elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

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

Garcia Crespillo, Omar and Ruiz-Sicilia, Juan Carlos and Kliman, Ana and Marais, Juliette (2023) Robust Design of Machine Learning based GNSS NLOS Detector with Multi-Frequency Features. Frontiers in Artificial Intelligence, 10. Frontiers Research Foundation. doi: 10.3389/frobt.2023.1171255. ISSN 2624-8212.

[img] PDF - Published version
14MB

Official URL: https://www.frontiersin.org/articles/10.3389/frobt.2023.1171255

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.

Item URL in elib:https://elib.dlr.de/196159/
Document Type:Article
Title:Robust Design of Machine Learning based GNSS NLOS Detector with Multi-Frequency Features
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Garcia Crespillo, OmarUNSPECIFIEDhttps://orcid.org/0000-0002-2598-7636UNSPECIFIED
Ruiz-Sicilia, Juan CarlosUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Kliman, AnaUNSPECIFIEDhttps://orcid.org/0009-0008-9683-6350139475571
Marais, JulietteUniversité Gustave EiffelUNSPECIFIEDUNSPECIFIED
Date:29 July 2023
Journal or Publication Title:Frontiers in Artificial Intelligence
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:10
DOI:10.3389/frobt.2023.1171255
Publisher:Frontiers Research Foundation
ISSN:2624-8212
Status:Published
Keywords:GNSS - Global Navigation Satellite System, NLOS (non-line-of-sight) propagation, machine learning - ML, urban enviroment, Local threats
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Communication, Navigation, Quantum Technology
DLR - Research area:Raumfahrt
DLR - Program:R KNQ - Communication, Navigation, Quantum Technology
DLR - Research theme (Project):R - GNSS Technologies and Services
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Communication and Navigation > Navigation
Deposited By: Garcia Crespillo, Omar
Deposited On:28 Jul 2023 14:36
Last Modified:04 Dec 2023 11:38

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.