An Unsupervised Transfer Learning Method for UWB Ranging Error Mitigation

Zhihang Li

doi:10.1109/LCOMM.2023.3325288

An Unsupervised Transfer Learning Method for UWB Ranging Error Mitigation

2023-12-01

1

PRE

AI

DOI：10.1109/LCOMM.2023.3325288

原文链接

原文求助

摘要

En 中文

Distance estimation using ultra-wideband transmissions suffers from significant accuracy loss in non-line-of-sight propagation environments. Prevailing machine learning-based error mitigation algorithms are often environment- or device-dependent. This letter proposes an unsupervised transfer learning method based on domain adversarial training and adaptive encoder-decoder, which can retain the ranging accuracy when the environment or the device changes with low data collection workload. Experimental results show that the proposed scheme can achieve a nearly supervised-level error mitigation performance in cross-environment and cross-device applications.

Keyword:

Distance measurement

Training

Transfer learning

Feature extraction

Decoding

Adaptation models

Ultra wideband technology

Ultra-wideband

ranging error mitigation

machine learning

transfer learning

An Unsupervised Transfer Learning Method for UWB Ranging Error Mitigation

摘要

期刊

机构