Predictive Intelligence for a Rail Traffic Management System

Simon Roberts, Lukasz Bonenberg, Xiaolin Meng, Terry Moore, Chris Hill

Abstract:	As the demands on terrestrial transport systems increase, there is a growing need for greater efficiencies. More intelligent mobility and ultimately autonomous transport assets will deliver these efficiencies through the evolution of cooperative intelligent transport system (C-ITS) technology. Central to this evolution will be the capability to accurately and precisely position assets within their environment and relative to each other to predefined and regulated standards. The core of modern positioning and navigation methods are the global navigation satellite systems (GNSS) (e.g. GPS, Galileo, GLONASS and BeiDou). These systems rely on line of sight radio frequency signals, which are vulnerable to obstruction and/or interference (e.g. multipath and/or non-line of sight reception). As a result, the position accuracy is degraded and therefore GNSS would greatly benefit from a priori intelligence that predicts where and when obscuration or interference will occur. Similarly, a real time assessment of where and when GNSS signal reception will be restored and the location of the satellites in the sky will aid in restoring satellite lock. This paper describes a computer vision system that utilises 360o images to derive a priori intelligence to predict changes in the environment that may threaten position and navigation integrity.
Published in:	Proceedings of the 30th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2017) September 25 - 29, 2017 Oregon Convention Center Portland, Oregon
Pages:	2117 - 2125
Cite this article:	Roberts, Simon, Bonenberg, Lukasz, Meng, Xiaolin, Moore, Terry, Hill, Chris, "Predictive Intelligence for a Rail Traffic Management System," Proceedings of the 30th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2017), Portland, Oregon, September 2017, pp. 2117-2125. https://doi.org/10.33012/2017.15328
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In