Attention based LSTM framework for robust UWB and INS integration in NLOS environments

Abstract This paper proposes a novel UWB/INS integration framework that utilizes attention-based Long Short-Term Memory (LSTM) neural networks to address challenges related to UWB signal degradation during non-line-of-sight (NLOS) propagation. The network is adopted to generate pseudo measurements t...

Full description

Saved in:
Bibliographic Details
Main Authors: Meilin Ren, Junyu Wei, Jiangyi Qin, Xiaojun Guo, Haowen Wang, Shiqi Li
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05501-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238419241172992
author Meilin Ren
Junyu Wei
Jiangyi Qin
Xiaojun Guo
Haowen Wang
Shiqi Li
author_facet Meilin Ren
Junyu Wei
Jiangyi Qin
Xiaojun Guo
Haowen Wang
Shiqi Li
author_sort Meilin Ren
collection DOAJ
description Abstract This paper proposes a novel UWB/INS integration framework that utilizes attention-based Long Short-Term Memory (LSTM) neural networks to address challenges related to UWB signal degradation during non-line-of-sight (NLOS) propagation. The network is adopted to generate pseudo measurements to maintain Kalman filter measurement update during NLOS. LSTM networks are well-suited for modeling sequential data due to their ability to capture long-term dependencies, making them particularly effective in handling the temporal aspects of navigation data. By leveraging attention mechanisms, the proposed approach enhances temporal feature extraction and improves the accuracy of pseudo-UWB observations generation. Extensive experiments demonstrate that the attention-LSTM model significantly reduces positioning errors under both loosely and tightly coupled configurations in NLOS scenarios. This hybrid fusion of model-based and learning-based techniques ensures robust and precise UWB/INS localization.
format Article
id doaj-art-dcb3bb6f97154e96a109c9768b9d94f8
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-dcb3bb6f97154e96a109c9768b9d94f82025-08-20T04:01:36ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-05501-3Attention based LSTM framework for robust UWB and INS integration in NLOS environmentsMeilin Ren0Junyu Wei1Jiangyi Qin2Xiaojun Guo3Haowen Wang4Shiqi Li5CATARC Automotive Test Center (Tianjin) Co., Ltd.College of Intelligence Science and Technoloy, National University of Defense TechnologyNational Innovation Institute of Defense Technology, Academy of Military ScienceCollege of Intelligence Science and Technoloy, National University of Defense TechnologyCollege of Intelligence Science and Technoloy, National University of Defense TechnologyCollege of Intelligence Science and Technoloy, National University of Defense TechnologyAbstract This paper proposes a novel UWB/INS integration framework that utilizes attention-based Long Short-Term Memory (LSTM) neural networks to address challenges related to UWB signal degradation during non-line-of-sight (NLOS) propagation. The network is adopted to generate pseudo measurements to maintain Kalman filter measurement update during NLOS. LSTM networks are well-suited for modeling sequential data due to their ability to capture long-term dependencies, making them particularly effective in handling the temporal aspects of navigation data. By leveraging attention mechanisms, the proposed approach enhances temporal feature extraction and improves the accuracy of pseudo-UWB observations generation. Extensive experiments demonstrate that the attention-LSTM model significantly reduces positioning errors under both loosely and tightly coupled configurations in NLOS scenarios. This hybrid fusion of model-based and learning-based techniques ensures robust and precise UWB/INS localization.https://doi.org/10.1038/s41598-025-05501-3UWB/INS integrated navigation systemNLOSAttention mechanismLSTMPseudo-observation
spellingShingle Meilin Ren
Junyu Wei
Jiangyi Qin
Xiaojun Guo
Haowen Wang
Shiqi Li
Attention based LSTM framework for robust UWB and INS integration in NLOS environments
Scientific Reports
UWB/INS integrated navigation system
NLOS
Attention mechanism
LSTM
Pseudo-observation
title Attention based LSTM framework for robust UWB and INS integration in NLOS environments
title_full Attention based LSTM framework for robust UWB and INS integration in NLOS environments
title_fullStr Attention based LSTM framework for robust UWB and INS integration in NLOS environments
title_full_unstemmed Attention based LSTM framework for robust UWB and INS integration in NLOS environments
title_short Attention based LSTM framework for robust UWB and INS integration in NLOS environments
title_sort attention based lstm framework for robust uwb and ins integration in nlos environments
topic UWB/INS integrated navigation system
NLOS
Attention mechanism
LSTM
Pseudo-observation
url https://doi.org/10.1038/s41598-025-05501-3
work_keys_str_mv AT meilinren attentionbasedlstmframeworkforrobustuwbandinsintegrationinnlosenvironments
AT junyuwei attentionbasedlstmframeworkforrobustuwbandinsintegrationinnlosenvironments
AT jiangyiqin attentionbasedlstmframeworkforrobustuwbandinsintegrationinnlosenvironments
AT xiaojunguo attentionbasedlstmframeworkforrobustuwbandinsintegrationinnlosenvironments
AT haowenwang attentionbasedlstmframeworkforrobustuwbandinsintegrationinnlosenvironments
AT shiqili attentionbasedlstmframeworkforrobustuwbandinsintegrationinnlosenvironments