Beamformed Fingerprint Learning for Accurate Millimeter Wave Positioning

TL;DR

This paper proposes a deep learning-based system that leverages millimeter wave multipath reflections and beamforming patterns to accurately estimate device positions in urban outdoor environments, achieving errors below 10 meters.

Contribution

It introduces a novel method combining beamforming pattern codebooks and deep learning to extract positional information from multipath millimeter wave signals.

Findings

Achieves average positioning errors below 10 meters in simulations.

Effectively utilizes multipath reflections for positioning in non-line-of-sight scenarios.

Demonstrates potential for new millimeter wave positioning systems.

Abstract

With millimeter wave wireless communications, the resulting radiation reflects on most visible objects, creating rich multipath environments, namely in urban scenarios. The radiation captured by a listening device is thus shaped by the obstacles encountered, which carry latent information regarding their relative positions. In this paper, a system to convert the received millimeter wave radiation into the device's position is proposed, making use of the aforementioned hidden information. Using deep learning techniques and a pre-established codebook of beamforming patterns transmitted by a base station, the simulations show that average estimation errors below 10 meters are achievable in realistic outdoors scenarios that contain mostly non-line-of-sight positions, paving the way for new positioning systems.