Abstract
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.
Funding Information
  • National Key Research and Development Program of China (2022YFC3006104)
  • National Natural Science Foundation of China (62271285)
  • Tsinghua University-Meituan Joint Institute for Digital Life

This publication has 9 references indexed in Scilit: