A Probabilistic Learning Approach to UWB Ranging Error Mitigation

Abstract

Ultra-Wide Band (UWB) radio is capable of providing sufficient information for high accuracy localization. However, its actual performance is degraded due to the non-line-of-sight (NLOS) propagation. This paper introduces a probabilistic learning approach to mitigate the ranging error and yield uncertainties which correlate with the mitigation results. By combining variational inference with probabilistic neural networks, we propose a new probabilistic deep learning architecture, which can improve the accuracy significantly especially when the training data is limited. Results show that the proposed model can reduce the root mean square error (RMSE) of UWB ranging by 16%~56% compared with existing support vector machine approach in practical environment.