EUVIMEDEUVIMED entdecken
Crossref

A Context-Separated and Semantic-Gated MAPPO Framework for Dynamic Task Assignment in UAV Swarms

Chen Qian, Zhuo Huang, Lei Su, Ke Li, Keyu Zhang, Siyu Zhang

IEEE Internet of Things Journal · 2026-11 · 13 (22) · 53555-53566

DOI: 10.1109/jiot.2026.3729378 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, 2026-11. Verfasst von Chen Qian und 5 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Joint Fund Key Project of the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamic task assignment in multi-unmanned aerial vehicle (UAV) swarms is a challenging problem due to partial observability, strongly coupled state information, and limited communication resources in complex environments. The existing multiagent reinforcement learning (MARL) methods often suffer from representation collapse when processing highly entangled observations, while communication-based coordination strategies may introduce excessive communication overhead and thus limit practical applicability. To address these issues, this article proposes a context-separated and semantic-gated multiagent proximal policy optimization (CSSG-MAPPO) framework for dynamic UAV task assignment. First, the problem is formulated as a partially observable Markov decision process (POMDP) to characterize the observation constraints encountered in realistic UAV swarm operations. Second, a context-separated representation (CSR) strategy is introduced to decompose observations into environment-oriented and agent-oriented components, which improves task-relevant feature extraction and alleviates representation collapse during training. Third, a semantic-gated communication (SGC) mechanism is designed to adaptively regulate interagent message passing, enabling UAVs to communicate only when necessary and thereby reducing redundant communication under bandwidth constraints. Extensive experiments are conducted to compare the proposed method with several representative algorithms. The results show that CSSG-MAPPO achieves faster convergence, higher cumulative rewards, and lower communication ratios than the compared methods. In addition, the ablation studies further verify that both the CSR strategy and the SGC mechanism make substantial contributions to training efficiency, communication efficiency, and overall task performance. These results demonstrate the effectiveness of the proposed framework for dynamic task assignment in resource-constrained UAV swarm systems.

Förderung

  • National Natural Science Foundation of China
  • Joint Fund Key Project of the National Natural Science Foundation of China

Zitieren

APA

Qian, C., Huang, Z., Su, L., Li, K., Zhang, K., & Zhang, S. (2026). A Context-Separated and Semantic-Gated MAPPO Framework for Dynamic Task Assignment in UAV Swarms. IEEE Internet of Things Journal, 13(22), 53555-53566. https://doi.org/10.1109/jiot.2026.3729378

Vancouver

Qian C, Huang Z, Su L, Li K, Zhang K, Zhang S. A Context-Separated and Semantic-Gated MAPPO Framework for Dynamic Task Assignment in UAV Swarms. IEEE Internet of Things Journal. 2026;13(22):53555-53566. doi:10.1109/jiot.2026.3729378

BibTeX
@article{Qian2026,
  author = {Qian, Chen and Huang, Zhuo and Su, Lei and Li, Ke and Zhang, Keyu and Zhang, Siyu},
  title = {A Context-Separated and Semantic-Gated MAPPO Framework for Dynamic Task Assignment in UAV Swarms},
  journal = {IEEE Internet of Things Journal},
  year = {2026},
  volume = {13},
  number = {22},
  pages = {53555--53566},
  doi = {10.1109/jiot.2026.3729378}
}
Kostenlos starten →