Saved in:
Bibliographic Details
Main Authors: Cai, Yeyue, Mo, Jianhua, Tao, Meixia
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.11391
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913044213268480
author Cai, Yeyue
Mo, Jianhua
Tao, Meixia
author_facet Cai, Yeyue
Mo, Jianhua
Tao, Meixia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11391
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SPOT: Single-Shot Positioning via Trainable Near-Field Rainbow Beamforming
Cai, Yeyue
Mo, Jianhua
Tao, Meixia
Machine Learning
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.
title SPOT: Single-Shot Positioning via Trainable Near-Field Rainbow Beamforming
topic Machine Learning
url https://arxiv.org/abs/2511.11391