"PhD Position Design and Control of Mixed Fixed-Flexible Transport Networks"

Would you like to work at the intersection of transportation, robotics and machine learning to design mixed fixed-flexible transport networks? The increase of public transport usage has clear potential in transforming our environment to be more liveable, sustainable and convenient. However, to ensure economic viability with off-peak times and relatively remote locations, while increasing the attractiveness to the users, we need innovative designs where fixed and flexible services support each other. This necessitates a multidisciplinary approach bringing together optimization, machine learning and behavioral modeling methodologies.

In the FlexMobility project we propose a holistic approach to design a public transport network that includes both traditional fixed lines and flexible on-demand services, while considering the underlying travel behaviour. In the future, these mixed transportation systems may include a fleet of autonomous cars, vans, and buses.

This PhD position within FlexMobility will focus on the underlying assignment and routing algorithms for real-time operation of the vehicle fleet and the multi-objective design of the mixed transportation network. Our key hypothesis is that it is possible to design a mixed network by simulating how to serve a given demand with an on-demand ridepooling service, tracking the vehicles’ routes, and allocating fixed lines wherever vehicles concentrated the most. For the implementation of the system, users will be allocated, in real time, to either the fixed lines or pooled on-demand vehicles. This requires efficient methods for large scale task assignment and routing leveraging combinatorial optimization and machine learning. To achieve a holistic system, the developed methods will be enhanced with behavioral representations researched by another PhD candidate in the project. The developed methods could be applicable across many multi-agent coordination domains, from mobility, to logistics and multi-robot systems.

In this work, we will consider two use cases: (1) a mobility network considering both fixed-line buses and on-demand vehicles, and (2) a network with water-taxis. For both use cases, there will be interaction with the project partners for generating/obtaining the needed data as well as for setting up realistic case studies.

The position is available with a flexible start date to be agreed upon. The PhD candidate will join the Autonomous Multi-Robots Lab at the Cognitive Robotics Department and will be supervised by both Javier Alonso-Mora and Bilge Atasoy. Thanks to that synergetic collaboration, the PhD candidate will be able to collaborate with various researchers working on robotics and on adaptive transport systems through methodologies of dynamic and predictive optimization, behavioral modeling and machine learning. There is vivid interaction within the group to foster collaboration both with scientific and social activities. As part of the PhD position, there will be opportunities to gain teaching experience in the relevant courses and/or supervising MSc students.

More information about our research group can be found at: https://autonomousrobots.nl/.

We are looking for a candidate with operations research, discrete planning, robotics or machine learning knowledge. As the project is a multi-faceted one, we expect candidates with an appreciation of the interaction between operations research and machine learning. Master of Science (MSc) diploma in Transportation, Robotics, Computer Science, Logistics, Operations Research, Industrial Engineering, Applied Maths or any other related field. Drive for excellence in research and the ability to work independently and as part of a team. Willingness to conduct multidisciplinary research in collaboration with both scientific and industrial partners. Excellent problem-solving and analytical skills. TOEFL or IELTS English proficiency tests for all applicants except those graduated from an MSc program that was taught in English. The minimum requirement of a TOEFL score of 100 or IELTS of 7.0 per sub-skill (writing, reading, listening, speaking).

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1.5 year contract with an official go/no go progress assessment within 15 months, followed by an additional contract for the remaining 2.5 years assuming everything goes well and performance requirements are met. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from Promovendus gross per month from the first year to the fourth year based on a fulltime contract (38 hours), plus 8% holiday allowance and an end-of-year bonus of 8.3%.