrid ant colony algorithm[J]. Ship Science and Technology, 2023, 45(22): 93-96
[5] 赵思沛, 史成军, 王浩亮, 等. 基于改进RRT算法的船舶机舱巡检机器人路径规划[J]. 船舶工程, 2022, 44(7): 109-114
ZHAO S P, SHI C P, WANG H L, et al. Path Planning of Ship Engine Room Inspection Robot Based on Improved RRT Algorithm[J]. Ship Engineering, 2022, 44(7): 109-114
[6] 张艳珠, 侯亢钧, 陈勇, 等. 基于强化学习的改进RRT*路径规划[J]. 沈阳理工大学学报, 2025, 44(4): 1-6+12
ZHANG Y Z, HOU K J, CHEN Y, et al. Improved RRT* path planning based on reinforcement learning[J]. Journal of Shenyang Ligong University, 2025, 44(4): 1-6+12
[7] XU T, MA J, QIN P, et al. An improved RRT? algorithm based on adaptive informed sample strategy for coastal ship path planning[J]. Ocean Engineering, 2025, 333: 121511
[8] LIU Z, CUI J, MENG F, et al. Research on intelligent ship route planning based on the adaptive step size informed-RRT* algorithm[J]. Journal of Marine Science and Application, 2024: 1-11.
[9] LIU C, XIAO F, MA Y, et al. An enhanced RRT* algorithm with biased sampling and dynamic stepsize strategy for ship route planning in the high-risk areas[J]. Ocean Engineering, 2025, 332: 121466
[10] 杨左华, 王玉龙, 戚爱春. 基于改进RRT*算法的无人艇全局避障规划[J]. 舰船科学技术, 2019, 41(23): 167-172
YANG Z H, WANG Y L, QI A C. Global obstacle avoidance planning for unmanned vessels based on the improved RRT* algorithm[J]. Ship Science and Technology, 2019, 41(23): 167-172
[11] 周卫祥, 许继强. 基于改进人工势场法的RRT*无人船路径规划算法[J]. 中北大学学报(自然科学版), 2024, 45(2): 123-131
ZHOU W X, XU J Q. RRT* unmanned ship path planning algorithm based on improved artificial potential field method[J]. Journal of North University of Chia (Natural Science Edition), 2024, 45(2): 123-131
[12] 张喜超, 尹勇. 基于改进RRT*算法的无人船路径规划[J]. 中国航海, 2023, 46(1): 143-147+154
ZHANG X C, YIN Y. Path planning for unmanned surface vehicle based on improved RRT* algorithm[J]. Navigation of China, 2023, 46(1): 143-147+154
[13] KARAMAN S, FRAZZOLI E. Sampling-based algorithms for optimal motion planning[J]. The International Journal of Robotics Research, 2011, 30(7): 846-894
[14] KHATIB O. Real-time obstacle avoidance for manipulators and mobile robots[J]. The International Journal of Robotics Research, 1986, 5(1): 90-98
[15] 魏凯, 潘家财, 杨朝棚, 等. 海流环境下面向动态目标的无人艇路径规划[J]. 舰船科学技术, 2025, 47(6): 69-75
WEI K, PAN J C, YANG C P, et al. Path planning for unmanned vessels facing dynamic targets in ocean current environments[J]. Ship Science and Technology, 2025, 47(6): 69-75
[16] 陈澳, 朱建阳, 蒋林, 等. 基于多策略融合的改进RRT路径规划算法[J]. 武汉科技大学学报, 2024, 47(4): 282-289
CHEN A, ZHU J Y, JIANG L, et al. Improved RRT path planning algorithm based on multi-strategy fusion[J]. Journal of Wuhan University of Science and Technology, 2024, 47(4): 282-289
[17] 符运来, 王魏, 刘妙男, 等. 基于改进P-RRT*算法的无人船路径规划[J/OL]. 控制工程, 1-8.
FU Y L, WANG W, LIU M N, et al. Path planning algorithm for unmanned vessel based on improved P-RRT* algorithm [J/OL]. Control Engineering, 1-8.
