基于图注意力网络的无人机蜂群作战目标分配

朱政; 魏喜庆; 李瑞康; 宋申民

doi:10.12382/bgxb.2025.0421

您当前的位置：

首页 >

文章列表页 >

基于图注意力网络的无人机蜂群作战目标分配

更新时间：2026-04-24

- 基于图注意力网络的无人机蜂群作战目标分配
- Target Assignment for UAV Swarm Combat Based on Graph Attention Network
- 兵工学报 2026年47卷第1期页码：250421
- 作者机构：
  
  上海电机学院电子信息学院，上海 201306
  中电科技扬州宝军电子有限公司，江苏扬州 225003
  上海机电工程研究所，上海 201109
  哈尔滨工业大学航天学院，黑龙江哈尔滨 150001
- 作者简介：
  
  *通信作者邮箱：weixq@sdju.edu.cn
- 基金信息：
  
  国家自然科学基金项目(62273277)
- DOI：10.12382/bgxb.2025.0421
  中图分类号： V279+.2;TP181
- 收稿：2025-05-29，
  
  网络首发：2026-02-11，
  
  纸质出版：2026-01-31
- 稿件说明：
移动端阅览
朱政, 魏喜庆, 李瑞康, 等. 基于图注意力网络的无人机蜂群作战目标分配[J]. 兵工学报, 2026,47(1):250421.

ZHU Zheng, WEI Xiqing, LI Ruikang, et al. Target Assignment for UAV Swarm Combat Based on Graph Attention Network[J]. Acta Armamentarii, 2026, 47(1): 250421.
朱政, 魏喜庆, 李瑞康, 等. 基于图注意力网络的无人机蜂群作战目标分配[J]. 兵工学报, 2026,47(1):250421. DOI： 10.12382/bgxb.2025.0421.

ZHU Zheng, WEI Xiqing, LI Ruikang, et al. Target Assignment for UAV Swarm Combat Based on Graph Attention Network[J]. Acta Armamentarii, 2026, 47(1): 250421. DOI： 10.12382/bgxb.2025.0421.

摘要

近年来，随着无人机集群在智能化军事作战中的广泛应用，复杂动态环境下的蜂群目标分配问题成为军事运筹研究的重要方向。传统方法在面对大规模、实时的无人机蜂群目标分配问题时，常面临精确算法计算开销大和启发式方法解质量不足的矛盾。以最小化敌方目标剩余价值为目标，构建目标分配模型，将无人机蜂群与敌方目标建模为二分图节点，生成结构化训练数据。在此基础上设计并训练一种改进的图注意力网络，融合节点属性与边特征实现高效分配。仿真实验结果表明，新方法在解质量和求解效率方面均优于传统方法，具备良好的泛化能力，适用于大规模实时作战场景。

Abstract

In recent years

with the widespread deployment of unmanned aerial vehicle (UAV) swarm in intelligent military operations

the problem of target assignment for UAV swarms in complex and dynamic environments has become an important direction in military operations research. When the traditional methods are confronted with large-scale and real-time UAV swarm target-assignment problems

they often face a trade-off between the high computational cost of exact algorithms and the insufficient solution quality of heuristic approaches. This paper constructs a target-assignment model with the objective of minimizing the residual value of enemy targets

models the UAV swarm and enemy targets as nodes in a bipartite graph

and generates structured training data. On this basis

an improved graph attention network is designed and trained

which fuses the node attributes and the edge features to achieve efficient target assignment. Simulation experiments indicate that the proposed method outperforms the conventional methods in both solution quality and computational efficiency

exhibits good generalization ability

and is suitable for large-scale and real-time combat scenarios.

关键词

Keywords

references

TUNCER O, RPAN H A. Adaptive fuzzy based threat evaluation method for air and missile defense systems [J]. Information Sciences,2023:643:119191.

宋怡然，申超，李东兵.美国分布式低成本无人机集群研究进展[J].飞航导弹，2016（8）:17-22.

SONG Y R, SHEN C, LI D B.A review of the research on distributed, low-cost system for unmanned aerial vehicles（UAVs）swarm of the United States [J].Aerodynamic Missile Journal, 2016（8）:17-22.（in Chinese）

MANNE A S. A target-assignment problem [J]. Operations Research,1958,6（3）:346-351.

FLOOD M. Target-assignment model [C]∥Proceedings of the Princeton University Conference on Linear Programming. Princeton, NJ, US:Princeton University,1957.

LI J R, WU G H, WANG L. A comprehensive survey of weapon target assignment problem:model, algorithm, and application[J]. Engineering Applications of Artificial Intelligence,2024,137（Part B）:20.

MATLIN S. A review of the literature on the missile-allocation problem[J].Operations Research,1970,18（2）:334-373.

HOSEIN P A, ATHANS M. An asymptotic result for the multi-stage weapon-target allocation problem[C]∥ Proceedings of the 29th IEEE Conference on Decision and Control. New York, NY, US:IEEE,1990:240-245.

LLOYD S P, WITSENHAUSEN H S. Weapons allocation is NP-complete[C]∥Proceedings of 1986 Summer Computer Simulation Conference. Reno, NV, US: U. S. A. Simulation Councils, 1986:1054-1058.

AHNER D K, PARSON C R. Optimal multi-stage allocation of weapons to targets using adaptive dynamic programming [J]. Optimization Letters,2015,9（8）:1689-1701.

ANDERSEN A C, PAVLIKOV K, TOFFOLO T A M. Weapon-target assignment problem: exact and approximate solution algorithms[J]. Annals of Operations Research,2022,312（2）:581-606.

周玉虎，王桐，陈立伟，等.基于人工蜂群算法的大规模武器目标分配研究[J].哈尔滨工程大学学报，2024,45（6）:1187-1195.

ZHOU Y H, WANG T, CHEN L W, et al.Research on large-scale weapon-target allocation based on artificial bee colony algorithm [J].Journal of Harbin Engineering University, 2024, 45（6）:1187-1195.（in Chinese）

刘攀，徐胜利，张迪，等.基于粒子群优化的多导弹动态武器目标分配算法[J].南京航空航天大学学报，2023,55（1）:108-115.

LIU P, XU S L, ZHANG D, et al.Multi-missile dynamic weapon target assignment algorithm based on particle swarm optimization [J].Journal of Nanjing University of Aeronautics & Astronautics, 2023,55（1）:108-115.（in Chinese）

陈琪锋，邹子缘，李鹏，等.基于决策树搜索的空间飞行器集群对抗目标分配方法[J].航空学报，2022,43（增刊1）:726910.

CHEN Q F, ZOU Z Y, LI P, et al.Target assignment method for spacecraft swarms confrontation based on decision tree search [J].Acta Aeronautica et Astronautica Sinica, 2022, 43（S1）:726910.（in Chinese）

KLINE A, AHNERD, LUNDAY B J. Real-time heuristic algorithms for the static weapon target assignment problem[J]. Journal of Heuristics,2019,25（3）:377-397.

ARSLAN C, KARASAKAL O, KRCA M. Naval air defense planning problem:a novel formulation and heuristics[J]. Naval Research Logistics,2024,71（7）:145-169.

MERKULOV G, ICELAND E, MICHAELI S, et al. Reinforcement learning based decentralized weapon-target assignment and guidance[C]∥Proceedings of AIAA SciTech 2024 Forum. Orlando, FL, US:AIAA,2024:125-139.

OH S H, BYEON G W, CHO Y I, et al. Artificial intelligence in combat decision-making: weapon target assignment via reinforcement learning and graph neural networks [J]. IEEE Transactions on Cybernetics,2025:1-15.

KARASAKAL O, KARASAKAL E, SILAV A. A multi-objective approach for dynamic missile allocation using artificial neural networks for time sensitive decisions[J]. Soft Computing,2021, 25（15）:10153-10166.

GIBBONS D, LIM C C, SHI P. Deep learning for bipartite assignment problems [C]∥ Proceedings of 2019 IEEE International Conference on Systems, Man and Cybernetics. Bari, Italy:IEEE,2019:1-8.

BERTSEKAS D P, HOMER M L. Missile defense and interceptor allocation by neuro-dynamic programming[J]. IEEE Transactions on Systems Man & Cybernetics Part A Systems & Humans,2000, 30（1）:42-51.

SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks,2009, 20（1）:61-80.

KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks: arXiv:1609. 02907 [R]. Ithaca, NY, US:Cornell University,2016:1609. 02907.

VELIKOVI P, CUCURULL G, CASANOVA A, et al. Graph attention networks: arXiv: 1710. 10903 [R]. Ithaca, NY, US:Cornell University,2017:1710. 10903.

CHUNG K T, LEE C K M, TSANG Y P. Neural combinatorial optimization with reinforcement learning in industrial engineering:a survey[J].Artificial Intelligence Review,2025,58（5）:130.

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据