GNSSmachine

Starting point / motivation

Machine Learning led to great advances and breakthroughs in a variety of different domains. However, it has hardly been used in applications concerning navigation and GNSS, a domain, which includes many challenges which could be tackled effectively using Machine Learning (ML)

Today, such challenges are mainly addressed using rule-based approaches which are hand-coded by developers and engineers. These approaches have the disadvantage of being tedious to implement and adapt and become more and more complex when adding new parameters. ML has the potential to significantly increase the performance of GNSS algorithms and realise solutions for future problems that are unthinkable as of today.

Contents and goals

In this project, concrete problems in the field of navigation and GNSS will be determined and tackled using ML approaches, in order to develop a strategy for coping with the current wave of technological advances imposed by ML.

Methods

As ML, especially in the form of neural networks, is considered the path to artificial intelligence, one can consider the application of related approaches in the GNSS domain as an introduction of intelligent algorithms.

We describe three problems that we aim to solve using machine learning techniques: Multipath classification, spoofing detection and learning of cost functions for off-road routing.

Expected results

The results will lead to an in-depth feasibility study that will allow to decide on a further strategy on machine learning.

Coordinator

OHB Digital Solutions GmbH

Project partner

DI Paul Savoie

OHB Digital Solutions GmbH
Rettenbacher Straße 22
A-8044 Graz
Web: www.ohb-digital.at