本文针对传统人工势场法在无人船向目标点移动过程中，由于障碍物斥力与目标点引力相平衡而导致局部极小值现象，以及目标点可能处于障碍物斥力影响范围从而无法到达的问题，提出基于粒子群优化算法的人工势场法。首先，将无人船与目标点之间的直线距离引入斥力函数中，解决目标点不可达问题；随后，在局部极小值区域的特定范围内利用粒子群优化算法生成若干粒子，并基于评价函数确定最优虚拟目标点，此虚拟目标点可引导无人船脱离局部极小值区域。仿真实验结果表明，改进后的算法能够成功使无人船摆脱局部极小值陷阱并顺利到达目标点，且整体路径平滑度有所提高，用时较短，提升了在复杂环境下的鲁棒性。
Aiming at the local minimum value phenomenon caused by the balance of the repulsive force of obstacles and the attractive force of the target point during the movement of the unmanned surface vehicle towards the target point in the conventional artificial potential field method, as well as the problem that the target point may be within the influence range of the repulsive force of obstacles and thus cannot be reached, presents an artificial potential field method grounded in the particle swarm optimization algorithm. Firstly, incorporating the straight-line distance between the unmanned surface vehicle and the target point into the repulsive force function effectively resolves the issue of the target being unreachable; then, within a specific range of the local minimum value area, several particles are generated using the particle swarm optimization algorithm, and the optimal virtual target point is determined based on the evaluation function. This virtual target point can guide the unmanned surface vehicle to escape from the local minimum value area. The simulation experiment results demonstrate that the improved algorithm effectively helps the unmanned surface vehicle escape the local minimum trap and reach the target point smoothly. Furthermore, the overall path smoothness is enhanced, and the travel time is reduced, thereby improving robustness in complex environments.
2026,48(4): 179-184 收稿日期：2025-7-3
DOI：10.3404/j.issn.1672-7649.2026.04.027
分类号：U664.82；TP242.6
基金项目：山西省科技创新人才团队专项资助项目（202304051001030）；水声对抗技术重点实验室开放基金项目（2023JCJQLB3302）
作者简介：孙岩林(2001-),男,硕士研究生,研究方向为嵌入式系统
参考文献：
[1] 王旭, 朱其新, 朱永红. 面向二维移动机器人的路径规划算法综述[J]. 计算机工程与应用, 2023, 59(20): 51-66.
WANG X, ZHU Q X, ZHU Y H. A review of path planning algorithms for two-dimensional mobile robots[J]. Computer Engineering and Applications, 2023, 59(20): 51-66.
[2] 李季睿. 基于改进A*算法的移动机器人路径规划研究[D]. 武汉: 江汉大学, 2023.
[3] 汪小帅, 朱其新, 朱永红. 改进D*算法下的无人机三维路径规划[J]. 西安工程大学学报, 2023, 37(3): 83-91.
WANG X S, ZHU Q X, ZHU Y H. 3D path planning of UAV based on improved D* algorithm[J]. Journal of Xi’an Polytechnic University, 2023, 37(3): 83-91.
[4] 黄永良, 李燕, 张小龙. 基于改进蚁群算法的机器人路径规划[J]. 电脑与信息技术, 2023, 31(2): 1-4.
HUANG Y L, LI Y, ZHANG X L. Robot path planning based on improved ant colony algorithm[J]. Computer and Information Technology, 2023, 31(2): 1-4.
[5] 倪建云, 杜合磊, 谷海青, 等. 改进人工势场法的移动机器人路径规划研究[J]. 重庆理工大学学报(自然科学), 2023, 37(11): 247-256.
NI J Y, DU H L, GU H Q, et al. Path planning of mobile robot based on improved artificial potential field method[J]. Journal of Chongqing University of Technology (Natural Science), 2023, 37(11): 247-256.
[6] 赖荣燊, 窦磊, 巫志勇, 等. 融合改进A*算法和动态窗口法的移动机器人路径规划[J]. 系统仿真学报, 2024, 36(8): 1884-1894.
LAI R S, DOU L, WU Z Y, et al. Mobile robot path planning based on fusion of improved A* algorithm and dynamic window approach[J]. Journal of System Simulation, 2024, 36(8): 1884-1894.
[7] 彭艳, 鲍凌志, 瞿栋, 等. Multi-Bug全局路径规划算法研究[J]. 农业机械学报, 2020, 51(6): 375-384.
PENG Y, BAO L Z, QU D, et al. Research on Multi-Bug global path planning algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(6): 375-384.
[8] 朱敏, 胡若海, 卞京. 基于改进蚁群算法的移动机器人路径规划[J]. 现代制造工程, 2024(3): 38-44.
ZHU M, HU R H, BIAN J. Path planning of mobile robot based on improved ant colony algorithm[J]. Modern Manufacturing Engineering, 2024(3): 38-44.
[9] 时光泰, 王合龙. 改进蚁群算法无人机三维航迹规划[J/OL]. 电光与控制, 2025: 1–8.
SHI G T, WANG H L. 3D trajectory planning of UAV based on improved ant colony algorithm [J/OL]. Electro-Optic & Control, 2025: 1–8.
[10] 许万, 程兆, 朱力, 等. 一种基于改进人工势场法的局部路径规划算法[J]. 电子测量技术, 2022, 45(19): 83-88.
XU W, CHENG Z, ZHU L, et al. A local path planning algorithm based on improved artificial potential field method[J]. Electronic Measurement Technology, 2022, 45(19): 83-88.
[11] LIU Y , CHEN C , WANG Y , et al. A fast formation obstacle avoidance algorithm for clustered UAVs based on artificial potential field[J]. Aerospace Science and Technology, 2024, 147108974.
[12] 李天国, 赖于树, 符庆川. 融合TangentBug算法和人工势场法的移动机器人路径规划[J]. 现代计算机, 2024, 30(17): 37-43.
LI T G, LAI Y S, FU Q C. Path planning for mobile robot based on integration of TangentBug algorithm and artificial potential field method[J]. Modern Computer, 2024, 30(17): 37-43.
[13] LUAN T, TAN Z, YOU B, et al. Path planning of unmanned surface vehicle based on artificial potential field approach considering virtual target points[J]. Transactions of the Institute of Measurement and Control, 2024, 46(6): 1190–1202.
[14] 赵炳巍, 贾峰, 曹岩, 等. 基于模拟退火算法的人工势场法路径规划研究[J]. 计算机工程与科学, 2022, 44(4): 746-752.
ZHAO B W, JIA F, CAO Y, et al. Path planning based on artificial potential field method with simulated annealing algorithm[J]. Computer Engineering and Science, 2022, 44(4): 746-752.
[15] 胡铮, 徐斌. 改进人工势场法的轨迹规划[J]. 电光与控制, 2023, 30(3): 38-41+53.
HU Z, XU B. Trajectory planning based on improved artificial potential field method[J]. Electro-Optic & Control, 2023, 30(3): 38-41+53.
