基于改进MADDPG的组网雷达兼顾分辨率与抗扰决策方法
By constructing a continuous transmission and reception signal model for networked radars, and combining a multi-agent Markov decision process and a deep deterministic policy gradient algorithm, the problems of broadband frequency sweeping interference and adjacent frequency interference in multi-radar networking scenarios are solved, thereby improving high-resolution detection and anti-interference capabilities.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NORTHEASTERN UNIV AT QINHUANGDAO
- Filing Date
- 2026-04-23
- Publication Date
- 2026-07-17
AI Technical Summary
In multi-radar networking scenarios, there is still a lack of effective solutions for simultaneously addressing broadband frequency sweep interference avoidance and adjacent frequency interference reduction through collaborative decision-making in the continuous domain, while also meeting the requirements for high-resolution detection, in the absence of online communication interaction.
A continuous transmission and reception signal model of a networked radar system is constructed. Through a multi-agent partially observable Markov decision process, a composite reward function is designed. A multi-agent deep deterministic policy gradient algorithm based on a centralized training and distributed execution architecture is applied to realize continuous frequency band resource scheduling of the radar, overcome the problem of multi-agent credit allocation, and introduce a self-attention mechanism to adaptively extract time-varying mutual interference topology.
It enables radars to flexibly expand their operating bandwidth by utilizing fragmented spectrum gaps, ensuring high-range resolution detection. It significantly enhances the coordination and battlefield survivability of networked radars in strong electromagnetic suppression environments, and effectively resolves the strategic coupling and environmental non-stationarity among multiple agents.
Smart Images
Figure CN122085227B_ABST