Self-Supervised Deep Location and Ranging Error Correction for UWB Localization

Abstract

In this paper, we propose a self-supervised deep network that mainly applies location and ranging error corrections to a classical UWB localization approach to improve its accuracy. The core of this method is the self-supervised learning strategy which removes the requirement for ground-truth in the training process, and thus reduces the training cost of the method. To this end, we first use an existing classical UWB localization approach to provide an initial tag location, and then build a deep location and ranging error correction (DLRC) network to jointly estimate the tag position corrections and distance corrections. The self-supervised training strategy is built based on these regressed corrections and the initial tag position as well as the fixed anchor positions and raw ranging measurements, through the topological structure of the UWB sensors. Finally, the initial tag location can be corrected by the trained DLRC network. For this proposed method, it makes use of high-level representations of the UWB measurements by the deep network, while the geometric information important for UWB localization is also considered though the self-training strategy and the classical approach. Therefore, it can effectively improve the localization performance compared to the stat-of-the-art classical approach. This improvement is also verified by conducting real-world experiments.