基于智能链式改进人工势场的无人机航迹规划

doi:10.12305/j.issn.1001-506X.2026.10.32

摘要/Abstract

摘要：

针对复杂环境下人工势场法规划无人机航迹易陷入局部极小值的难题，提出一种智能链式改进人工势场无人机航迹规划方法。通过在航迹中设置利用蚁群算法智能生成的链式子目标点，避免陷入局部最优，解决局部极小值问题；但传统蚁群算法规划航迹转弯点多、收敛速度慢，通过构造多因素启发函数、优化信息素更新方法、设置自适应权重、设计航迹清洗策略，平滑航迹，加快收敛速度。针对人工势场法目标不可达问题，引入相对距离改进斥力函数，使目标可达。仿真结果表明，改进算法能在局部极小值点快速逃脱，实现复杂动态环境下的无人机航迹规划。

关键词: 蚁群算法, 人工势场法, 链式子目标点, 动态环境, 航迹规划

Abstract:

To address the problem that the artificial potential field method is prone to falling into local minima when planning unmanned aerial vehicle （UAV） trajectories in complex environments, an intelligent chain-based improved artificial potential field method for UAV trajectory planning is proposed. By setting chain sub-target points intelligently generated by the ant colony algorithm in the trajectory, it can avoid falling into local optimality and solve the problem of local minima. However, the traditional ant colony algorithm for trajectory planning has problems such as too many turning points and slow convergence speed. By constructing a multi-factor heuristic function, optimizing the pheromone update method, setting adaptive weights, and designing a trajectory cleaning strategy, we achieve smoother the trajectories and accelerated convergence rate. To address the problem of target inaccessibility in the artificial potential field method, a relative distance is introduced to improve the repulsive force function, making the target accessible. Simulation results show that the improved algorithm can quickly escape from local minimum points and realize UAV trajectory planning in complex dynamic environments.

Key words: ant colony algorithm, artificial potential field, chain-like sub-target point, dynamic environment, route planning

中图分类号:

V 249

刘武君, 赵慧珍, 李龙跃, 王攀荣, 陈俊峰. 基于智能链式改进人工势场的无人机航迹规划[J]. 系统工程与电子技术, 2026, 48(10): 3622-3633.

Wujun Liu, Huizhen Zhao, Longyue Li, Panrong Wang, Junfeng Chen. Unmanned aerial vehicle trajectory planning based on intelligent chain-based modified artificial potential field[J]. Systems Engineering and Electronics, 2026, 48(10): 3622-3633.

图/表 22

图1

表1

图2

图3

图4

表2

图5

表3

图6

表4

表5

图7

表6

图8

表7

图9

图10

表8

图11

图12

图13

图14

参考文献 31

1	Fei C, Lu Z, Jiang W W. Heuristic optimization-based trajectory planning for UAV swarms in urban target strike operations[J]. Drones, 2024, 8 (12): 777. doi: 10.3390/drones8120777
2	Alam M M, Arafat M Y, Moh S, et al. Topology control algorithms in multi-unmanned aerial vehicle networks: an extensive survey[J]. Journal of Network and Computer Applications, 2022, 207, 103495. doi: 10.1016/j.jnca.2022.103495
3	Zhou C Y, Liu J Y, Qu K G, et al. Delay-aware UAV computation offloading and communication assistance for post-disaster rescue[J]. IEEE Trans. on Wireless Communications, 2024, 23 (12): 19110. doi: 10.1109/TWC.2024.3479709
4	Huang J B, Chen C M, Shen J J, et al. A self-adaptive neighborhood search A-star algorithm for mobile robots global path planning[J]. Computers and Electrical Engineering, 2025, 123, 110018. doi: 10.1016/j.compeleceng.2024.110018
5	Farid G, Cocuzza S, Younas T, et al. Modified A-star （A*） approach to plan the motion of a quadrotor UAV in three-dimensional obstacle-cluttered environment[J]. Applied Sciences, 2022, 12 (12): 5791. doi: 10.3390/app12125791
6	Gutierrez-martinez M A, Rojo-rodriguez E G, Cabriales-ramirez L E, et al. Genetic algorithm-based path planning of quadrotor UAVs on a 3D environment[J]. The Aeronautical Journal, 2025, 129 (1334): 902. doi: 10.1017/aer.2024.132
7	Yang Y, Fu Y J, Lu D Y, et al. Three-dimensional unmanned aerial vehicle trajectory planning based on the improved whale optimization algorithm[J]. Symmetry, 2024, 16 (12): 1561. doi: 10.3390/sym16121561
8	Xiang F T, Chen K X, Su J M, et al. Penetration planning and design method of unmanned aerial vehicle inspired by biological swarm intelligence algorithm[J]. Wireless Communications and Mobile Computing, 2021, 2021 (1): 4312592. doi: 10.1155/2021/4312592
9	Xu C, Xu Z B, Xia M Y. Obstacle avoidance in a three-dimensional dynamic environment based on fuzzy dynamic windows[J]. Applied Sciences, 2021, 11 (2): 504. doi: 10.3390/app11020504
10	Heidari H, Saska M. Collision-free trajectory planning of multi-rotor UAVs in a wind condition based on modified potential field[J]. Mechanism and Machine Theory, 2021, 156, 104140. doi: 10.1016/j.mechmachtheory.2020.104140
11	Shao M Z, Liu X, Xiao C S, et al. Research on UAV trajectory planning algorithm based on adaptive potential Field[J]. Drones, 2025, 9 (2): 79. doi: 10.3390/drones9020079
12	Kelner J M, Burzynski W, Stecz W. Modeling UAV swarm flight trajectories using rapidly-exploring random tree algorithm[J]. Journal of King Saud University-Computer and Information Sciences, 2024, 36 (1): 101909. doi: 10.1016/j.jksuci.2023.101909
13	Gómez A C, Zamarreño S M, Pérez M F, et al. Path planning for unmanned aerial vehicles in complex environments[J]. Drones, 2024, 8 (7): 288. doi: 10.3390/drones8070288
14	韩尧, 李少华. 基于改进人工势场法的无人机航迹规划[J]. 系统工程与电子技术, 2021, 43 (11): 3305- 3311.
15	Hao G Q, Lv Q, Huang Z, et al. UAV path planning based on improved artificial potential field method[J]. Aerospace, 2023, 10 (6): 562. doi: 10.3390/aerospace10060562
16	王庆禄, 吴冯国, 郑成辰, 等. 基于优化人工势场法的无人机航迹规划[J]. 系统工程与电子技术, 2023, 45 (5): 1461.
17	Goricanec J, Milas A, Markovic L, et al. Collision-free trajectory following with augmented artificial potential field using UAVs[J]. IEEE Access, 2023, 11, 83492. doi: 10.1109/ACCESS.2023.3303109
18	Ren C X, Fu F F, Yin C C, et al. Improved artificial potential field method based on robot local path information[J]. International Journal of Advanced Robotic Systems, 2024, 21(5). DOI: 10.1177/17298806241278172.
19	Liu J L, Yan Y H, Yang Y H, et al. An improved artificial potential field UAV path planning algorithm guided by RRT under environment-aware modeling: theory and simulation[J]. IEEE Access, 2024, 12, 12080. doi: 10.1109/ACCESS.2024.3355275
20	Sun M X, Xiao X T, Luan T T, et al. The path planning algorithm for UUV based on the fusion of grid obstacles of artificial potential field[J]. Ocean Engineering, 2024, 306, 118043. doi: 10.1016/j.oceaneng.2024.118043
21	Shan D R, Zhang S S, Wang X F, et al. Path-planning strategy: adaptive ant colony optimization combined with an enhanced dynamic window approach[J]. Electronics, 2024, 13 (5): 825. doi: 10.3390/electronics13050825
22	余婧, 吴晓军, 蒋安林, 等. 基于多精度规划窗口的无人机航迹规划方法研究[J]. 系统工程与电子技术, 2024, 46 (5): 1767.
23	Nie J, Xie W Q, Zhang H, et al. Research on optimal vehicle path algorithm based on improved ant colony algorithm[C]// SPIE International Conference on Optics, Electronics, and Communication Engineering, 2024: 604.
24	时维国, 宁宁, 宋存利, 等. 基于蚁群算法与人工势场法的移动机器人路径规划[J]. 农业机械学报, 2023, 54 (12): 407.
25	Wang S C, Zhang Z A, Huang X G. Research on path planning based on improved ant colony algorithm[C]// SPIE Third International Conference on Artificial Intelligence and Computer Engineering, 2023: 1402.
26	Tian Y, Zhang J, Wang Q, et al. Application of hybrid algorithm based on ant colony optimization and sparrow search in UAV path planning[J]. International Journal of Computational Intelligence Systems, 2024, 17 (1): 286. doi: 10.1007/s44196-024-00652-z
27	Wu J K, Luo Y, Zhang X F. Path planning of mobile robot based on ant colony algorithm-improved genetic algorithm[C]// SPIE Conference on Optical Metrology and Inspection for Industrial Applications XI, 2024: 311.
28	Ma J W, Ma X Y, Zang S F. Multidestination path planning based on ant colony decision and rolling control[J]. IEEE Trans. on Aerospace and Electronic Systems, 2024, 60 (6): 8667. doi: 10.1109/TAES.2024.3434777
29	Yang F, Fang X, Gao F, et al. Obstacle avoidance path planning for UAV based on improved RRT algorithm[J]. Discrete Dynamics in Nature and Society, 2022, 2022 (1): 4544499.
30	Feng K, He X Y, Wang M L, et al. Path optimization of agricultural robot based on immune ant colony: B-spline interpolation algorithm[J]. Mathematical Problems in Engineering, 2022, 2022 (1): 2585910.
31	Yang L W, Fu L X, Li P, et al. An effective dynamic path planning approach for mobile robots based on ant colony fusion dynamic windows[J]. Machines, 2022, 10 (1): 50. doi: 10.3390/machines10010050

类型	对算法产生的影响
$ \alpha $	$ \alpha $越大，随机搜索性减小，蚂蚁越倾向于选择之前走过的航迹，收敛速度快
$ \alpha $	$ \alpha $越小，更加注重全局搜索，随机性增强，增加可选航迹，收敛速度慢
$ \beta $	$ \beta $越大，启发函数作用增强，蚂蚁越倾向于选择局部最优航迹，陷入局部最优
$ \beta $	$ \beta $过小，蚂蚁会陷入单纯随机搜索，收敛速度过慢，难以找到最优解

参数	数值
蚂蚁数量$ m $	50
最大迭代次数$ {N_{\max }} $	100
信息素权重最小值$ {\alpha _{\min }} $	1
信息素权重最大值$ {\alpha _{\max }} $	4
启发函数权重最小值$ {\beta _{\min }} $	3
启发函数权重最大值$ {\beta _{\max }} $	8
信息素挥发系数$ \rho $	0.7
迭代界限量$ T $	30
信息素常量$ Q $	100
平滑因子$ \mu $	10
归一化距离常数$ f $	0.01
初始化信息素常数$ C $	0.01
归一化距离权重$ {\omega _1} $	0.8
航迹平滑度权重$ {\omega _2} $	0.2

算法	最优航迹长度/m	迭代次数	转弯次数
本文算法	28.1	6	5
传统蚁群算法	29.8	42	12
文献[24]改进蚁群算法	29.2	23	10

算法	最优航迹长度/m	迭代次数	转弯次数
本文算法	29.3	10	8
传统蚁群算法	32.3	30	16
文献[24]改进蚁群算法	31.2	25	13

参数	数值
引力系数$ {k_{{\mathrm{att}}}} $	5
斥力系数$ {k_{{\mathrm{rep}}}} $	15
斥力作用范围$ {d_0} $/m	1.5
步长$ L $/m	0.1
起点位置$ {X_0} $	（1,1）
终点位置$ {X_{{g}}} $	（18,19）