PhD: Department of Intelligent Systems for Mobility and Logistics

We are looking for a researcher to join the Intelligent Systems for Mobility and Logistics department to develop a PhD project in the following scope:

Scope

Intelligent urban and interurban traffic management systems require complex control methods. Heterogeneous actors such as private cars, public transport, goods delivery vehicles, micromobility vehicles like (e-)bikes or (e-)scooters and pedestrians sharing a common urban space and transportation infrastructure need to be accommodated into an efficient and safe flow. Diverse regulations and traffic control strategies (i.e. traffic lights) help determine priorities and how these actors interact with the objective of reducing conflicts and bottlenecks.  

The high level of digitization, sensing capabilities and communications enable more dynamic decision making nowadays. For instance, urban access regulations may include dynamic access control and limitations to some vehicles (e.g. to Low Emission Zones, residential areas) and intersection management through traffic signal control (TSC) may adapt to unexpected incidents or congestion, include priorities to collective transportation if they are suffering delays, or prioritize emergency vehicles approaching the intersection.  Making decisions without carrying out a prior analysis of the consequences can even lead to decongesting certain areas at the expense of increasing congestion in others, so the global objectives are not met.

Therefore, building digital replicas of the connected transport infrastructure and the moving actors can be of help. Very different transport models can be found in the literature, used by the most advanced commercial transportation planning and simulation software. For instance, transportation planning studies based on mesoscopic and macroscopic models evaluate the mobility demand and support any changes and investments needed to adjust the capacity of the transportation network infrastructure to satisfy current and future travel flows for mid- and long-term horizons. Models can be extended and applied to understand the temporal affections of any short-term planned interventions or unexpected incidents into overall mobility patterns. Microscopic models operate at the vehicle or actor level understanding a fine-grain detail inside the mobility flow. Multiple diverse approaches are used to solve different problems and the one-size-fits-all does not exist when trying to build a digital replica of the mobility behaviour.

The objective of the PhD. will be to work on the inclusion of diverse control actuation strategies into transportation models. Diverse challenges remain unsolved in the state-of-the-art, that will be explored. For instance, since the effects of lane closures and road works in upstream and downstream traffic are not isolated and thus a global perspective of the network is sometimes needed, the inclusion of large-scale real time data into city-wide and regional decision-making processes opens scalability challenges. Moreover, the deployment of ML techniques such as reinforcement learning, well suited to solve control problems, is currently limited in real-life traffic management scenarios and intensive usage of simulation environments is required to ensure the validity of the actuation strategies.