Towards Smarter Sensing: 2D Clutter Mitigation in RL-Driven Cognitive MIMO Radar

• DOI: 10.48550/arxiv.2502.04967
• Publication Date: 2025-02-07
• Authors: Adam Umra; Aya Mostafa Ahmed; Aydin Sezgin
• Keywords: Signal Processing (eess.SP); FOS: Computer and information sciences; Computer Science - Machine Learning; FOS: Electrical engineering, electronic engineering, information engineering; Electrical Engineering and Systems Science - Signal Processing; Machine Learning (cs.LG)

Motivated by the growing interest in integrated sensing and communication for 6th generation (6G) networks, this paper presents a cognitive Multiple-Input Multiple-Output (MIMO) radar system enhanced reinforcement learning (RL) robust multitarget detection dynamic environments. The employs planar array configuration adapts its transmitted waveforms beamforming patterns to optimize performance presence of unknown two-dimensional (2D) disturbances. A Wald-type detector is with SARSA-based RL algorithm, enabling learn adapt complex clutter environments modeled 2D autoregressive process. Simulation results demonstrate significant improvements probability compared omnidirectional methods, particularly low Signal-to-Noise Ratio (SNR) targets masked clutter.