Environment-RF-Based Positioning Using Machine Learning

Andres I. Vila Casado, Alon Krauthammer, Sebastian Olsen, and Esteban Valles

Peer Reviewed

Abstract:	This radio frequency (RF) based sensor offers a method for determining the location of a mobile unit (MU) in an environment where GNSS localization may not be suitable. This innovative localization sensor works by taking advantage of the uniqueness of environment RF signals in different locations. The sensor captures information from a wide portion of the RF spectrum and runs this data through a locator algorithm that produces the most likely location of the MU. This locator algorithm is created by a machine-learning classifier using previously recorded RF spectrum along with the truth positions of the recorder.
Published in:	Proceedings of the 31st International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2018) September 24 - 28, 2018 Hyatt Regency Miami Miami, Florida
Pages:	3327 - 3334
Cite this article:	Casado, Andres I. Vila, Krauthammer, Alon, Olsen, Sebastian, Valles, Esteban, "Environment-RF-Based Positioning Using Machine Learning," Proceedings of the 31st International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2018), Miami, Florida, September 2018, pp. 3327-3334. https://doi.org/10.33012/2018.16069
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In