Traffic Monitoring and Control with a Swarm of Drones

Abstract

Unmanned aerial vehicles (UAVs) are increasingly shaping the future of urban mobility, logistics, and infrastructure monitoring. This talk will investigate recent contributions in traffic monitoring, traffic forecasting and parcel delivery with a routing optimization for a swarm of drones integrated in the urban environment. First, we present a series of unique drone experiments around the world for monitoring complex multimodal traffic interactions and offer a scalable and flexible alternative for obtaining high-resolution data. Then, an accurate multi-sensor mobility observatory for large-scale urban networks is developed to predict both the individual traffic of all road segments and the regional traffic. A simple yet effective graph-based model with multiple input sources is proposed to integrate multiple data modalities and learn spatio-temporal correlations. In the second part of this talk we focus on drone routing optimization. Coordinating a swarm forimproved situational awareness across wide urban areas introduces a new layer of complexity as their limited flight time, communication constraints, and decentralized nature directly turn traffic monitoring into an instance of a dynamic multi-agent control problem. We will finally introduce a dual control framework to simultaneously fulfil delivery requests and perform road monitoring in a coordinated manner.

Speaker

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 PhD 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.