RF-LEGO: Modularized Signal Processing-Deep Learning Co-Design for RF Sensing via Deep Unrolling
For wireless sensing researchers, this work provides a reusable and interpretable SP-DL co-design paradigm that outperforms both traditional and end-to-end deep learning approaches.
RF-LEGO introduces a modular framework that converts interpretable signal processing algorithms into trainable deep learning modules via deep unrolling, achieving significant performance gains over existing SP and DL baselines across Wi-Fi, mmWave, UWB, and 6G sensing tasks.
Wireless sensing, traditionally relying on signal processing (SP) techniques, has recently shifted toward data-driven deep learning (DL) to achieve performance breakthroughs. However, existing deep wireless sensing models are typically end-to-end and task-specific, lacking reusability and interpretability. We propose RF-LEGO, a modular co-design framework that transforms interpretable SP algorithms into trainable, physics-grounded DL modules through deep unrolling. By replacing hand-tuned parameters with learnable ones while preserving core processing structures and mathematical operators, RF-LEGO ensures modularity, cascadability, and structure-aligned interpretability. Specifically, we introduce three deep-unrolled modules for critical RF sensing tasks: frequency transform, spatial angle estimation, and signal detection. Extensive experiments using real-world data for Wi-Fi, millimeter-wave, UWB, and 6G sensing demonstrate that RF-LEGO significantly outperforms existing SP and DL baselines, both standalone and when integrated into multiple downstream tasks. RF-LEGO pioneers a novel SP-DL co-design paradigm for wireless sensing via deep unrolling, shedding light on efficient and interpretable deep wireless sensing solutions. Our code is available at https://github.com/aiot-lab/RF-LEGO.