Adaptive Not-direct-path Identification in UWB Localization

Abstract In specific ultra-wideband (UWB) localization scenarios, conventional non-line-of-sight (NLOS) identification algorithm cannot detect other not-direct-path conditions. We proposed an adaptive method based on machine learning and artificial neural networks. Compared to the division of data sets, we verified advantages set partitioning by method. The performance NLOS recognition using different methods in scenes is also analyzed, average accuracy scenarios can reach 92% or more.