1. Learning-Enhanced Adaptive Robust GNSS Navigation in Challenging Environments
- Author
-
Yi Ding, Paul Chauchat, Gael Pages, Philippe Asseman, Département Electronique, Optronique et Signal (DEOS), Institut Supérieur de l'Aéronautique et de l'Espace (ISAE-SUPAERO), Airbus Operation S.A.S., Airbus [France], Institut d'Électronique et des Technologies du numéRique (IETR), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ), Airbus SAS and ANRT, France, Cifre [2019/1073], Airbus (FRANCE), Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE), and CentraleSupélec (FRANCE)
- Subjects
Control and Optimization ,GNSS ,Mechanical Engineering ,Biomedical Engineering ,Computer Science Applications ,Human-Computer Interaction ,Machine Learning ,[SPI]Engineering Sciences [physics] ,Artificial Intelligence ,Control and Systems Engineering ,machine learning for robot control ,Localization ,probability and statistical methods ,Traitement du signal et de l'image ,Computer Vision and Pattern Recognition ,Robust Statistics - Abstract
International audience; Global Navigation Satellite System (GNSS) is the widely used technology when it comes to outdoor positioning. But it has severe limitations with regard to safety-critical applications involving unmanned autonomous systems. Namely, the positioning performance degrades in harsh propagation environment such as urban canyons. In this letter we propose a new algorithm for GNSS navigation in challenging environments based on robust statistics. M-estimators showed promising results in this context, but are limited by some fixed hyper-parameters. Our main idea is to adapt this parameter, for the Huber cost function, to the current environment in a data-driven manner. Doing so, we also present a simple yet efficient way of learning with satellite data, whose number may vary over time. Focusing the learning problem on a single parameter enables to efficiently learn with a lightweight neural network. The generalization capability and the positioning performance of the proposed method are evaluated in multiple contexts scenarios (open-sky, trees, urban and urban canyon), with two distinct GNSS receivers, and in an airplane ground inspection scenario. The maximum positioning error is reduced by up to 68% with respect to M-estimators.
- Published
- 2022