Reconfigurable Intelligent Surface Based RF Sensing: Design, Optimization, and Implementation

TLDR

RF sensing for human posture recognition is attractive for its pervasiveness, contact‑free observation, and privacy protection, yet conventional methods are limited by radio environments that restrict transmission channels, making high‑accuracy recognition dependent on optimizing RIS configuration. The study designs an RF sensing system for posture recognition using reconfigurable intelligent surfaces and formulates an optimization problem, decomposing it into two subproblems with proposed algorithms. The system actively customizes the environment via RISs to create favorable propagation and multiple transmission channels, and the developed algorithms are implemented and tested in practical experiments. Simulations and experiments confirm that the proposed RIS‑based system and its optimization algorithms significantly improve posture recognition accuracy compared to random or non‑configurable setups.

Abstract

Using radio-frequency (RF) sensing techniques for human posture recognition has attracted growing interest due to its advantages of pervasiveness, contact-free observation, and privacy protection. Conventional RF sensing techniques are constrained by their radio environments, which limit the number of transmission channels to carry multi-dimensional information about human postures. Instead of passively adapting to the environment, in this paper, we design an RF sensing system for posture recognition based on reconfigurable intelligent surfaces (RISs). The proposed system can actively customize the environments to provide desirable propagation properties and diverse transmission channels. However, achieving high recognition accuracy requires the optimization of RIS configuration, which is a challenging problem. To tackle this challenge, we formulate the optimization problem, decompose it into two subproblems, and propose algorithms to solve them. Based on the developed algorithms, we implement the system and carry out practical experiments. Both simulation and experimental results verify the effectiveness of the designed algorithms and system. Compared to the random configuration and non-configurable environment cases, the designed system can greatly improve the recognition accuracy.