Failure Tolerant Phase-Only Indoor Positioning via Deep Learning

TL;DR

This paper introduces a deep learning-based phase-only indoor positioning method that is robust to antenna failures, significantly improving localization accuracy in practical scenarios compared to previous approaches.

Contribution

It proposes a novel DL approach leveraging the hyperbola intersection principle for phase-only positioning that is resilient to antenna impairments, advancing the state-of-the-art.

Findings

Achieves high-precision localization despite antenna failures

Outperforms previous phase-only positioning methods in accuracy

Demonstrates robustness through extensive numerical evaluations

Abstract

High-precision localization turns into a crucial added value and asset for next-generation wireless systems. Carrier phase positioning (CPP) enables sub-meter to centimeter-level accuracy and is gaining interest in 5G-Advanced standardization. While CPP typically complements time-of-arrival (ToA) measurements, recent literature has introduced a phase-only positioning approach in a distributed antenna/MIMO system context with minimal bandwidth requirements, using deep learning (DL) when operating under ideal hardware assumptions. In more practical scenarios, however, antenna failures can largely degrade the performance. In this paper, we address the challenging phase-only positioning task, and propose a new DL-based localization approach harnessing the so-called hyperbola intersection principle, clearly outperforming the previous methods. Additionally, we consider and propose a processing and learning mechanism that is robust to antenna element failures. Our results show that the proposed DL model achieves robust and accurate positioning despite antenna impairments, demonstrating the viability of data-driven, impairment-tolerant phase-only positioning mechanisms. Comprehensive set of numerical results demonstrates large improvements in localization accuracy against the prior art methods.