基于混合策略多目标粒子群的异构无人机协同多任务分配

doi:10.3785/j.issn.1008-973X.2025.04.018

浙江大学学报(工学版)

2025, Vol. 59

Issue (4): 821-831 DOI: 10.3785/j.issn.1008-973X.2025.04.018

计算机技术与控制工程

基于混合策略多目标粒子群的异构无人机协同多任务分配

王昱1(

),马春荣2,赵明月1

1. 沈阳航空航天大学自动化学院，辽宁沈阳 110136
2. 航天神舟飞行器有限公司，天津 300450

Collaborative multi-task assignment of heterogeneous UAVs based on hybrid strategies based multi-objective particle swarm

Yu WANG1(

),Chunrong MA2,Mingyue ZHAO1

1. College of Automation, Shenyang Aerospace University, Shenyang 110136, China
2. Aerospace Shenzhou Aerial Vehicle Ltd., Tianjin 300450, China

全文: PDF(1201 KB) HTML

摘要：

针对多约束条件下的异构无人机协同多任务分配问题，构建综合考虑航程代价、时间代价、作战效能和多个约束的三目标优化模型，提出基于混合策略的多目标粒子群优化算法. 为了评价任务打击效率同时考虑死锁难题，在建模过程中提出弹药平均作用效能指标和等待时间计算. 为了解决传统粒子群算法易陷入局部最优的问题，确保始终搜索到满足约束的可行解，分别提出基于约束的粒子动态优选初始化策略、基于支配关系的优势个体选择策略和基于任务的小模块粒子更新及修正策略，有效提升算法在收敛精度及多样性方面的综合性能. 通过多场景下的仿真、消融实验验证模型及算法的有效性. 结果表明，相较对比算法，所提算法得到的解集更收敛、多样，分布更均匀，能够高效实现异构无人机的协同多任务分配.

关键词： 异构无人机; 任务分配; 多目标优化; 粒子群; 混合策略

Abstract:

Aiming at the problem of collaborative multi-task assignment of heterogeneous UAVs under multiple constraints, a three-objective optimization model was constructed, which considered the UAV flight distance cost, time cost, combat effectiveness and multiple constraints. A multi-objective particle swarm optimization algorithm based on hybrid strategies was proposed to solve the model. An average action efficiency index of ammunition was proposed to evaluate the task strike efficiency, and considering the possibility of deadlock during task execution, a calculation of waiting time was proposed in the process of modeling. In order to solve the problem that traditional particle swarm optimization falls into local optimality, and ensure that feasible solutions satisfying constraints are searched, a constraint-based particle dynamic optimal initialization strategy, a dominance relationship-based advantageous individual selection strategy, and a task-based small module particle update and correction strategy were proposed, respectively. The overall performance of the algorithm in terms of convergence accuracy and diversity was effectively improved by these strategies. The validity of the model and the algorithm was verified through multi-scenario simulation experiments and ablation experiments. Results show that the solution sets obtained by the proposed algorithm are more convergent, diverse and evenly distributed than the comparative algorithms, and the collaborative multi-task assignment of heterogeneous UAVs is efficiently realized by the proposed algorithm.

Key words: heterogeneous UAVs task assignment multi-objective optimization particle swarm hybrid strategy

收稿日期: 2024-02-21 出版日期: 2025-04-25

CLC:

TP 393

基金资助: 国家自然科学基金资助项目（61906125, 62373261）；辽宁省高校基本科研业务费项目（LJ232410143020, LJ212410143047）.

作者简介: 王昱（1980—），女，副教授，从事智能优化算法及其空战应用. orcid.org/0000-0002-8262-9317. E-mail：wangyu@sau.edu.cn

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	王昱
	马春荣
	赵明月

引用本文:

王昱,马春荣,赵明月. 基于混合策略多目标粒子群的异构无人机协同多任务分配[J]. 浙江大学学报(工学版), 2025, 59(4): 821-831.

Yu WANG,Chunrong MA,Mingyue ZHAO. Collaborative multi-task assignment of heterogeneous UAVs based on hybrid strategies based multi-objective particle swarm. Journal of ZheJiang University (Engineering Science), 2025, 59(4): 821-831.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2025.04.018 或 https://www.zjujournals.com/eng/CN/Y2025/V59/I4/821

表 1 任务分配模型参数

图 1 基于混合策略多目标粒子群优化算法流程图

图 2 粒子动态初始化编码示例

图 3 优势个体选择策略流程图

图 4 基于任务的小模块粒子学习示例

图 5 基于任务的小模块粒子变异示例

图 6 基于约束的粒子修正结果

实例	无人机	任务分配结果
6×3	$ u_{\text{O}}^{\text{1}} $	$ {T_1}\left( {{M_{\text{O}}}} \right) \to {T_1}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{O}}^{\text{2}} $	$ {T_2}\left( {{M_{\text{O}}}} \right) \to {T_2}\left( {{M_{\text{E}}}} \right) \to {T_3}\left( {{M_{\text{O}}}} \right) \to {T_3}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{A}}^{\text{1}} $	$ {T_1}\left( {{M_{\text{A}}}} \right) $
	$ u_{\text{A}}^{\text{2}} $	$ {T_2}\left( {{M_{\text{A}}}} \right) $
	$ u_{\text{A}}^{\text{3}} $	$ {T_3}\left( {{M_{\text{A}}}} \right) $
10×6	$ u_{\text{O}}^{\text{1}} $	$ {T_6}\left( {{M_{\text{O}}}} \right) \to {T_1}\left( {{M_{\text{O}}}} \right) \to {T_1}\left( {{M_{\text{E}}}} \right) \to {T_6}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{O}}^{\text{2}} $	$ {T_2}\left( {{M_{\text{O}}}} \right) \to {T_4}\left( {{M_{\text{O}}}} \right) \to {T_3}\left( {{M_{\text{O}}}} \right) \to {T_4}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{O}}^{\text{4}} $	$ {T_2}\left( {{M_{\text{O}}}} \right) \to {T_5}\left( {{M_{\text{O}}}} \right) \to {T_3}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{O}}^{\text{5}} $	$ {T_2}\left( {{M_{\text{O}}}} \right) \to {T_2}\left( {{M_{\text{E}}}} \right) \to {T_5}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{A}}^{\text{1}} $	$ {T_2}\left( {{M_{\text{A}}}} \right) $
	$ u_{\text{A}}^{\text{3}} $	$ \begin{gathered} {T_6}\left( {{M_{\text{A}}}} \right) \to {T_1}\left( {{M_{\text{A}}}} \right) \to {T_4}\left( {{M_{\text{A}}}} \right) \to {T_3}\left( {{M_{\text{A}}}} \right) \to {T_5}\left( {{M_{\text{A}}}} \right) \end{gathered} $
15×10	$ u_{\text{O}}^{\text{1}} $	$ \begin{gathered} {T_2}\left( {{M_{\text{O}}}} \right) \to {T_1}\left( {{M_{\text{O}}}} \right) \to {T_6}\left( {{M_{\text{O}}}} \right) \to {T_4}\left( {{M_{\text{E}}}} \right) \to \\ {T_1}\left( {{M_{\text{E}}}} \right) \to {T_6}\left( {{M_{\text{E}}}} \right) \\ \end{gathered} $
	$ u_{\text{O}}^{\text{2}} $	$ \begin{gathered} {T_{10}}\left( {{M_{\text{O}}}} \right) \to {T_3}\left( {{M_{\text{O}}}} \right) \to {T_8}\left( {{M_{\text{O}}}} \right) \to {T_9}\left( {{M_{\text{O}}}} \right) \to \\ {T_5}\left( {{M_{\text{E}}}} \right) \to {T_7}\left( {{M_{\text{E}}}} \right) \to {T_9}\left( {{M_{\text{E}}}} \right) \\ \end{gathered} $
	$ u_{\text{O}}^{\text{3}} $	$ {T_4}\left( {{M_{\text{O}}}} \right) \to {T_6}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{O}}^{\text{4}} $	$ {T_2}\left( {{M_{\text{O}}}} \right) \to {T_7}\left( {{M_{\text{O}}}} \right) \to {T_4}\left( {{M_{\text{O}}}} \right) \to {T_2}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{O}}^{\text{5}} $	$ {T_7}\left( {{M_{\text{O}}}} \right) \to {T_3}\left( {{M_{\text{E}}}} \right) \to {T_8}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{O}}^{\text{7}} $	$ {T_2}\left( {{M_{\text{O}}}} \right) \to {T_5}\left( {{M_{\text{O}}}} \right) $
	$ u_{\text{O}}^{\text{9}} $	$ {T_{10}}\left( {{M_{\text{E}}}} \right) $
	$ u_{\text{A}}^{\text{1}} $	$ {T_7}\left( {{M_{\text{A}}}} \right) $
	$ u_{\text{A}}^{\text{2}} $	$ {T_9}\left( {{M_{\text{A}}}} \right) $
	$ u_{\text{A}}^{\text{3}} $	$ {T_3}\left( {{M_{\text{A}}}} \right) \to {T_4}\left( {{M_{\text{A}}}} \right) \to {T_{10}}\left( {{M_{\text{A}}}} \right) \to {T_6}\left( {{M_{\text{A}}}} \right) $
	$ u_{\text{A}}^5 $	$ {T_5}\left( {{M_{\text{A}}}} \right) \to {T_1}\left( {{M_{\text{A}}}} \right) \to {T_{10}}\left( {{M_{\text{A}}}} \right) $
	$ u_{\text{A}}^6 $	$ {T_2}\left( {{M_{\text{A}}}} \right) \to {T_8}\left( {{M_{\text{A}}}} \right) $

表 2 无人机任务分配结果

图 7 实例10×6中的无人机任务分配结果

图 8 删除等待时间的任务分配结果

图 9 混合策略消融实验中不同算法的平均适应度

图 10 不同实例下5种粒子群优化算法的帕累托前沿

图 11 不同实例下5种粒子群优化算法的平均适应度

表 3 所提算法相较对比算法在3个实例中的平均适应度下降幅度

表 4 不同粒子群优化算法在3个实例中的性能对比

表 5 不同粒子群优化算法在3个实例中的运行时间

图 12 混合策略消融实验中不同算法的运行时间

1	PENG Q, WU H, XUE R Review of dynamic task allocation methods for UAV swarms oriented to ground targets[J]. Complex System Modeling and Simulation, 2021, 1 (3): 163- 175 doi: 10.23919/CSMS.2021.0022
2	MAYER M The new killer drones: understanding the strategic implications of next-generation unmanned combat aerial vehicles[J]. International Affairs, 2015, 91 (4): 765- 780 doi: 10.1111/1468-2346.12342
3	彭鹏菲, 龚雪, 姜俊, 等基于改进多维粒子群的多无人机任务分配方法[J]. 兵器装备工程学报, 2023, 44 (7): 227- 236 PENG Pengfei, GONG Xue, JIANG Jun, et al An improved multi-dimensional particle swarm-based approach to multi-UAV mission assignment[J]. Journal of Ordnance Equipment Engineering, 2023, 44 (7): 227- 236 doi: 10.11809/bqzbgcxb2023.07.030
4	GAO S, WU J, AI J Multi-UAV reconnaissance task allocation for heterogeneous targets using grouping ant colony optimization algorithm[J]. Soft Computing, 2021, 25 (10): 7155- 7167 doi: 10.1007/s00500-021-05675-8
5	郭继峰, 郑红星, 贾涛, 等异构无人系统协同作战关键技术综述[J]. 宇航学报, 2020, 41 (6): 686- 696 GUO Jifeng, ZHENG Hongxing, JIA Tao, et al Summary of key technologies for heterogeneous unmanned system cooperative operations[J]. Journal of Astronautics, 2020, 41 (6): 686- 696 doi: 10.3873/j.issn.1000-1328.2020.06.006
6	张瑞鹏, 冯彦翔, 杨宜康多无人机协同任务分配混合粒子群算法[J]. 航空学报, 2022, 43 (12): 412- 427 ZHANG Ruipeng, FENG Yanxiang, YANG Yikang Hybrid particle swarm algorithm for multi-UAV cooperative task allocation[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43 (12): 412- 427
7	王峰, 张衡, 韩孟臣, 等基于协同进化的混合变量多目标粒子群优化算法求解无人机协同多任务分配问题[J]. 计算机学报, 2021, 44 (10): 1967- 1983 WANG Feng, ZHANG Heng, HAN Mengchen, et al Co-evolution based mixed-variable multi-objective particle swarm optimization for UAV cooperative multi-task allocation problem[J]. Chinese Journal of Computers, 2021, 44 (10): 1967- 1983 doi: 10.11897/SP.J.1016.2021.01967
8	TANG X, LI X, YU R, et al Digital-twin-assisted task assignment in multi-UAV systems: a deep reinforcement learning approach[J]. IEEE Internet of Things Journal, 2023, 10 (17): 15362- 15375 doi: 10.1109/JIOT.2023.3263574
9	王峰, 黄子路, 韩孟臣, 等基于KnCMPSO算法的异构无人机协同多任务分配[J]. 自动化学报, 2023, 49 (2): 399- 414 WANG Feng, HUANG Zilu, HAN Mengchen, et al A knee point based coevolution multi-objective particle swarm optimization algorithm for heterogeneous UAV cooperative multi-task allocation[J]. Acta Automatica Sinica, 2023, 49 (2): 399- 414
10	王峰, 付青坡, 韩孟臣, 等 LeCMPSO算法求解异构无人机协同多任务重分配问题[J]. 控制理论与应用, 2024, 41 (6): 1009- 1017 WANG Feng, FU Qingpo, HAN Mengchen, et al Learning-guided coevolution multi-objective particle swarm optimization for heterogeneous UAV cooperative multi-task reallocation problem[J]. Control Theory and Applications, 2024, 41 (6): 1009- 1017
11	XIA T, HE J, ZOU X, et al. Research and application of a high-efficiency attack method based on statistical model for search and strike integrated UAV [C]// Proceedings of the 2nd International Conference on Education, Knowledge and Information Management . Xiamen: IEEE, 2021: 636–639.
12	YE F, CHEN J, TIAN Y, et al Cooperative task assignment of a heterogeneous multi-UAV system using an adaptive genetic algorithm[J]. Electronics, 2020, 9 (4): 687 doi: 10.3390/electronics9040687
13	LEMAIRE T, ALAMI R, LACROIX S. A distributed tasks allocation scheme in multi-UAV context [C]// Proceedings of the IEEE International Conference on Robotics and Automation . New Orleans: IEEE, 2004: 3622–3627.
14	CHEN Y, YANG D, YU J Multi-UAV task assignment with parameter and time-sensitive uncertainties using modified two-part wolf pack search algorithm[J]. IEEE Transactions on Aerospace and Electronic Systems, 2018, 54 (6): 2853- 2872 doi: 10.1109/TAES.2018.2831138
15	LIAO T, SOCHA K, MONTES DE OCA M A, et al Ant colony optimization for mixed-variable optimization problems[J]. IEEE Transactions on Evolutionary Computation, 2014, 18 (4): 503- 518 doi: 10.1109/TEVC.2013.2281531
16	MIRJALILI S, LEWIS A The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51- 67 doi: 10.1016/j.advengsoft.2016.01.008
17	MIRJALILI S, GANDOMI A H, MIRJALILI S Z, et al Salp swarm algorithm: a bio-inspired optimizer for engineering design problems[J]. Advances in Engineering Software, 2017, 114: 163- 191 doi: 10.1016/j.advengsoft.2017.07.002
18	王丹丹, 汤健, 夏恒, 等基于多目标PSO混合优化的虚拟样本生成[J]. 自动化学报, 2024, 50 (4): 790- 811 WANG Dandan, TANG Jian, XIA Heng, et al Virtual sample generation method based on hybrid optimization with multi-objective PSO[J]. Acta Automatica Sinica, 2024, 50 (4): 790- 811
19	HAN H, BAI X, HAN H, et al Self-adjusting multitask particle swarm optimization[J]. IEEE Transactions on Evolutionary Computation, 2022, 26 (1): 145- 158 doi: 10.1109/TEVC.2021.3098523
20	LI Y, DAI J. Research on UAV task assignment based on hybrid particle swarm algorithm [C]// Proceedings of the 4th International Conference on Intelligent Autonomous Systems . Wuhan: IEEE, 2021: 361–365.
21	WEI C, JI Z, CAI B Particle swarm optimization for cooperative multi-robot task allocation: a multi-objective approach[J]. IEEE Robotics and Automation Letters, 2020, 5 (2): 2530- 2537 doi: 10.1109/LRA.2020.2972894
22	王万良, 金雅文, 陈嘉诚, 等多角色多策略多目标粒子群优化算法[J]. 浙江大学学报: 工学版, 2022, 56 (3): 531- 541 WANG Wanliang, JIN Yawen, CHEN Jiacheng, et al Multi-objective particle swarm optimization algorithm with multi-role and multi-strategy[J]. Journal of Zhejiang University: Engineering Science, 2022, 56 (3): 531- 541
23	喻明让, 陈云, 张志刚离散粒子群优化算法求解多目标柔性作业车间调度问题[J]. 制造技术与机床, 2019, (1): 159- 165 YU Mingrang, CHEN Yun, ZHANG Zhigang Adiscrete version of particle swarm optimization for multi-objective flexible job-shop scheduling problems[J]. Manufacturing Technology and Machine Tool, 2019, (1): 159- 165
24	于洋, 谭学治, 殷聪, 等基于二进制混沌粒子群算法的认知决策引擎[J]. 哈尔滨工业大学学报, 2014, 46 (3): 8- 13 YU Yang, TAN Xuezhi, YIN Cong, et al Cognitive decision engine based on binary chaotic particle swarm optimization[J]. Journal of Harbin Institute of Technology, 2014, 46 (3): 8- 13 doi: 10.11918/hitxb20140302
25	TONG L, DU B, LIU R, et al An improved multiobjective discrete particle swarm optimization for hyperspectral endmember extraction[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57 (10): 7872- 7882 doi: 10.1109/TGRS.2019.2917001

[1]	张盈斐,胡小兵,周航,冯序增. 基于改进的NSGA-II算法的三维扇区自动划设[J]. 浙江大学学报(工学版), 2025, 59(2): 413-422.
[2]	李勇,王跃,柳富强,孙柏青,李恺如. 护工-机器人协作养老情境下的多任务分配框架[J]. 浙江大学学报(工学版), 2025, 59(2): 375-383.
[3]	余廷芳,张艮离,周嘉鹏,汤一村. 超临界CO₂布雷顿循环耦合有机闪蒸循环的性能分析及优化[J]. 浙江大学学报(工学版), 2025, 59(1): 130-140.
[4]	李若琼,翁源,李欣. 分数阶磁耦合谐振双向无线电能传输系统参数优化[J]. 浙江大学学报(工学版), 2025, 59(1): 141-151.
[5]	薛雅丽,李寒雁,欧阳权,崔闪,洪君. 战场环境下遗传黏菌算法的多机协同任务分配[J]. 浙江大学学报(工学版), 2024, 58(8): 1748-1756.
[6]	叶倩琳,王万良,王铮. 多目标粒子群优化算法及其应用研究综述[J]. 浙江大学学报(工学版), 2024, 58(6): 1107-1120.
[7]	门茂琛,赵睿,张金帅,王鹏,张庆. 基于改进模拟退火-粒子群的配电网分布式光伏承载力评估[J]. 浙江大学学报(工学版), 2024, 58(6): 1255-1265.
[8]	王骏骋,王法慧. 基于变权重PSO-Elman神经网络的路面附着系数估计[J]. 浙江大学学报(工学版), 2024, 58(3): 622-634.
[9]	詹燕,陈洁雅,江伟光,鲁建厦,汤洪涛,宋新禹,许丽丽,刘赛淼. 基于改进NSGA-Ⅱ的多目标车间物料配送方法[J]. 浙江大学学报(工学版), 2024, 58(12): 2510-2519.
[10]	汤雪扬,蔡小培,王伟华,常文浩,王启好. 基于粒子概率神经网络算法的钢轨波磨识别[J]. 浙江大学学报(工学版), 2023, 57(9): 1766-1774.
[11]	曹晓彦,于敏,周瑾,王运志. 可调旋转式流体阻尼器参数多目标优化设计[J]. 浙江大学学报(工学版), 2023, 57(7): 1439-1449.
[12]	常同立,傅万斌. 自对准人工膝关节的人机匹配设计[J]. 浙江大学学报(工学版), 2023, 57(4): 753-759.
[13]	余廷芳,宋凌. 超临界CO₂布雷顿循环余热回收系统性能分析与优化[J]. 浙江大学学报(工学版), 2023, 57(2): 404-414.
[14]	王万良,陈忠馗,吴菲,王铮,俞梦娇. 基于个体预测的动态多目标优化算法[J]. 浙江大学学报(工学版), 2023, 57(11): 2133-2146.
[15]	陶治同,陶建峰,覃程锦,刘成良. 基于时间冲击最优的TBM换刀机器人轨迹规划[J]. 浙江大学学报(工学版), 2023, 57(1): 1-9.

Viewed

Full text

Abstract

Cited

Shared

Discussed