Black-Boxing GNSS Signals Post-Processing Through Machine Learning for Multi-Agent Collaborative Positioning of IoT Devices - Conference Paper

Aug 5, 2026

Upload by Oliver

Modern GNSS receivers are increasingly embedded in everyday electronics, and their use in urban environments has expanded with the growth of small-scale IoT devices. Limited GNSS signal power and changing surroundings make continuous signal tracking demanding, while demodulation of navigation data further increases receiver workload and energy consumption. Low-power IoT platforms also benefit from network connectivity, enabling collaborative multi-agent positioning, navigation, and timing without continuous operation of the embedded receiver. This preliminary study tests whether machine learning can improve IoT position estimation using shared delay-Doppler data and receiver positions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

I. Introduction

Biography

POLITECNICO DI TORINO Repository ISTITUZIONALE Black-Boxing GNSS Signals Post-Processing Through Machine Learning for Multi-Agent Collaborative Positioning of IoT Devices Original Black-Boxing GNSS Signals Post-Processing Through Machine Learning for Multi-Agent Collaborative Positioning of IoT Devices / Minetto, Alex; Jahier-Pagliari, Daniele; Rotunno, Angela. -ELETTRONICO. - (2024), pp. 589-603. (Intervento presentato al convegno 2024 International Technical Meeting of The Institute of Navigation tenutosi a Long Beach, California (USA) nel January 23-25, 2024) [10 .33012/2024 . 19566] . Availability: This version is available at: 11583/2987532 since: 2024-04-03T14:42:47Z Publisher: Institute of Navigation (ION) Published DOI:10.33012/2024.19566 Terms of use: This article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository Publisher copyright GENERICO--per es. Nature : semplice rinvio dal preprint/submitted, o postprint/AAM [ex default] The original publication is available at [https://www.ion.org/publications/abstract.cfm?articleID=19566 /](https://www.ion.org/publications/abstract.cfm?articleID=19566 /) [http://dx.doi.org/10.33012/2024.19566](http://dx.doi.org/10.33012/2024.19566) . (Article begins on next page) 07 November 2024 Black-Boxing GNSS Signals Post-Processing Through Machine Learning for Multi-Agent Collaborative Positioning of IoT Devices Alex Minetto 1 , Daniele Jahier-Pagliari 1 , Angela Rotunno 1 ,2 , 1 Politecnico di Torino Turin, Italy, 2Punch Torino S.p.A., Turin, Italy BIOGRAPHY Alex Minetto received the B.Sc., [and M.sc. degrees](and M.sc. degrees) in Telecommunications Engineering from Politecnico di Torino, Turin, [Italy and his Ph.D. degree](Italy and his Ph.D. degree) in Electrical, Electronics and Communications Engineering, in 2020. He joined the Department of Electronics and Telecommunications of Politecnico di Torino in 2021 as researcher and assistant professor. His current research interests cover navigation signal design and processing, advanced Bayesian estimation applied to Positioning and Navigation Technologies (PNT) and applied Global Navigation Satellite System (GNSS) to space weather and space PNT. Daniele Jahier-Pagliari received the M.Sc. and Ph.D. degrees in computer engineering from the Politecnico di Torino, Turin, Italy, in 2014 and 2018, respectively.,He is currently an Assistant Professor with the Politecnico di Torino. His research interests are in the computer-aided design and optimization of digital circuits and systems, with a particular focus on energy-efficiency aspects and on emerging applications, such as machine learning at the edge. Angela Rotunno was born in Salerno, Italy. She received the M.Sc. degree in mechanical engineering in 2010, and the M.Sc. in mechatronic engineering in 2023 from the Politecnico di Torino. Her research work has been focused on the use of machine learning techniques for collaborative positioning solutions. She is currently working as test automation engineer for Punch Torino, an engine development company. ABSTRACT Nowadays, GNSS (GNSS) receivers are embedded in a variety of electronics devices, and a growing number of users rely on them to track their position, velocity, and time. The density of Global Navigation Satellite System (GNSS) receiver has especially increased in urban areas with the advent of small-scaled IoT devices. Due to the limited GNSS signal power and the variability of the environment, continuous GNSS signal tracking may represent a demanding task for receivers, which, in addition, have to perform demodulation of the navigation message to provide the user with meaningful information. Furthremore, when operated by low-power platforms, such as Internet of Things (IoT) devices, the aforementioned tasks may quickly drain the battery. On the other hand, the low-power-consumption network connectivity host

FAQs

Why is continuous GNSS signal tracking challenging for IoT devices?

Limited GNSS signal power, environmental variability, and receiver dynamics make continuous tracking demanding. Demodulation requirements and low-power platform constraints can also drain battery quickly.

How does the study enable collaborative positioning without continuous receiver operation?

The approach uses network connectivity to support collaborative, multi-agent PNT methods. Shared multi-satellite delay-Doppler matrices and positions are used to estimate a reference IoT receiver position.

Which machine learning models are used and what performance improvement is reported?

The study employs XGBoost (gradient-boosted decision trees) and Keras (multi-layer perceptron). ML-based position estimation error is typically 10% to 20% lower than a simplistic arithmetic-average reference model.

Aug 5, 2026

Upload by Oliver