Estimating Multipath Component Delays With Transformer Models

Multipath in radio propagation provides essential environmental information that is exploited for positioning or channel-simultaneous localization and mapping. This enables accurate and robust localization that requires less infrastructure than traditional methods. A key factor is the reliable and a...

Full description

Saved in:
Bibliographic Details
Main Authors: Jonathan Ott, Maximilian Stahlke, Tobias Feigl, Christopher Mutschler
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Indoor and Seamless Positioning and Navigation
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10584252/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850226636111216640
author Jonathan Ott
Maximilian Stahlke
Tobias Feigl
Christopher Mutschler
author_facet Jonathan Ott
Maximilian Stahlke
Tobias Feigl
Christopher Mutschler
author_sort Jonathan Ott
collection DOAJ
description Multipath in radio propagation provides essential environmental information that is exploited for positioning or channel-simultaneous localization and mapping. This enables accurate and robust localization that requires less infrastructure than traditional methods. A key factor is the reliable and accurate extraction of multipath components (MPCs). However, limited bandwidth and signal fading make it difficult to detect and determine the parameters of the individual signal components. In this article, we propose multipath delay estimation based on a transformer neural network. In contrast to the state of the art, we implicitly estimate the number of MPCs and achieve subsample accuracy without using computationally intensive super-resolution techniques. Our approach outperforms known methods in detection performance and accuracy at different bandwidths. Our ablation study shows exceptional results on simulated and real datasets and generalizes to unknown radio environments.
format Article
id doaj-art-92ca83e2e76e4c52b343957cb29edbc7
institution OA Journals
issn 2832-7322
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Indoor and Seamless Positioning and Navigation
spelling doaj-art-92ca83e2e76e4c52b343957cb29edbc72025-08-20T02:05:01ZengIEEEIEEE Journal of Indoor and Seamless Positioning and Navigation2832-73222024-01-01221922910.1109/JISPIN.2024.342290810584252Estimating Multipath Component Delays With Transformer ModelsJonathan Ott0https://orcid.org/0009-0006-4328-4228Maximilian Stahlke1https://orcid.org/0000-0002-3572-7707Tobias Feigl2https://orcid.org/0000-0002-3040-3543Christopher Mutschler3https://orcid.org/0000-0001-8108-0230Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Division Positioning and Networks, Nuremberg, GermanyFraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Division Positioning and Networks, Nuremberg, GermanyFraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Division Positioning and Networks, Nuremberg, GermanyFraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Division Positioning and Networks, Nuremberg, GermanyMultipath in radio propagation provides essential environmental information that is exploited for positioning or channel-simultaneous localization and mapping. This enables accurate and robust localization that requires less infrastructure than traditional methods. A key factor is the reliable and accurate extraction of multipath components (MPCs). However, limited bandwidth and signal fading make it difficult to detect and determine the parameters of the individual signal components. In this article, we propose multipath delay estimation based on a transformer neural network. In contrast to the state of the art, we implicitly estimate the number of MPCs and achieve subsample accuracy without using computationally intensive super-resolution techniques. Our approach outperforms known methods in detection performance and accuracy at different bandwidths. Our ablation study shows exceptional results on simulated and real datasets and generalizes to unknown radio environments.https://ieeexplore.ieee.org/document/10584252/5Gattentionmultipath (MP)radio localizationtransformer (TF)ultrawideband (UWB)
spellingShingle Jonathan Ott
Maximilian Stahlke
Tobias Feigl
Christopher Mutschler
Estimating Multipath Component Delays With Transformer Models
IEEE Journal of Indoor and Seamless Positioning and Navigation
5G
attention
multipath (MP)
radio localization
transformer (TF)
ultrawideband (UWB)
title Estimating Multipath Component Delays With Transformer Models
title_full Estimating Multipath Component Delays With Transformer Models
title_fullStr Estimating Multipath Component Delays With Transformer Models
title_full_unstemmed Estimating Multipath Component Delays With Transformer Models
title_short Estimating Multipath Component Delays With Transformer Models
title_sort estimating multipath component delays with transformer models
topic 5G
attention
multipath (MP)
radio localization
transformer (TF)
ultrawideband (UWB)
url https://ieeexplore.ieee.org/document/10584252/
work_keys_str_mv AT jonathanott estimatingmultipathcomponentdelayswithtransformermodels
AT maximilianstahlke estimatingmultipathcomponentdelayswithtransformermodels
AT tobiasfeigl estimatingmultipathcomponentdelayswithtransformermodels
AT christophermutschler estimatingmultipathcomponentdelayswithtransformermodels