Robust Design of Machine Learning based GNSS NLOS Detector with Multi-Frequency Features

Abstract

The robust detection of non-line-of-sight (NLOS) signals is of vital importance for land-based and close-to-land safe navigation applications. Their reception and use without adapted mitigation may induce unacceptable inaccuracy and loss of safety. Due to the complex signal conditions in urban environments, the use of machine learning or artificial intelligence techniques and algorithms have recently shown as potential tools to classify GNSS LOS/NLOS signals. The design of machine learning algorithms with GNSS features is an emerging approach that must however, be tackled carefully to avoid biased estimation results and guarantee generalized algorithms for different scenarios, receivers, antennas and their specific installations and configurations. This work has provided new options to guarantee a proper generalization of trained algorithms by means of a pre-normalization of features with models extracted in open-sky (nominal) scenarios. The second main contribution focused on designing a branched (or parallel) machine learning process to handle the intermittent presence of GNSS features in certain frequencies. This allows to exploit measurements in all available frequencies as compared to current approaches in the literature based only on single frequency features. The detection by means of logistic regression not only provides a binary LOS/NLOS decision, but also an associated probability which can be used in the future as a mean to weight specific measurements. The detection with the proposed branched logistic regression with pre-normalized multi-frequency features has shown better results than the state of the art, reaching more than 90% detection accuracy in the validation scenarios evaluated.