Fast Direct Localization for Millimeter Wave MIMO Systems via Deep ADMM Unfolding

TL;DR

This paper introduces a deep unfolding neural network based on ADMM to achieve fast, accurate, and computationally efficient direct localization in millimeter-wave MIMO systems, outperforming traditional methods.

Contribution

It formulates direct localization as a sparse recovery problem and develops a deep ADMM unfolding network with a position refinement algorithm for improved performance.

Findings

DAUN outperforms baseline solvers in accuracy

DAUN achieves faster convergence

DAUN significantly reduces computational complexity

Abstract

Massive arrays deployed in millimeter-wave systems enable high angular resolution performance, which in turn facilitates sub-meter localization services. Albeit suboptimal, up to now the most popular localization approach has been based on a so-called two-step procedure, where triangulation is applied upon aggregation of the angle-of-arrival (AoA) measurements from the collaborative base stations. This is mainly due to the prohibitive computational cost of the existing direct localization approaches in large-scale systems. To address this issue, we propose a deep unfolding based fast direct localization solver. First, the direct localization is formulated as a joint $l_1$-$l_{2,1}$ norm sparse recovery problem, which is then solved by using alternating direction method of multipliers (ADMM). Next, we develop a deep ADMM unfolding network (DAUN) to learn the ADMM parameter settings from the training data and a position refinement algorithm is proposed for DAUN. Finally, simulation results showcase the superiority of the proposed DAUN over the baseline solvers in terms of better localization accuracy, faster convergence and significantly lower computational complexity.