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

• Published in: Scientific reports Vol. 15; no. 1; pp. 21637 - 18
• Main Authors: Ren, Meilin, Wei, Junyu, Qin, Jiangyi, Guo, Xiaojun, Wang, Haowen, Li, Shiqi
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.07.2025; Nature Portfolio
• Subjects: 639/166/984; 639/166/987; Attention mechanism; Humanities and Social Sciences; LSTM; multidisciplinary; NLOS; Pseudo-observation; Science; Science (multidisciplinary); UWB/INS integrated navigation system; UWB/INS integrated navigation system; Attention mechanism; LSTM; Pseudo-observation; NLOS

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 maintai...