针对水下无人艇（Autonomous Underwater Vehicle，AUV）路径规划问题，在传统人工鱼群算法的基础上提出一种融合差分进化算法的DE-IAFSA算法。通过引入自适应因子更新鱼群的视野范围和移动步长，提高算法的前期收敛速度与后期收敛精度；利用对数函数优化个体表现，增强算法的适应性；融合差分进化算法的变异和交叉操作，以避免陷入局部最优。利用Matlab软件开展仿真实验，将改进后的DE-IAFSA算法与传统的人工鱼群算法进行对比。实验结果表明，改进后的DE-IAFSA算法比传统人工鱼群算法在三维地图(a)、地图(b)和地图(c)中收敛精度分别提高了18.2%、3.4%、2.6%，平均路径长度分别减少了12.9%、29.7%、19.8%，收敛速度分别提高了93%、82%、70%，进而验证了改进后算法的优化能力。该算法具有收敛速度快、收敛精度高、适应性强、避免陷入局部最优的特点。
Path planning for AUV in marine environments, proposing a DE-IAFSA algorithm incorporating differential evolutionary algorithm based on the traditional artificial fish schooling algorithm. By introducing an adaptive factor to update the visual field range and moving step size of the fish swarm, the early convergence speed and later convergence accuracy of the algorithm are improved. The logarithmic function is used to optimize the individual performance and enhance the adaptability of the algorithm. The mutation and crossover operations of differential evolution algorithm are integrated to avoid falling into local optimum. Simulation experiments using Matlab software, comparing the improved DE-IAFSA algorithm with the traditional artificial fish schooling algorithm. The experimental results show that, the experimental results show that the convergence accuracy of the improved DE-IAFSA algorithm is 18.2%, 3.4% and 2.6% higher than that of the traditional artificial fish swarm algorithm in the three-dimensional map (a), map (b) and map (c), respectively. The average path length is reduced by 12.9%, 29.7% and 19.8%, and the convergence speed is increased by 93%, 82% and 70%, respectively. This improves the efficiency of the algorithm in finding the shortest path. The algorithm has the characteristics of fast convergence speed, high convergence precision, strong adaptability and avoiding falling into local optimum.
2026,48(6): 141-149 收稿日期：2025-5-15
DOI：10.3404/j.issn.1672-7649.2026.06.019
分类号：U674.941；TP242
基金项目：2023年辽宁省教育厅基本科研资助项目（JYTMS20230472）
作者简介：郭阳(1999-),男,硕士研究生,研究方向为水下无人艇技术
参考文献：
[1] 石博博, 朱嘉晟, 杨天慈, 等. 改进粒子群权重的水下机器人路径规划[J]. 舰船科学技术, 2025, 47(5): 159-165.
SHI B B, ZHU J S, YANG T C, et al. Path planning of underwater vehicle based on improved particle swarm weight[J]. Ship Science and Technology, 2025, 47(5): 159-165.
[2] YANG Y, WANG Z, HU F, et al. Multi-objective optimization design for the maneuverability of underwater vehicles based on fully coupled hull-propeller-rudder interaction [J]. Ocean Engineering, 2025, (7): 333.
[3] YAO Z F, LIU Q Z, JU Y Z. Improved artificial fish swarm based optimize rapidly-exploring random trees multi-robot exploration algorithm[J]. Journal of Computational Methods in Sciences and Engineering, 2023, 23(5): 2779-2794.
[4] 王雷, 王艺璇, 李东东, 等. 基于改进遗传算法的移动机器人路径规划研究[J]. 华中科技大学学报(自然科学版), 2024, 52(5): 158-164.
WANG L, WANG Y X, LI D D, et al. Research on mobile robot path planning based on improved genetic algorithm[J]. Journal of Huazhong University of Science and Technology(Natural Science Edition), 2024, 52(5): 158-164.
[5] CHENG Y M, ZHANG J Q, MAHMOUD A S, et al. An improved multiple adaptive neuro fuzzy inference system based on genetic algorithm for energy management system of island microgrid[J]. Scientific Reports, 2025, 15(1): 17988-17988.
[6] 巩慧, 倪翠, 王朋, 等. 基于Dijkstra算法的平滑路径规划方法[J]. 北京航空航天大学学报, 2024, 50(2): 535-541.
GONG H, NI C, WANG P, et al. Smooth path planning method based on Dijkstra's algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics, 2024, 50(2): 535-541.
[7] 郭明皓, 姬鹏, 黄海威. 基于改进人工势场法的无人车路径规划与跟踪控制[J/OL]. 系统仿真学报, 1–10[2024–06–21].
GUO M H, JI P, HUANG H W. Unmanned vehicle path planning and tracking control based on improved artificial potential field method [J/OL]. Journal of System Simulation, 1–10 [2024–06–21].
[8] YU J Y, SHI Q Y, LIN W, et al. Path planning for emergency response and rescue vessels in inland rivers by improved artificial potential field algorithms[J]. Journal of Marine Science and Application, 2025(prepublish): 1-13.
[9] 张亮, 王鑫, 张建锋. 多障碍场景下改进RRT算法路径规划[J]. 计算机工程与设计, 2023, 44(6): 1706-1713.
ZHANG L, WANG X, ZHANG J F. Improved RRT algorithm path planning in multi-obstacle scenarios[J]. Computer Engineering and Design, 2023, 44(6): 1706-1713.
[10] 崔志伟, 张宇琳, 张飞舟, 等. 基于改进A~*算法的船舶路径优化[J]. 船舶工程, 2023, 45(11): 98-103.
CUI Z W, ZHANG Y L, ZHANG F Z, et al. Ship path optimization based on improved A~* algorithm[J]. Ship Engineering, 2023, 45(11): 98-103.
[11] YANG T Y, ZOU L, WU Z X, et al. An improved A-star algorithm coupled with graph division and AIS data for ship path planning [J]. Ocean Engineering, 2025, 30121234 –121234.
[12] ZHANG T , YU L , LI S , et al. Unmanned aerial vehicle 3d path planning based on an improved artificial fish swarm algorithm[J]. Drones, 2023, 7(10): 636.
[13] ZHAO L, WANG F, BAI Y. Route planning for autonomous vessels based on improved artificial fish swarm algorithm[J]. Ships and Offshore Structures, 2023, 18(6): 897-906.
[14] 马小陆, 李成成, 谭毅波, 等. 人工鱼群优化算法的移动机器人路径规划研究[J]. 机械科学与技术, 2024, 43(10): 1786-1796.
MA X L, LI C C, TAN Y B, et al. Research on mobile robot path planning based on artificial fish swarm optimization algorithm[J]. Mechanical Science and Technology, 2024, 43(10): 1786-1796.
[15] 高金喆, 寇志伟, 许寒琪, 等. 基于改进鱼群算法的牧场巡检机器人路径规划研究[J]. 中国农机化学报, 2024, 45(11): 202-208.
GAO J Z, KOU Z W, XU H Q, et al. Research on path planning of pasture inspection robot based on improved fish swarm algorithm[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(11): 202-208.
[16] 杨惠珍, 王子江, 周卓彧, 等. 基于改进PSO-Lévy算法的海流环境下AUV节能路径规划[J]. 水下无人系统学报, 2024, 32(2): 337-344.
YANG H Z, WANG Z J, ZHOU Z Y, et al. AUV energy-saving path planning in ocean current environment based on improved PSO-Lévy algorithm[J]. Journal of Underwater Unmanned Systems, 2024, 32(2): 337-344.
[17] LI F F, YUN D, JIN J K. Path planning and smoothing of mobile robot based on improved artificial fish swarm algorithm[J]. Scientific Reports, 2022, 12(1): 659-659.
[18] CHEN Y X, LI Q N. Vehicle behavior discovery and three-dimensional object detection and tracking based on spatio-temporal dependency knowledge and artificial fish swarm algorithm[J]. Biomimetics, 2024, 9(7): 412.
[19] 郭长珍, 李整. 自适应差分变异的人工鱼群算法[J]. 计算机系统应用, 2024, 33(8): 214-221.
GUO C Z, LI Z. Adaptive differential variation algorithm for artificial fish swarming[J]. Computer Systems & Applications, 2024, 33(8): 214-221.
[20] GUO W, QIN G X, WANG L, et al. Robot path planning based on improved artificial fish swarm algorithm and MAKLINK graph [J]. Control and Decision Making, 2020, 35(9): 2145–2152.
