针对无人艇在多动态障碍物下避障、快速规划路径进行导航决策的要求，传统的动态窗口算法（DWA）存在运行效率低、容易陷入局部优化、复杂环境下搜索能力差等问题。在具有多个动态障碍物的复杂环境中，引入一种模糊逻辑算法对DWA算法进行改进，提高了路径评估函数的灵活性。模糊控制系统通过输入无人艇、终点和周围障碍物的信息，输出评价函数的相应系数权值。在无人艇搜索路径过程中，实时调整轨迹评价函数的权重，以达到优化路径的目的。仿真实验表明，模糊改进的动态窗口方法可以使规划的路径更平滑，获得更短的路径，同时有效地减少了无人艇的路径搜索时间。在具有多个动态障碍物的环境中，可以有效地实现动态避障。
For the requirements of unmanned boats to avoid obstacles under multi-dynamic obstacles and quickly plan paths for navigational decision-making, traditional dynamic window algorithms suffer from the problems of low operating efficiency, easy fall into local optimization, and poor search ability in complex environments. In this paper, a fuzzy logic algorithm is introduced to improve the DWA algorithm in a complex environment with multiple dynamic obstacles, which improves the flexibility of the path evaluation function. The fuzzy control system outputs the corresponding coefficient weights of the evaluation function by inputting information about the unmanned boat, the endpoint, and surrounding obstacles. The weights of the trajectory evaluation function are adjusted in real time during the search path of the unmanned boat to achieve the purpose of optimizing the path. The simulation experiments show that the fuzzy improved dynamic window method can make the planned path smoother and obtain shorter paths while effectively reducing the time of searching paths for unmanned craft. Dynamic obstacle avoidance can be effectively realized in an environment with multiple dynamic obstacles while searching for the globally optimal path.
2025,47(6): 62-68 收稿日期：2024-5-11
DOI：10.3404/j.issn.1672-7649.2025.06.010
分类号：U666.11
基金项目：高性能船舶技术教育部重点实验室开放基金课题资助项目（gxnc23052803）
作者简介：林泽琼（1999 – ），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 status and challenges of surface unmanned craft path planning[J]. Ship Engineering, 2022, 44(4): 1-7+48.
[2] BAI C E, LI B H, XU X F, et al. Current status of unmanned ship research and internal structure outlook (in English)[J]. Journal of Marine Science and Application, 2022, 21(2): 47-58.
[3] 柳晨光, 初秀民, 谢朔, 等. 船舶智能化研究现状与展望[J]. 船舶工程, 2016, 38(3): 77-84+92.
[4] GUO B, GUO N, CEN Z. Obstacle avoidance with dynamic avoidance risk region for mobile robots in dynamic environments[J]. IEEE Robotics and Automation Letters, 2022, 7(3): 5850-5857.
[5] XING B, YU M, LIU Z, et al. A Review of path planning for unmanned surface vehicles[J]. J. Mar. Sci. Eng. 2023, 11, 1556.
[6] LI M, MOU J, HE Y, et al. Dynamic trajectory planning for unmanned ship under multi-object environment. J Mar Sci Tech, 2022, 27: 173–185.
[7] GUAN C, WANG S. Robot Dynamic path planning based on improved A* and DWA algorithms[C]//2022 4th International Conference on Control and Robotics (ICCR), Guangzhou, China, 2022.
[8] 谭智坤, 张隆辉, 刘正锋, 等. 融合改进动态窗口法与速度障碍法的无人船局部路径规划[J]. 船舶力学, 2023, 27(3): 311-322.
TAN Z K, ZHANG L H, LIU Z F, et al. Localized path planning for unmanned vessels by integrating the improved dynamic window method and velocity barrier method[J]. Ship Mechanics, 2023, 27(3): 311-322.
[9] 姚进鑫, 刘丽桑, 何栋炜, 等. 融合优化A~*算法与动态窗口法的动态路径规划算法研究[J]. 重庆理工大学学报(自然科学), 2022, 36(7): 197-207.
[10] GUO T, SUN Y, LIU Y, et al. An automated guided vehicle path planning algorithm based on improved A* and dynamic window approach fusion[J]. Appl. Sci. 2023, 13, 10326.
[11] 高宇, 赵嵩郢. 基于动态窗口法的无人艇局部路径规划[J]. 船电技术, 2022, 42(7): 50-54.
GAO Y, YING ZHAO S. Localized path planning for unmanned boats based on dynamic window method[J]. Ship Electricity Technology, 2022, 42(7): 50-54.
[12] 程传奇, 郝向阳, 李建胜等. 融合改进A~*算法和动态窗口法的全局动态路径规划[J]. 西安交通大学学报, 2017, 51(11): 137-143.
[13] 齐款款, 李二超, 毛玉燕. 改进A*算法融合自适应DWA的移动机器人动态路径规划[J]. 数据采集与处理, 2023, 38(2): 451-467.
[14] XHANG L Y, HAN Y, JIANG B. Research on path planning method of unmanned boat based on improved DWA algorithm[J]. Journal of Sensors, 2022, 2022.
[15] 龚鹏, 李文博, 马庆升, 等. 基于改进A~*算法的无人车路径规划研究[J]. 组合机床与自动化加工技术, 2023(3): 17-20+24.
