针对快速扩展随机树（Rapidly-Exploring Random Tree, RRT）算法在结合无人船进行路径规划时存在规划时间长、路径冗余大、路径平滑度不符合欠驱动无人船航行要求等问题，提出一种改进RRT的无人船全局路径规划算法。算法中将贝叶斯优化算法融入目标采样过程，增强目标点采样导向性；引入动态步长和双向贪心剪枝策略作为重要辅助，进一步提升算法效率和路径质量；得到初始路径后采用动态权重3次B样条曲线进一步平滑处理。最后在3种类型障碍物环境下进行仿真实验并与RRT、RRT*算法进行对比。结果表明，改进RRT算法在规划时长、路径长度以及路径质量等方面有明显优势。改进后算法效率更高，路径平滑度更高，研究成果可为无人船自主航行提供参考。
To address issues like long planning time, excessive path redundancy, and insufficient smoothness for underactuated unmanned vessels when using the rapidly-exploring random tree (RRT) algorithm, an enhanced RRT-based global path planning method is proposed. The Bayesian optimization algorithm improves target point sampling orientation, while dynamic step size and bidirectional greedy pruning strategies boost algorithm efficiency and path quality. After generating the initial path, a dynamic weighted cubic B-spline curve refines smoothness. Simulations in three obstacle environments demonstrate the improved RRT algorithm’s superior planning speed, shorter path length, and higher-quality trajectories compared to RRT and RRT*. The results validate its efficiency and smoothness, offering insights for autonomous navigation of unmanned vessels.
2026,48(4): 155-161 收稿日期：2025-6-24
DOI：10.3404/j.issn.1672-7649.2026.04.024
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）资助项目（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] WU Y, WANG T, LIU S. A review of path planning methods for marine autonomous surface vehicles[J]. Journal of Marine Science and Engineering, 2024, 12(5): 833.
[2] 张树凯, 刘正江, 蔡垚, 等. 无人船艇航线自动生成研究现状及展望[J]. 中国航海, 2019, 42(3): 6-11.
[3] 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.
[4] 廖功铭, 任鸿翔, 王德龙, 等. 融合改进A*与VO算法的船舶避碰策略研究[J]. 舰船科学技术, 2025, 47(3): 32-38.
LIAO G M, REN H X, WANG D L, et al. Research on ship collision avoidance strategy based on improved A* and VO algorithm[J]. Ship Science and Technology, 2025, 47(3): 32-38.
[5] 黄兴旺. 基于多子域分组粒子群优化算法的小型无人船路径规划[J]. 船舶工程, 2021, 43(12): 158-165.
HUANG X W. Multi-area grouping-based particle swarm optimization for path-planning of small unmanned surface vehicle[J]. Ship Engineering, 2021, 43(12): 158-165.
[6] 欧阳子路, 王鸿东, 黄一, 等. 基于改进RRT算法的无人艇编队路径规划技术[J]. 中国舰船研究, 2020, 15(3): 18-24.
OUYANG Z L, WANG H D, HUANG Y, et al. Path planning technologies for USV formation based on improved RRT[J]. Chinese Journal of Ship Research, 2020, 15(3): 18-24.
[7] ZHANG R, GUO H, ANDRIUKAITIS D, et al. Intelligent path planning by an improved RRT algorithm with dual grid map[J]. Alexandria Engineering Journal, 2024, 88: 91-104.
[8] 李刚, 李祥, 陈智欣, 等. 面向改进RRT算法的全局路径规划研究[J]. 重庆理工大学学报(自然科学), 2025, 39(5): 1-9.
[9] HU W, CHEN S, LIU Z, et al. HA-RRT: A heuristic and adaptive RRT algorithm for ship path planning[J]. Ocean Engineering, 2025, 316: 119906.
[10] GU Q, ZHEN R, LIU J, et al. An improved RRT algorithm based on prior AIS information and DP compression for ship path planning[J]. Ocean Engineering, 2023, 279: 114595.
[11] CHEN R, ZHU Y, LIU J, et al. Research on ship path planning technology based on improved RRT algorithm[C]//2023 7th International Conference on Transportation Information and Safety (ICTIS). IEEE, 2023.
[12] 李军涛, 陈璐瑶, 侯星星, 等. 基于改进APF-RRT算法的无人艇航迹规划[J/OL]. 复杂系统与复杂性科学, 2024, 1-11.
[13] 李光宇, 李守军, 张锦. 应用改进RRT算法的水下机器人全局路径规划[J]. 舰船科学技术, 2021, 43(24): 46-48.
LI G Y, LI S J, ZHANG J. Research on global path planning of underwater vehicle using improved RRT algorithm[J]. Ship Science and Technology, 2021, 43(24): 46-48.
[14] 曲胜, 许志远, 张晓鹏, 等. 基于改进RRT算法的无人船路径规划研究[J]. 中国航海, 2024, 47(4): 175-180.
[15] LAVALLE S M. Rapidly-exploring random trees: a new tool for path planning[D]. Ames, USA: Iowa State University, 1998.
[16] LI Y, CUI R X, LI Z J, et al. Neural network approximation based near-optimal motion planning with kinodynamic constraints using RRT[J]. IEEE Transactions on Industrial Electronics, 2018, 65(11): 8717-8729.
[17] GONG L, ZHANG Y, CHENG J. Coordinated path planning based on RRT algorithm for robot[J]. Applied Mechanics and Materials, 2024, (494-495): 1003-1007.
[18] 谢高杨, 房立清, 李亚男, 等. 基于改进RRT算法的无人靶车路径规划研究[J]. 火炮发射与控制学报, 2024, 45(3): 80-86.
[19] 陈泉霖, 陈奕宇, 霍静, 等. 高维贝叶斯优化研究综述[J]. 软件学报, 2025, 36(6): 2576-2603.
[20] XU Z, GUO Y, SALEH J H. Efficient hybrid Bayesian optimization algorithm with adaptive expected improvement acquisition function[J]. Engineering Optimization, 2021, 53(10): 1786-1804.
[21] 闫成, 夏佳豪, 许可晗, 等. 降低涡轮转子气动激振力的改进贝叶斯优化算法[J/OL]. 北京航空航天大学学报, 1-12[2025-06-16].
[22] 谢国兵, 贺沩, 胡旺文, 等. 基于不均匀分配信息素及多目标优化的改进蚁群算法在无人船路径规划中的应用研究[J]. 中国舰船研究, 2025, 20(1): 115-124.
XIE G B, HE W, HU W W, et al. Application of an improved ant colony algorithm based on unevenly distributed pheromone and multi-objective optimization in path planning for unmanned surface vehicles[J]. Chinese Journal of Ship Research, 2025, 20(1): 115-124.
