Framewise Optimized Range Gate Pull-Off Jamming Strategy via Action Masking Reinforcement Learning
IEEE Transactions on Aerospace and Electronic Systems · 2026 · 62 · 9797-9812
DOI: 10.1109/taes.2026.3680863 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2026. Verfasst von Yujie Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Range gate pull-off (RGPO) jamming is a critical electronic attack technique used to deceive radar tracking systems. However, traditional RGPO strategies often rely on fixed pull-off patterns, which are susceptible to recognition and suppression by modern adaptive radar counter-countermeasures. To address this limitation, this article proposes a framewise optimized pull-off (FOP) jamming strategy based on action masking reinforcement learning, named MaskFOP. The proposed method decomposes the jamming process into discrete frames and dynamically optimizes the pull-off increments in real time. Specifically, a sequential state representation method is proposed to capture temporal dynamics by leveraging historical pull-off information. An action masking mechanism is designed to constrain the action selection space, ensuring physical feasibility and temporal consistency. Furthermore, a weighted reward function is formulated to balance the pull-off success rate and pull-off distance. Experimental results demonstrate that MaskFOP significantly outperforms benchmark strategies in terms of both deception success rate and cumulative pull-off distance. The proposed framework provides a robust and adaptive solution for modern electronic warfare scenarios.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, Y., Huo, W., Zhou, X., Zhang, C., Huang, Y., Pei, J., & Zhang, Y. (2026). Framewise Optimized Range Gate Pull-Off Jamming Strategy via Action Masking Reinforcement Learning. IEEE Transactions on Aerospace and Electronic Systems, 62, 9797-9812. https://doi.org/10.1109/taes.2026.3680863
Vancouver
Zhang Y, Huo W, Zhou X, Zhang C, Huang Y, Pei J, et al. Framewise Optimized Range Gate Pull-Off Jamming Strategy via Action Masking Reinforcement Learning. IEEE Transactions on Aerospace and Electronic Systems. 2026;62:9797-9812. doi:10.1109/taes.2026.3680863
BibTeX
@article{Zhang2026,
author = {Zhang, Yujie and Huo, Weibo and Zhou, Xu and Zhang, Cui and Huang, Yulin and Pei, Jifang and Zhang, Yin},
title = {Framewise Optimized Range Gate Pull-Off Jamming Strategy via Action Masking Reinforcement Learning},
journal = {IEEE Transactions on Aerospace and Electronic Systems},
year = {2026},
volume = {62},
pages = {9797--9812},
doi = {10.1109/taes.2026.3680863}
}
EUVIMED