Sparse Recovery with Attention: A Hybrid Data/Model Driven Solution for High Accuracy Position and Channel Tracking at mmWave

TL;DR

This paper introduces a hybrid data/model-driven approach combining sparse recovery and attention networks for high-precision vehicle positioning and channel tracking at mmWave frequencies, achieving sub-20cm accuracy.

Contribution

It presents a novel mmWave channel tracking algorithm using MOMP with reduced dictionaries and an attention network for refined position estimation, outperforming previous Bayesian filtering methods.

Findings

Position tracking error below 20 cm

Significant improvement over Bayesian filtering

Effective in realistic ray-tracing channel scenarios

Abstract

In this paper, we propose first a mmWave channel tracking algorithm based on multidimensional orthogonal matching pursuit algorithm (MOMP) using reduced sparsifying dictionaries, which exploits information from channel estimates in previous frames. Then, we present an algorithm to obtain the vehicle's initial location for the current frame by solving a system of geometric equations that leverage the estimated path parameters. Next, we design an attention network that analyzes the series of channel estimates, the vehicle's trajectory, and the initial estimate of the position associated with the current frame, to generate a refined, high accuracy position estimate. The proposed system is evaluated through numerical experiments using realistic mmWave channel series generated by ray-tracing. The experimental results show that our system provides a 2D position tracking error below 20 cm, significantly outperforming previous work based on Bayesian filtering.