Unreliability Defines Poor Mobility.
Or Does It?
Mobility research usually treats unreliability as a problem to be eliminated. And indeed, the downsides of unreliability—such as delays, missed connections, and disruptions—are evident. However, a broader, long-term perspective suggests a more nuanced discussion of unreliability. Under certain conditions, unreliability can contribute to robustness and flexibility, enable novel forms of interaction, and give rise to adaptive or creative responses.
About the Conference
This conference explores the broad spectrum of positive and negative consequences of unreliability in mobility. We will combine viewpoints of traditional mobility research with cutting-edge developments in data science and AI and with a holistic sociological perspective. Indeed, growing emphasis on local accessibility and slow mobility, as in the 15-minute city and machizukuri, highlights the importance of well-being, social connection, and sustainability in the context of transportation. Theories on the benefits of inconvenience and Rosa’s resonance suggest that unlimited accessibility may erode meaning by removing effort, surprise, and unpredictability. Hence, future planning must balance optimization with human-centered values. Against this background, the conference invites contributions that engage with the following questions:
-
What is the best mathematical framework for rigorous data analyses of unreliability? What mathematical guarantees can and cannot be expected?
-
How can data science help distinguish “good” from “bad” unreliability, quantify the long- and short-term impacts, and communicate the results?
-
Can the “benefits of inconvenience”, positive (side-)effects of “surprise” and “unavailability” be quantified? If yes, should these aspects even be considered in cost-benefit analysis?
-
How can approaches like gamification and fuzzy information create more robust, safer, and smarter traveler experiences? In the longer term, can such approaches support well-being? If yes, what methods and pipelines from contemporary machine learning and AI might lead to new tools for travelers? Are new tools even necessary?
Contributions are welcome from all disciplines and at all academic level. Abstracts can be submitted here until May 30, and decisions will be communicated by June 15. The three best student posters will be awarded prizes during the conference.
What Participants Get from the Conference
-
Researchers will discuss their ideas with a group of international experts from diverse disciplines
-
Business leaders will gain insights into the latest developments in the field
-
Policymakers will get inspiration to develop concrete strategies for better mobility
Scientific Committee
Connecting Data Science and Transportation
Jan-Dirk and Johannes share a mission to bridge the world of transportation with the latest advances in data science and artificial intelligence. This workshop represents a first step toward that vision by bringing together leading researchers from around the globe. We are convinced that today’s transportation challenges—and their short- and long-term social impacts on accessibility, equity, safety, and quality of life—can only be addressed through true interdisciplinary collaboration. Join us and become part of this journey.
Keynote Talks
Title: Between Optimization and Unavailability: Why Future-Ready Transportation Is Not Just a Question of More Data Abstract: Data science and artificial intelligence are increasingly promising to make mobility more efficient, predictable, and seemingly reliable. At the same time, growing evidence suggests that maximum optimization does not automatically lead to higher quality of life, but can instead generate new forms of stress, loss of control, and alienation. Taking the Unreliability Paradox as a starting point, this talk reconsiders mobility from a future-oriented and societal perspective. It explores the role of unavailability, surprise, and serendipity in well-being, resonance, and meaningful mobility, and examines how limited choice can, under certain conditions, function as a quality rather than a deficit. Against this backdrop, contemporary concepts such as the 15-minute city are discussed alongside the challenges of an increasingly atomized society. - Where do connective spaces and places emerge today? - How can mobility systems be designed not only to optimize movement, but also to foster social resonance, encounters, and a sense of commitment and belonging? - Who decides which forms of optimization are desirable and where intentional limits or friction should be designed into mobility systems? Drawing on future scenarios, conceptual frameworks from futures studies, and examples from urban and mobility development, the talk argues that beyond better predictions, we need new normative frameworks for “good” mobility and reflects on the implications this has for data science, design, and governance in transportation.
Title: Assessing an EbikeCity: Limits and possibilities Abstract: Transport planning is in a dilemma, as the gains of the successful strategies and investments of the past are now negated by their induced demand effects and global warming impacts. The past strategies remain nevertheless the preferred options of most policy makers and voters. The challenge is therefore twofold: a) formulate the required radical new strategies and b) assess their likely impacts credibly and reliably. The talk will present one such strategy, which was developed and then simulated for the city of Zürich. The ebikecity strategy shifts 50% of the road space to the non-motorized modes, while maintaining access and accessibility levels. The current approach used to simulate the strategy will be discussed and then queried for its reliability and trustworthiness. The role of “big data” and ML will be discussed. The approach will be compared against the traditional approaches employed in transport planning. The gaps in both will be identified and possible solutions outlined.
Title: The Geometry of Good Unreliability: How AI Can Balance Optimization with Meaningful Flexibility Abstract: Modern transportation optimization pursues an alluring goal: minimize uncertainty, maximize predictability, deliver the optimal route. Yet this framing conflates two fundamentally different types of uncertainty: the frustrating unpredictability that erodes trust, and the generative uncertainty that enables discovery, encounter, and adaptation. In this keynote I will (try to) argue that distinguishing "good" from "bad" unreliability is not just a philosophical exercise but might admit a tractable mathematical perspective and that AI may be uniquely positioned to operationalize this distinction at scale. We will motivate a geometric perspective on mobility optimization, where the feasible region represents not a constraint to be minimized against, but a space of possibilities to be thoughtfully navigated and even explored. Rather than collapsing this space to a single optimal point, AI systems can learn to balance competing objectives: efficiency and serendipity, reliability and exploration, predictability and the productive friction that fosters social connection. Similar to multi-objective optimization, robust planning under uncertainty, and recent advances in reinforcement learning, we outline how AI can serve as a balancing mechanism, by dynamically adjusting tradeoffs between, e.g., tight optimization and deliberate slack based on context, user needs, and system-wide considerations. The result is not optimization or unreliability, but "optimized unreliability". We finish with a few thoughts on the implications for the design of future mobility systems and the broader question of how AI can enhance rather than erode human agency.
Tentative Schedule
20th
SUNDAY
9:00 am
Keynote (Christiane Varga)
10:00 am
Coffee break
10:30 am
Breakout sessions
-
Unreliability as Source of Innovation (Christiane Varga)
-
Designing Surprise (TBD)
-
Streaming Analytics for Last-Mile Delivery Platforms (Ines Wilms/Jeroem Rombouts)
12:30 pm
Lunch break
2:00 pm
Contributed talks
3:30 pm
Coffee break
3:45 pm
Poster lightning pitches
4:30 pm
Poster session
21st
MONDAY
9:00 am
Keynote (Sebastian Pokutta)
10:00 am
Coffee break
10:30 am
Breakout sessions
-
Resilience Through Unreliability (Francesco Corman)
-
For Whom Is Unreliability "Good"? Relational Legitimacy Beyond Optimization (Tommy Ho Chan)
-
Time-Use Research and Mobility (TBD)
12:30 pm
Lunch break
2:00 pm
Contributed talks
3:30 pm
Social program
22nd
TUESDAY
9:00 am
Plenary talk
10:00 am
Coffee break
10:30 am
Keynote (Kay Axhausen)
11:30 pm
Closing discussion
Registration & Fees
Register early to secure discounted early bird rates. All registrations include full conference access, coffee breaks, and lunches.
Category
Regular (Ph.D. holders)
Student
Early Bird
(Before July 1, 2026)
475 EUR
400 EUR
Standard
(July 1 — Oct. 31, 2026)
550 EUR
475 EUR
Late
(After Nov. 1, 2026)
600 EUR
525 EUR
Location
The conference takes place in Donaueschingen, a historic town at the gateway to the Black Forest and the birthplace of the Danube River. Known for its palace gardens, cultural heritage, and proximity to some of southern Germany’s most scenic landscapes, Donaueschingen offers participants an appealing setting to combine professional exchange with sightseeing and regional exploration.