LAUSR

Ultra-wideband (UWB) positioning performance is highly related to the accuracy of the coordinates of the fixed anchor nodes, which form the system infrastructure. The process of determining the position of the anchors is called calibration. In an anchor-based system, it is crucial for the fixed nodes to know their locations with the highest possible accuracy. However, in certain situations, it is almost impossible to perform the calibration manually, e.g., during emergency interventions. Moreover, calibration is always delicate and time-consuming. We designed an effortless and accurate self-calibration algorithm that does not require any manual intervention to precisely pinpoint the position of the anchors. This paper presents an innovative algorithm that combines machine learning and exploits the time resolution capabilities of UWB with adaptive physical settings to enable the automatic calibration of the fixed anchor nodes, even in realistic NLOS (non-line-of-sight) conditions. The self-calibration algorithm combines iterative gradient descent to pinpoint the positions of the anchors and uses error detection and correction from a convolutional neural network. Moreover, the algorithm can use a different set of settings for each anchor pair. This is done to ensure the most robust and accurate communication between nodes. Extensive measurements were carried out to allow anchors to estimate distances among each others. Distances were then combined and processed by the self-calibration algorithm. Experimental evaluation in two complex and large environments with many obstacles and reflections shows that accuracy reached by the algorithm is about 2.4 cm on average and 95th percentile is 5.7 cm, in best case. The results refer to the relative positions among the anchors. Results prove that in order to precisely calibrate the anchors nodes in an UWB positioning system, high correctness can be obtained by combining the accuracy of UWB together with deep learning and adaptive PHY modulation schemes.