| Issue |
ITM Web Conf.
Volume 69, 2024
International Conference on Mobility, Artificial Intelligence and Health (MAIH2024)
|
|
|---|---|---|
| Article Number | 03005 | |
| Number of page(s) | 7 | |
| Section | Mobility | |
| DOI | https://doi.org/10.1051/itmconf/20246903005 | |
| Published online | 13 December 2024 | |
Towards artificial intelligence based rail driving assistance tool
1 LAMIH, UMR 8201 - CNRS
2 INSA Hauts-de-France, Valenciennes, France
3 Univ. Polytechnique Hauts-de-France, Valenciennes, France
4 Dalle Molle Institute for Artificial Intelligence, SUPSI, Lugano, Switzerland
* e-mail: jeanvalentin.merlevede@uphf.fr
** e-mail: simon.enjalbert@uphf.fr
*** e-mail: frederic.vanderhaegen@uphf.fr
**** e-mail: francesco.flammini@supsi.ch
This work proposes additional levels of progressive driver assistance expanding the traditional Grades Of Automation (GoA) in order to allow both higher level of automation and keeping the driver involved in driving task at the same time. The second contribution is the Digital Co-Driver which aims to bring the driver back in the train driving activity with the new GoA defined before, taking into account human involvement and driving skills. This framework is made up of several modules, each of which addresses a specific issue arising from the increased level of automation. The Driver State and Performance Monitoring Module monitors the driver’s involvement, situation awareness and performance. The Digital Adviser Module improves driver’s situational awareness, and the Digital Teacher Module improves his/her driving skills and knowledge of the system. Finally, the Safety Manager ensures the system’s compatibility with safety standards.
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.