EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Task Graph Generation for Heterogeneous UAV Swarms in Partially Observable Adversarial Environments

Wenxin Li, Yongxin Feng

Entropy · 18.06.2026 · 28 (6) · 708

DOI: 10.3390/e28060708 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 18.06.2026. Verfasst von Wenxin Li und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Shenyang Ligong University, Shenyang 110158, China. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Xingliao Talents Plan, the central government leads local science and technology development projects.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In partially observable adversarial environments, heterogeneous unmanned aerial vehicle (UAV) swarms must generate tasks online from noisy observations while respecting platform capabilities, consumable resources, and structural dependencies among tasks. This paper proposes a task graph generation method that converts local observations, target beliefs, and UAV resource states into executable task graphs with explicit resource semantics and inter-task relations. The method first constructs a sufficiently expressive candidate task graph in the belief and resource spaces. An offline search teacher then evaluates future trajectory particles, resource feasibility, and structural interaction values to produce supervision for node selection, marginal task value, and relation prediction. A relation-biased graph attention network learns to generate task graphs online, and a task manager further performs task filtering, dependency repair, conflict completion, and resource checking. Simulation results under complex observation pressure and unseen adversarial strategies show that the proposed method consistently improves structural generation quality and execution feasibility. Compared with Graphormer, it improves the task-graph utility, task-edge F1-score, and executable-graph ratio by 5.83%, 5.41%, and 2.68%, respectively, while reducing the infeasible-task ratio by 35.14%. These results indicate that combining an offline search teacher with resource-constrained graph modeling provides an effective front-end task organization mechanism for heterogeneous UAV swarm planning.

Schlagwörter

Stichwörter der Autor:innen

UAV swarmpartial observabilityresource constraintstask generationtask graph

Autor:innen und Institutionen

  • School of Information Science and Engineering, Shenyang Ligong University, Shenyang 110158, China.

Förderung

  • National Natural Science Foundation of China
  • Xingliao Talents Plan
  • the central government leads local science and technology development projects
  • Shenyang Natural Science Foundation

Zitieren

APA

Li, W., & Feng, Y. (2026). Task Graph Generation for Heterogeneous UAV Swarms in Partially Observable Adversarial Environments. Entropy, 28(6), 708. https://doi.org/10.3390/e28060708

Vancouver

Li W, Feng Y. Task Graph Generation for Heterogeneous UAV Swarms in Partially Observable Adversarial Environments. Entropy. 2026;28(6):708. doi:10.3390/e28060708

BibTeX
@article{Li2026,
  author = {Li, Wenxin and Feng, Yongxin},
  title = {Task Graph Generation for Heterogeneous UAV Swarms in Partially Observable Adversarial Environments},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {6},
  pages = {708},
  doi = {10.3390/e28060708}
}
Kostenlos starten →