Track / Overview

A reliable and dynamic Transportation System is the key to broad sustainable mobility of the future. Such a mobility network consists of many different transportation modalities, which need to be integrated seamlessly to offer reliable service to a demand. Constraints from technology, infrastructure, resources, and costs need to be considered.

Such complex and highly connected systems face many different challenges, from traffic flow optimization, addressing the demand by responsive and appropriate scheduling, coordinated maintenance, personnel, and supply chain management. 

Traditionally many of the challenges were solved separately, through experience and human efforts. The introduction of computer systems and classical optimization algorithms allowed to partially improve specific processes. In recent years however, the rise of AI and the simplified access to large datasets have started to influence how problems are solved within the transportation and mobility domain. Modern AI and ML solutions can complement shortcomings of classical optimization algorithms and thus present a viable addition to the current algorithmic solutions. 

In this track we would like to introduce a system-wide discussion on how AI and advanced analytics can play a role to shape the performance of transportation systems and the mobility of the future. This pertains to supervised and unsupervised predictive and prescriptive methods. To this end, the state of the art is balanced with the applied research, and the identification of possible use case, and blockers towards industrial applications.

Track / Schedule

Introduction

With Erik Nygren & Francesco Corman

Predictions for Better Decisions: Towards Integrated Prediction and Optimization

With Emma Frejinger

Learning Individual Behaviors from Vehicle Trajectory Data

With Kenan Zhang

Break

Measuring Traffic through Partially Biased Observations

With Moritz Neun & Christian Eichenberger

Artificial Intelligence and Autonomous Vehicles

With Alexandre Alahi

Predicting Time-to-Green of Fully-actuated Signal Control Systems with Deep Learning Models

With Alexander Genser

On Board Monitoring for Railway Infrastructure Condition Assessment

With Cyprien Hoelzl

Towards a Data-driven Operational Digital Twin for Railway Wheels

With Katharina Rombach

Aerial Imagery Analytics for Railways

With Bruno Hauser

Break

Improve Railway Safety and reliability with NLP

With Fionn Gantenbein & Daniele Mele

Lessons Learned from Watching Machines Learn

With Thilo Stadelmann

Wrap-up

With Erik Nygren & Francesco Corman

Track / Speakers

Erik Nygren

Product Manager Analytics, SBB

Alexandre Alahi

Professor, EPFL

Francesco Corman

Professor for Transport Systems. ETH Zürich

Cyprien Hoelzl

PhD Student, ETH Zürich

Emma Frejinger

Professor, Université de Montréal

Kenan Zhang

Postdoctoral researcher, ETH Zurich

Thilo Stadelmann

Professor, ZHAW

Daniele Mele

Data Scientist / Product Owner, SBB

Katharina Rombach

MSc, ETHZ

Moritz Neun

Researcher and Engineer, IARAI

Christian Eichenberger

Resarchers and Engineers, IARAI

Bruno Hauser

Data Scientist, SBB

Fionn Gantenbein

Data Scientist, SBB

Alexander Genser

PhD Candidate, ETH Zurich

Track / Co-organizers

Erik Nygren

Product Manager Analytics, SBB

Francesco Corman

Professor for Transport Systems. ETH Zürich

AMLD EPFL 2022 / Tracks & talks

AMLD Keynote Session – Monday morning

Marcel Salathé, Lenka Zdeborová, Carmela Troncoso, Chiara Enderle, Patrick Barbey, Thomas Wolf, Gunther Jansen, Laure Willemin, Simon Hefti, Arthur Gassner

10:00-12:00 March 28Auditorium A

AI & Physics

Francesca Mignacco, Gert-Jan Both, Michael Unser, Thomas Asikis, Dalila Salamani, Pietro Rotondo, Tom Beucler, Giulio Biroli

12:30-18:00 March 285BC

AI & Pharma

Asif Jan, Jonas Richiardi, Patrick Schwab, Naghmeh Ghazaleh, Alexander Büsser, Carlos Ciller, Caibin Sheng, Silvia Zaoli, Félix Balazard, Giulia Capestro, Marianna Rapsomaniki, Martijn van Attekum

13:30-17:30 March 281BC

AMLD / Global partners