Joint Detection Tracking via Fuzzy Reinforcement Learning and Collaborative Radar Sensors

Multiple radar sensors (MRSs) observe targets from various perspectives, and their emission waveform design and collaborative detection and tracking (DT) are critical challenges to enhancing system performance. Facing the complexities of target DT in cluttered environments, this work proposes a cognitive waveform optimization strategy for MRSs via fuzzy Q learning (FQL). Specifically, a distributed collaborative joint DT fusion framework is developed, integrating a joint detection tracker with an adaptive threshold and employing a covariance intersection fusion approach to enhance the accuracy and reliability of global state estimation. The proposed strategy employs closed-loop feedback to update both waveforms and parameters collaboratively to improve target DT accuracy, and self-changing fuzzy rules adapt to target and environment changes, which enhances the situational awareness of MRSs. The numerical results demonstrate that the proposed method outperforms existing benchmarks in terms of computational efficiency and DT accuracy, providing a prospective solution for cognitive perception in MRSs.