The Dagstuhl Seminar aims to bring together leading and emerging minds on urban mobility analytics and future urban mobility to address recent trends that are shaping the information derived from increasingly larger data sets. One of these trends, not only in transportation research, is the of deep learning methods massive data analytics. In the domain of urban mobility this massive data emerges from a range of sensor platforms, from infrastructure to vehicles and smartphones, in volume, heterogeneity, velocity and veracity a prime application domain for deep learning. A second trend is the digital divide between academia and industry its challenges for reproducible research, a trend that has been compared to digital feudalism. While massive data on urban mobility is collected by industry and transport authorities, their access for academic research is limited by privacy concerns and also by commercial sensitivities. While reproducible research hinges on access to data, much of the urban mobility research and development is now done behind the closed doors of large transnational companies.

We might address questions at the seminar such as eliciting behavior from data, trajectory analysis including inferring travel mode and activity, travel behavior dynamics, harnessing massive data, activity-based approaches for mobility and travel behavior analysis, exploring potential of Deep Learning, challenges of Big Data processing, and quality and reliability of extracted information.

In this context the seminar makes a deliberate effort to invite people from both sides of the digital divide (i.e., from academia and industry) to share their experiences, their approaches, and their challenges, and to explore more future collaboration.

The organizing team, consisting of Stephan Winter (University of Melbourne, Australia), Monika Sester (Leibniz University Hannover, Germany), Kathleen Stewart (University of Maryland, USA), and David Jonietz (HERE Technologies, Switzerland), invites you cordially to this very special event in your calendar: Dagstuhl Seminars are frequently praised by participants as the most productive academic events they have ever experienced. This seminar, in the tradition of the house, promotes personal interactions and open discussions. As an outcome, we aim for a joint vision paper of the participants. Indirectly, these discussions will lead to new international collaborative research initiatives. The dynamics at the seminar will also be fostered by an industry-sized traffic dataset sponsored by HERE Technologies and the Institute of Advanced Research in Artificial Intelligence (IARAI). This dataset will be available for the working groups to explore and test their ideas.

The seminar will be structured by plenary presentations and discussions, and work in smaller groups. Selected participants will be invited for presentations or tutorials focusing both on new directions relating to big mobility data processing and AI/machine learning-based approaches, as well as on other key mobility-related topics from different disciplinary perspectives. All participants will be invited to discuss their own current research and newly developed methodologies as the basis for plenary discussions and for forming working groups. Working groups will target specialized topics or develop smaller initiatives. The sponsored dataset will offer an opportunity to explore ideas in hacks. In addition, a panel session will be planned to discuss issues around the growing digital divide involving mobility data and how academic research can still remain vital in this area. Equally important will be the seminar’s informal activities (meals, breaks, evenings, and a hiking trip) that will contribute by serendipity to new inspirations and collaborations.

Unlike most conferences, the focus is not solely on the presentation of established results but in equal parts on results, ideas, sketches, and open problems. Schloss Dagstuhl offers modern facilities and is located in the scenic countryside of Saarland.
The seminar lasts for the full week.

Creative Commons BY 3.0 DE

David Jonietz, Monika Sester, Kathleen Stewart, and Stephan Winter