Attention-Guided Deep Reinforcement Learning for Continuous UAV Penetration in Heterogeneous Radar Networks
Drones · 06.11.2026 · 10 (11) · 833
DOI: 10.3390/drones10110833 ↗Kurz gefasst
Fachartikel in der Zeitschrift Drones, online erschienen am 06.11.2026. Verfasst von Tao Hu und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Autonomous stealth navigation through modern Integrated Air Defense Systems requires Unmanned Aerial Vehicles (UAVs) to minimize radar detectability while maintaining efficient flight. This poses a severe continuous-control challenge under partial observability, as the dynamic radar cross-section (RCS) is highly coupled with the aircraft’s real-time attitude. In this paper, we formulate this task as a Partially Observable Markov Decision Process (POMDP) and propose an attention-guided deep reinforcement learning framework. Specifically, we design a cross-attention state encoder to adaptively process variable-length, localized radar warning signals, enabling dynamic threat prioritization. The control policy is optimized using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to generate high-precision continuous lateral maneuvers. Extensive simulations demonstrate that our proposed TD3-Att framework achieves improved convergence stability, higher average returns, and robust zero-shot generalization compared to DDPG and SAC baselines. Notably, the learned policy steers the aircraft along low-RCS heading/aspect angles, providing an effective continuous-control solution for navigating contested electromagnetic environments.
Zitieren
APA
Hu, T., Liu, J., Chen, T., Luo, X., & Li, R. (2026). Attention-Guided Deep Reinforcement Learning for Continuous UAV Penetration in Heterogeneous Radar Networks. Drones, 10(11), 833. https://doi.org/10.3390/drones10110833
Vancouver
Hu T, Liu J, Chen T, Luo X, Li R. Attention-Guided Deep Reinforcement Learning for Continuous UAV Penetration in Heterogeneous Radar Networks. Drones. 2026;10(11):833. doi:10.3390/drones10110833
BibTeX
@article{Hu2026,
author = {Hu, Tao and Liu, Junxian and Chen, Tao and Luo, Xueshan and Li, Ruozhe},
title = {Attention-Guided Deep Reinforcement Learning for Continuous UAV Penetration in Heterogeneous Radar Networks},
journal = {Drones},
year = {2026},
volume = {10},
number = {11},
pages = {833},
doi = {10.3390/drones10110833}
}
EUVIMED