In this PhD position you will join the Department of Information and Computer Science of Utrecht University in the LTP Robust Rail Project on Responsible Decision Support for Efficient and Dynamic Railway Systems. This project is a collaboration between Utrecht University, NS (Dutch Railways, the main Dutch passenger rail operator), ProRail (the Dutch rail infra manager) and TU Delft. The main goal is to improve the planning of Railway hubs, consisting of station areas and service sites. As you will work on real-life research questions with high societal impact your results might actually be implemented in practice to improve public transport.

During your PhD you will mainly focus on research, for which you will have a large amount of freedom to select the topics that you like within the project. Next to your research project you will coach students, complete a personalised set of courses, and develop technical and conceptual skills. During the PhD you will learn to present, advertise your work, and communicate with media. Supplementary to your research, you have educational tasks. These tasks include co-supervision of BSc and MSc-students, supervision of practicals and lectures. Your supervisors will coach you on education such that your development on this aspect is fueled as much as possible.

Within the project, multiple subjects are at hand. When rolling stock is not needed, for example at night, then it is brought to service sites. Here the trains are parked and service tasks (cleaning, inspection, maintenance) are conducted. Service sites are dynamic environments in which many disturbances take place with respect to the arrival of the trains (delays, differences in composition) and the service work. Your challenge in this project is to deal with this by designing algorithms that can construct shunting plans that are resilient against small changes in the original input and that can repair an initial plan with a minimum number of changes. Similar plans should be produced in similar circumstances to increase the acceptance of the algorithms by human planners. Therefore, we aim to construct plans that serve as a blueprint for one of the `standard’ days, which are easily adjustable to accommodate for small changes. Finding such easily adjustable base plans is a further challenge. Furthermore, we want to extend the usage of these algorithms to deal with similar challenges that play a role in freight train planning in the Rotterdam harbour area. Finally, the train traffic on a hub interferes with (freight) traffic on the main lines, which requires synchronisation.

You will be part of the RAIL lab, which is one of the seventeen new ICAI labs. The RAIL lab consists of five PhD candidates, who collaborate on ensuring safe and reliable logistic operations and capacity planning that is trusted by human experts.

This lab is part of the 10-year LTP ROBUST programme “Trustworthy AI-based Systems for Sustainable Growth” consortium, which unites seventeen knowledge institutions, nineteen participating industry sponsors and fifteen civil-social organisations from across the Netherlands. You will gain valuable experience working with an industry partner, and will be able to tap into a wealth of networking, career development, and training opportunities in conjunction with ICAI, the Innovation Center for Artificial Intelligence at the University of Amsterdam.