A physics-informed generative model for passive radio-frequency sensing

TL;DR

This paper introduces a physics-informed generative neural network model, based on a Variational Auto-Encoder, to efficiently simulate electromagnetic body effects for passive RF sensing and localization, validated against classical models and real data.

Contribution

It presents a novel EM-informed VAE model that integrates physical diffraction laws, enabling faster passive RF sensing and localization compared to traditional EM models.

Findings

Model accurately reproduces classical EM diffraction results.

Validated on real RF measurement data.

Enables real-time passive RF sensing applications.

Abstract

Electromagnetic (EM) body models predict the impact of human presence and motions on the Radio-Frequency (RF) stray radiation received by wireless devices nearby. These wireless devices may be co-located members of a Wireless Local Area Network (WLAN) or even cellular devices connected with a Wide Area Network (WAN). Despite their accuracy, EM models are time-consuming methods which prevent their adoption in strict real-time computational imaging problems and Bayesian estimation, such as passive localization, RF tomography, and holography. Physics-informed Generative Neural Network (GNN) models have recently attracted a lot of attention thanks to their potential to reproduce a process by incorporating relevant physical laws and constraints. Thus, GNNs can be used to simulate/reconstruct missing samples, or learn physics-informed data distributions. The paper discusses a Variational Auto-Encoder (VAE) technique and its adaptations to incorporate a relevant EM body diffraction method with applications to passive RF sensing and localization/tracking. The proposed EM-informed generative model is verified against classical diffraction-based EM body tools and validated on real RF measurements. Applications are also introduced and discussed.