App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 12

Graph neural network and hierarchical qmix-based method for task allocation in Heterogeneous unmanned swarms under strong constraints

Long Yingying
Zhao Tongzhou
Ming Anqi
Wang Chao
School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan Hubei 430205, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0112

Abstract

This study proposed a task allocation method that integrated a graph neural network (GNN) with hierarchical QMIX (monotonic value function factorisation) to address strongly coupled constraints, dynamic task arrivals, and delayed feedback in multi-stage task allocation for heterogeneous unmanned swarms in maritime search and rescue scenarios. The method used a heterogeneous graph to model dynamic relationships among equipment, tasks, and platforms. It generated macro-priority actions to express high-level scheduling intentions and employed constraint-aware decoding to produce executable allocation results that satisfied capability-matching, platform dependency, and safety requirements. The method also introduced a window-level reward mechanism to alleviate delayed feedback in multi-stage tasks. Experiments in a custom-built simulation environment with 85 heterogeneous unmanned units showed that the proposed method achieved a normalized comprehensive system cost of 0.10, a task completion time cost of 14.10, and a task completion rate of 0.98, outperforming all compared methods. Ablation experiments showed that removing hierarchical decoding, the graph encoder, and the window-level reward increased the comprehensive system cost to 1.07, 0.73, and 1.33, respectively. These results indicate that the proposed method improves the executability and overall scheduling performance of task allocation for heterogeneous unmanned swarms under strong constraints through the coordinated use of graph-based relational modeling, hierarchical decision-making, constraint-aware decoding, and window-level feedback.

Foundation Support

军委科技委某基金项目

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0112
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 12

Publish History

[2026-08-04] Accepted Paper

Cite This Article

龙盈盈, 赵彤洲, 明安琪, 等. 基于图神经网络与分层QMIX的强约束异构无人集群任务分配方法 [J]. 计算机应用研究, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0112. (Long Yingying, Zhao Tongzhou, Ming Anqi, et al. Graph neural network and hierarchical qmix-based method for task allocation in Heterogeneous unmanned swarms under strong constraints [J]. Application Research of Computers, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0112. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)