STAGE: spatio-temporal attention graph-enhanced policy optimization for area defense in UAV swarm confrontations
Journal of King Saud University Computer and Information Sciences · 2026-07 · 38 (5)
DOI: 10.1007/s44443-026-00536-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 16.02.2026. Verfasst von Yunchen Su und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Defense Science and Technology Innovation project, the Basic Frontier Innovation Project at the Engineering University of PAP, Key project of National Social Science Foundation.
Abstract (Originalsprache)
Defending against adversarial unmanned aerial vehicle (UAV) swarms presents a critical challenge for modern security systems, requiring coordinated strategies under partial observability. Existing multi-agent reinforcement learning (MARL) and spatio-temporal graph neural networks (ST-GCN) methods typically treat agents as homogeneous nodes, failing to effectively model large-scale, dynamic spatio-temporal dependencies to support cooperative decision-making, and lacking semantic interpretation of adversarial tactics. To address this, we propose the Spatio-Temporal Attention Graph-Enhanced policy optimization (STAGE). Unlike ST-GCN that uses fixed or predefined graph structures, STAGE models the diverse swarm topology through a learnable dynamic adjacency matrix and a multi-hop neighborhood aggregation mechanism to capture dependencies at different ranges. Moreover, to overcome the black-box nature of existing adversarial analysis, we design a dual-path intent recognition framework, which concatenates cluster-level features from graph attention networks with computed tactical metric vectors, and trains a classifier for four types of swarm tactical intents, enabling explicit recognition of enemy intent by the defenders. The policy is optimized end-to-end within the MAPPO framework through a structured multi-objective reward function. Extensive experiments in multi-scale area defense scenarios demonstrate that STAGE outperforms state-of-the-art methods in task performance and tactical comprehension robustness.
Förderung
- National Defense Science and Technology Innovation project
- the Basic Frontier Innovation Project at the Engineering University of PAP
- Key project of National Social Science Foundation
- the Graduate Student Funding Priority Project
Zitieren
APA
Su, Y., Wu, Q., Jiang, L., Tong, T., & Tan, W. (2026). STAGE: spatio-temporal attention graph-enhanced policy optimization for area defense in UAV swarm confrontations. Journal of King Saud University Computer and Information Sciences, 38(5). https://doi.org/10.1007/s44443-026-00536-6
Vancouver
Su Y, Wu Q, Jiang L, Tong T, Tan W. STAGE: spatio-temporal attention graph-enhanced policy optimization for area defense in UAV swarm confrontations. Journal of King Saud University Computer and Information Sciences. 2026;38(5). doi:10.1007/s44443-026-00536-6
BibTeX
@article{Su2026,
author = {Su, Yunchen and Wu, Qiwu and Jiang, Lingzhi and Tong, Tao and Tan, Weicong},
title = {STAGE: spatio-temporal attention graph-enhanced policy optimization for area defense in UAV swarm confrontations},
journal = {Journal of King Saud University Computer and Information Sciences},
year = {2026},
volume = {38},
number = {5},
doi = {10.1007/s44443-026-00536-6}
}
EUVIMED