Abstract
In modern electronic warfare, synthetic aperture radar (SAR) imaging results remain suboptimal due to jamming. To enhance SAR's anti-jamming capability and gain initiative in this game-theoretic confrontation, this paper proposes a waveform-agile radar active anti-jamming method based on the dueling double Deep Q-Network (D3QN) algorithm. We model the radar anti-jamming process as a Markov decision process (MDP), enabling accurate and rapid generation of anti-jamming strategies across different jamming patterns through interactive learning. The simulation results verify the effectiveness of the proposed method.
| Original language | English |
|---|---|
| Journal | Asian and Pacific Conference on Synthetic Aperture Radar proceedings, APSAR |
| Issue number | 2025 |
| DOIs | |
| State | Published - 2025 |
| Externally published | Yes |
| Event | 9th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2025 - Matsue, Japan Duration: 5 Oct 2025 → 9 Oct 2025 |
Keywords
- Anti-Jamming
- Dueling Double Deep Q-Network
- Markov Decision Process
- Waveform Agile
Fingerprint
Dive into the research topics of 'Anti-Jamming Strategy Design Based on D3QN for Pulse Waveform Agile SAR'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver