This project aims at developing a parsimonious and accurate dynamic model of train motion, with values calibrated from real life measurement of different sensor types; explicitly considering uncertainty and probability distributions of parameters; and embedding expert knowledge at multiple levels, both as input of the model specification, and as output of the model estimation.
Despite the excellent quality of public transport systems in Switzerland, the railway system needs to increase its performance (quality, for instance, travel time) and capacity (amount of services run) and attract more travellers to match the ambitious targets from policy and environmental goals. One key aspect of traditional railway transport systems is the complexity of aspects governing their motion. Safety and performance consideration limit what one can assume vehicles can do. The precise determination of the motion of a vehicle is very relevant to determine an effective timetable, energy efficient speed trajectories, and to integrate higher automation in the management of both vehicles and networks, also integrating human aspects from the driver and safety procedures (see for instance for a recent review of the subject: A. Cunillera, N. Bešinović, R. M. Lentink, N. van Oort and R. M. P. Goverde, "A Literature Review on Train Motion Model Calibration," in IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 4, pp. 3660-3677, doi: 10.1109/TITS.2023.3236062).
The project focuses on learning a motion model of train operations at the level of vehicles and parameters from detailed data collected on real vehicles, based on a collaboration with industrial partners.
We expect the following tasks to be performed:
The ultimate objective is to be both precise /accurate, parsimonious, and useful for decision making. Moreover there is a lot of expert knowledge to be considered at multiple levels, both as input of the model specification, and as output of the model estimation. The process, data and output should determine standards and specification for both human driver and automated train operations, and trajectory planning for any downstream optimization of the schedule, for both passenger trains, and especially for freight trains (which have very variable composition, weight, length).
Ideally, you have (or are about to receive) a Masters’ degree in transport sciences, quantitative finance, data science, econometrics, management/ decision sciences mathematics, statistics, computer science, physics or related fields.
Your research track is consistent and shows a track record, or clear potential, for modelling, control, and optimisation of transport systems. You are highly motivated and self-driven, with a clear research vision, academic ambition, and excellent communication and writing skills (fluent spoken and written English is mandatory). Moreover, the following skills are expected of a promising candidate:
You enjoy working in an interactive international environment with doctoral students, post-docs and senior scientists, referring continuously to practical problems and solutions.
ETH Zurich is a family-friendly employer with excellent working conditions. You can look forward to an exciting working environment, cultural diversity and attractive offers and benefits.
We look forward to receiving your online application by 15.05.2024 including the following documents:
The selection will be based on a multi-step application process.
Furthermore, we aim to maintain and expand our diversity and thus, we encourage people from underrepresented groups to apply. After a first selection, potential candidates will be contacted for a final selection, which will be based on the candidates’ qualifications as well as on a personal interview with the supervisors.
This position will be available, with an ideal starting date between July 2024 and December 2024, or further upon agreement; the planned duration of the initial contract is 18 months, after which an aptitude colloquium will determine the further continuation of the project. The total doctoral project is expected to be finished in 4 years in total. The project is to be performed in close collaboration with academic partner (Prof A. Rupenyan, ZHAW) and industrial partners (major railway operator in Switzerland). The position is within, and profits from networking and competeneces from, the large academic network of the NCCR Automation project.
Please note that we exclusively accept applications submitted through our online application portal. Applications via email or postal services will not be considered.
For further information about the institute and the group please our website. Questions regarding the position should be directed to Prof. Dr. Francesco Corman by email francesco.corman@ivt.baug.ethz.ch (no applications).
ETH Zürich is well known for its excellent education, ground-breaking fundamental research and for implementing its results directly into practice.
Besuchen Sie die Arbeitgeberseite