SPOT: Single-Shot Positioning via Trainable Near-Field Rainbow Beamforming

TL;DR

This paper introduces a deep learning approach for designing phase-time array beams and estimating user positions, significantly reducing overhead and improving localization accuracy in wideband sensing.

Contribution

It presents a novel end-to-end trainable scheme that jointly optimizes rainbow beamforming and position estimation using a lightweight neural network.

Findings

Reduces localization overhead by an order of magnitude.

Achieves lower two-dimensional positioning error than existing methods.

Uses trainable PS and TTD coefficients for task-oriented beam synthesis.

Abstract

Phase-time arrays, which integrate phase shifters (PSs) and true-time delays (TTDs), have emerged as a cost-effective architecture for generating frequency-dependent rainbow beams in wideband sensing and localization. This paper proposes an end-to-end deep learning-based scheme that simultaneously designs the rainbow beams and estimates user positions. Treating the PS and TTD coefficients as trainable variables allows the network to synthesize task-oriented beams that maximize localization accuracy. A lightweight fully connected module then recovers the user's angle-range coordinates from its feedback of the maximum quantized received power and its corresponding subcarrier index after a single downlink transmission. Compared with existing analytical and learning-based schemes, the proposed method reduces overhead by an order of magnitude and delivers consistently lower two-dimensional positioning error.