Experimental researches on an UWB NLOS identification method based on machine learning

Non line of sight (NLOS) error identification and mitigation is of great importance in ultra wideband (UWB) ranging and localization. Based on the features extracted from the received waveform in practical experiments, a machine learning method is proposed for UWB NLOS identification in this paper. Corresponding NLOS error mitigation method is also given based on the identification results. Compared with the traditional NLOS identification methods, the proposed method is able to achieve better results with less a priori knowledge, which makes it practical in universal applications.