为提高水下机器人路径规划的收敛速度和行驶路径的光滑性，本文提出改进粒子群算法的最优路径规划。建立改进的粒子群算法数学模型，对传统粒子群算法进行3种权重系数改进研究；建立水下环境场景数学模型，模拟水下复杂地形；融合贝塞尔曲线。在迭代10次的最优适应度，收敛速度提高44%；在迭代20次时，收敛速度提高15%；在迭代30次时，收敛速度提高2%。改进算法相比于传统算法，实现前期全局寻优能力强，易得到合适的种子；后期局部寻优能力强，易提高收敛精度；并且在复杂环境下可以更快收敛到最优路径，缩短水下机器人的作业周期。改进的算法可以对水下环境进行全局搜索，且不易陷入最优解，供水下机器人领域参考。
In order to improve the convergence speed and smoothness of the path planning of the underwater vehicle, the optimal path planning of the improved particle swarm optimization algorithm is proposed. The mathematical model of the improved particle swarm optimization algorithm is established, and the three weight coefficients of the traditional particle swarm optimization algorithm are improved. The mathematical model of underwater environment scene is established to simulate underwater complex terrain. Blending Bessel Curves. At the optimal fitness of 10 iterations, the convergence speed is increased by 44 %. When the iteration is 20 times, the convergence speed is increased by 15 %. When the iteration is 30 times, the convergence speed is increased by 2 %. Compared with the traditional algorithm, the improved algorithm has strong global optimization ability in the early stage, and it is easy to get suitable seeds. In the later stage, the local optimization ability is strong, and the convergence accuracy is easy to be improved. In addition, it can converge to the optimal path faster in complex environment and shorten the operation cycle of underwater robot. The improved algorithm can search the underwater environment globally and is not easy to fall into the optimal solution. It can be used as a reference for the field of robots under water supply.
2025,47(5): 159-165 收稿日期：2024-8-22
DOI：10.3404/j.issn.1672-7649.2025.05.024
分类号：U676
基金项目：辽宁省教育厅基本科研资助项目（JYTMS20230472）
作者简介：石博博（1998 – ），男，硕士研究生，研究方向为水下机器人技术
参考文献：
[1] POLI R, KENNEDY J, BLACKWELL T. Particle swarm optimization. [J]. Swarm Intelligence, 2007, 1(1): 33-57.
[2] 张琬琦. 基座移动状态下水下机械臂末端控制研究[D]. 哈尔滨: 哈尔滨工业大学, 2022.
[3] 蒲兴成, 张军, 张毅. 基于时变适应度函数的改进粒子群算法及其在移动机器人路径规划中的应用[J]. 计算机应用研究, 2010, 27(12): 4454-4456.
PU X C, ZHANG J, ZHANG Y. Improved particle swarm algorithm based on time-varying fitness function and its application in mobile robot path planning Research on end control of underwater robotic arm under base moving state[J]. Application Research of Computers, 2010, 27(12): 4454-4456.
[4] 陈旭东, 杨光永, 徐天奇, 等. 基于多策略融合改进粒子群算法的路径规划研究[J]. 组合机床与自动化加工技术, 2024(2): 44-50.
CHEN X D, YANG G Y, XU T Q, et al. Research on path planning based on multi-strategy fusion improved particle swarm algorithm[J]. Combined machine tool and automatic machining technology, 2024(2): 44-50.
[5] 宋智, 姬书得, 胡为, 等. 基于改进粒子群算法的两栖机器人三维路径规划研究[J]. 科技与创新, 2024(4): 59-61.
SONG Z, JI S D, HU W, et al. Research on three-dimensional path planning for amphibious robots based on improved particle swarm algorithm[J]. Science and Technology & Innovation, 2024(4): 59-61.
[6] 孔鹏飞. 融合爬山策略的改进粒子群混合路径规划算法[J]. 电光与控制, 2024, 31(9): 6-11+30.
KONG P F. An improved particle swarm hybrid path planning algorithm incorporating hill climbing strategies[J]. Electronics Optics & Control, 2024, 31(9): 6-11+30.
[7] ARUMUGAM S M , RAO C V M. On the performance of the particle swarm optimization algorithm with various inertia weight variants for computing optimal control of a class of hybrid systems[J]. Discrete Dynamics in Nature and Society, 2006.
[8] 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. Global path planning for underwater robots applying improved RRT algorithm[J]. Ship Science and Technology, 2021, 43(24): 46-48.
[9] 孙兵, 戚国亮, 张威, 等. 基于粒子群-人工势场的多AUV拦截技术研究[J]. 控制工程, 2024, 31(5): 769-777.
SUN B, QI G L, ZHANG W, et al. Research on multi-AUV interception technique based on particle swarm-artificial potential field[J]. Control Engineering, 2024, 31(5): 769-777.
[10] 李根强. 基于三次样条插值的采样数据光滑曲线形成法[J]. 计算技术与自动化, 2001(1): 59-62.
LI G Q. Smooth curve formation method for sampled data based on cubic spline interpolation[J]. Computing Technology and Automation, 2001(1): 59-62.
[11] 翁昱, 曾庆军, 李维, 等. 基于智能预测控制的鱼雷状小型无人艇轨迹跟踪研究[J]. 中国舰船研究, 2024, 19(1): 158-168.
WENG Y, ZENG Q J, LI W, et al. Trajectory tracking study of torpedo-shaped small unmanned boats based on intelligent predictive control[J]. Chinese Journal of Ship Research[J]. Chinese Journal of Ship Research, 2024, 19(1): 158-168.
[12] 林焰, 辛登月, 卞璇屹, 等. 改进自适应惯性权重粒子群算法及其在核动力管道布置中的应用[J]. 中国舰船研究, 2023, 18(3): 1-12.
LIN Y, XIN D Y, BIAN X Y, et al. Improved adaptive inertial weight particle swarm algorithm and its application to nuclear power piping arrangement[J]. Chinese Journal of Ship Research, 2023, 18(3): 1-12.
[13] 印波, 王锡淮, 肖健梅. 基于改进粒子群优化算法的船舶能量管理方案[J]. 中国舰船研究, 2020, 15(6): 37-45.
YIN B, WANG X H, XIAO J M. Ship energy management scheme based on improved particle swarm optimization algorithm[J]. Chinese Journal of Ship Research, 2020, 15(6): 37-45.
[14] 李广强, 董文超, 朱大庆, 等. 基于改进鲸鱼优化算法的AUV三维路径规划[J]. 系统工程与电子技术, 2023, 45(7): 2170-2182.
LI G Q, DONG W C, ZHU D Q, et al. AUV 3D path planning based on improved whale optimization algorithm[J]. Systems Engineering and Electronics, 2023, 45(7): 2170-2182.
[15] 李世奇, 孙兵, 朱蟋蟋. 海流环境下基于改进D*算法的AUV动态路径规划[J]. 高技术通讯, 2022, 32(1): 84-92.
LI S Q, SUN B, ZHU X X. AUV dynamic path planning based on improved D* algorithm in sea current environment[J]. Chinese High Technology Letters, 2022, 32(1): 84-92.
[16] 张瀚彬, 史先鹏, 刘喜梅. 基于改进量子粒子群算法的AUV路径规划研究[J]. 海洋工程, 2023, 41(2): 86-92.
ZHANG H B, SHI X P, LIU X M. Research on AUV path planning based on improved quantum particle swarm algorithm[J]. The Ocean Engineering, 2023, 41(2): 86-92.
[17] 蒲兴成, 冼文杰, 聂壮. 基于改进蚁群优化算法的AUV三维路径规划[J]. 智能系统学报, 2024, 19(3): 627-634.
PU X C, XIAN W J, NIE Z. Three-dimensional path planning for AUV based on improved ant colony optimization algorithm[J]. CAAI Transactions on Intelligent Systems, 2024, 19(3): 627-634.
[18] 张亚林, 李晓松. 改进AOA结合贝塞尔曲线平滑的机器人路径规划[J]. 计算机工程与设计, 2023, 44(10): 3170-3178.
ZHANG Y L, LI X S. Improved AOA combined with bessel curve smoothing for robot path planning[J]. Computer Engineering and Design, 2023, 44(10): 3170-3178.
[19] 周凯莉, 刘从军. 基于优化麻雀搜索算法的水下机器人路径规划研究[J]. 计算机与数字工程, 2023, 51(9): 2048-2054.
ZHOU K L, LIU C J. Research on underwater robot path planning based on optimized sparrow search algorithm[J]. Computer & Digital Engineering, 2023, 51(9): 2048-2054.
