为了解决无人船在路径规划过程中与目标船或障碍物距离过近、未能及时采取避让措施的问题，提出一种结合国际海上避碰规则的改进差分进化算法，并将其应用于无人船的路径规划和避碰。对差分进化算法中的控制因子F和CR进行自适应调整，从而动态优化算法在不同时期的搜索能力，进而提高搜索效率。本文使用总航程、路径平滑度以及国际海上避碰规则构建适应度函数，选取高质量路径点。仿真实验结果表明，改进的差分进化算法使得本船在与其他船舶的会遇过程中能及时有效采取避让措施，同时确保规划路径的经济性，从而证明了算法的有效性。
To solve the problem of unmanned ships getting too close to target vessels or obstacles and fail to take avoidance measures in time during the path planning process, an improved differential evolution algorithm integrated with the International Regulations for Preventing Collisions at Sea (COLREGs) was proposed and applied to the path planning and collision avoidance of USVs. The control factor F and CR in the differential evolution algorithm were adaptively adjusted to dynamically optimize the algorithm's search capabilities at different stages, enhancing search efficiency. The fitness function is constructed using total voyage distance, path smoothness, and COLREGs to select high-quality path points. Simulation results demonstrate that the improved differential evolution algorithm enables the vessel to take timely and effective evasive actions during encounters with other ships while ensuring the economic efficiency of the planned path, thereby proving the effectiveness of the algorithm.
2026,48(1): 154-158 收稿日期：2024-10-30
DOI：10.3404/j.issn.1672-7649.2026.01.022
分类号：U664.82
基金项目：国家自然科学基金资助项目（51939001，62371085）；中央高校基本科研基金（3132024137）；2023 DMU 航海学院一等交叉学科研究项目（2023JXA09）
作者简介：肖仲明(1982-),男,副教授,研究方向为海上交通风险评价、路径规划与避碰
参考文献：
[1] 张文拴, 李争, 郑瑶. 国内外无人船发展现状及研发趋势[J]. 舰船科学技术, 2024, 46(15): 79-83.
ZHANG W S, LI Z, ZHENG Y. The current status and research and development trend of unmanned ships at home and abroad[J]. Ship Science and Technology, 2024, 46(15): 79-83.
[2] 宁君, 马昊冉, 李伟, 等. 基于改进RRT算法的船舶路径规划与跟踪控制[J]. 中国航海, 2022, 45(3): 106-112.
NING J, MA H R, LI W, et al. Ship route planning and tracking control based on improved RRT algorithm [J]. Navigation of China, 2022, 45(3): 106-112.
[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 status and challenges of unmanned surface vehicle path planning [J]. Ship Engineering, 2022, 44(4): 1-7+48.
[4] 陈新, 袁宇浩, 饶丹. 一种改进A*算法在无人船路径规划中的应用[J]. 计算机仿真, 2021, 38(3): 277-281.
CHEN X, YUAN Y H, RAO D. Improved A* algorithm and its application in path planning of unmanned surface vehicle [J]. Computer Simulation, 2021, 38(3): 277-281.
[5] 王成, 任佳, 张育. 基于改进蚁群算法的无人船路径规划研究[J]. 海南大学学报(自然科学版), 2021, 39(3): 242-250.
WANG C, REN J, ZHANG Y. Research on unmanned ship path planning based on improved ant colony algorithm[J]. Journal of Hainan University (Natural Science), 2021, 39(3): 242-250.
[6] 王鸿东, 易宏, 向金林, 等. 基于海事规则的中型无人艇避碰路径规划算法研究及应用[J]. 中国舰船研究, 2022, 17(5): 184-195+203.
WANG H D, YI H, XIANG J L, et al. Collision avoidance path planning algorithm research and application of medium-sized USV based on COLREGS[J]. Chinese Journal of Ship Research, 2022, 17(5): 184-195+203.
[7] 徐小强, 刘静雯, 冒燕. 基于改进粒子群算法的无人船全局路径规划研究[J]. 武汉理工大学学报, 2023, 45(3): 131-138.
XU X Q, LIU J W, MAO Y. Global path planning of USV based on improved PSO [J]. Journal of Wuhan University of Technology, 2023, 45(3): 131-138.
[8] 宁君, 马昊冉, 李铁山. 基于改进人工势场法的船舶路径规划与跟踪控制[J]. 哈尔滨工程大学学报, 2022, 43(10): 1414-1423.
NING J, MA H R, LI T S. Underactuated surface vessel path planning and following control based on an improved artificial potential field method[J]. Journal of Harbin Engineering University, 2022, 43(10): 1414-1423.
[9] STORN R, PRICE K. Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11: 341–359.
[10] GONG Y, ZHANG S, LUO M. A mutation operator self-adaptive differential evolution particle swarm optimization algorithm for USV navigation[J]. Front. Neurorobot 2022, 16: 1076455.
[11] YUAN Q, SUN R, DU X. Path planning of mobile robots based on an improved particle swarm optimization algorithm[J]. Processes. 2023, 11(1): 26.
