RF-LEGO: Modularized Signal Processing-Deep Learning Co-Design for RF Sensing via Deep Unrolling

2026-04-11

AI Summary

This work addresses the limited reusability and interpretability of existing end-to-end, task-specific deep learning models for RF sensing. The authors propose a deep unfolding–based co-design paradigm that transforms classical signal processing algorithms into structured, parameterized, physics-informed modules, enabling a modular and cascaded RF sensing framework. By integrating interpretable components—such as frequency transformation, spatial angle estimation, and signal detection—the proposed approach achieves substantial performance gains over both conventional signal processing methods and purely data-driven baselines across real-world datasets from Wi-Fi, millimeter-wave, UWB, and 6G systems. The framework demonstrates strong generalization across diverse downstream tasks while maintaining high performance, interpretability, and cross-task reusability.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

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.

Problem

• wireless sensing
• deep learning
• interpretability
• reusability
• signal processing

Innovation

• deep unrolling
• modular co-design
• physics-grounded deep learning
• RF sensing
• interpretable AI