Prof. Nikolas Geroliminis is a Full Professor at EPFL and the head of the Urban Transport Systems Laboratory (LUTS). Before joining EPFL he was an Assistant Professor on the faculty of the Department of Civil Engineering at the University of Minnesota. He has a diploma in Civil Engineering from the National Technical University of Athens (NTUA) and a MSc and Ph.D. in civil engineering from University of California, Berkeley. His research interests focus primarily on urban transportation systems, traffic flow theory and control, public transportation and on-demand transport, car sharing, Optimization and Large Scale Networks. Among his recent initiatives is the creation of an open-science large-scale dataset of naturalistic urban trajectories of half a million vehicles that have been collected by one-of-a-kind experiment by a swarm of drones (https://open-traffic.epfl.ch). Among other editorial responsibilities, he is currently the Editor-In-Chief of Transportation Research part C: Emerging Technologies.

Urban mobility systems are undergoing a profound transformation driven by rapid urbanization, increasing congestion, emerging mobility services, and new sensing and automation technologies. Managing these complex multimodal systems requires an integrated framework that connects high-resolution monitoring, accurate forecasting, and network-level control. This talk presents recent advances along this direction, with a focus on UAV-based traffic monitoring, spatio-temporal traffic prediction, traffic signal perimeter control, and ride-hailing vehicle rebalancing.

The first part of the talk discusses how unmanned aerial vehicles can provide a scalable and flexible alternative for observing complex urban traffic interactions. A series of drone experiments conducted in different urban environments demonstrate the potential of UAVs to capture high-resolution multimodal traffic data, including vehicle movements, pedestrian interactions, and network-level dynamics. Building on these data sources, we develop a multi-sensor urban mobility observatory for large-scale traffic forecasting.

The second part of the talk focuses on the control and optimization of large-scale multimodal urban networks. For traffic signal management, we present a two-layer adaptive control framework that combines macroscopic fundamental diagram-based perimeter control with distributed Max Pressure signal control. For ride-hailing systems, we introduce (i) a geofencing strategy to manage the competition between ride-hailing services and public transit by restricting pick-up activities near transit stops, and (ii) a hierarchical rebalancing strategy that integrates proactive macro-level repositioning of idle vehicles with micro-level vehicle guidance. Aggregated models based on the macroscopic fundamental diagram are extended to capture the mixed dynamics of different traffic systems (ground and low altitude) with private vehicles, UAVs and ride-hailing fleets.

Finally, the talk integrates how UAV monitoring, traffic forecasting, delivery drone routing, signal control, and ride-hailing rebalancing can be viewed as interconnected components of an intelligent urban mobility management system.