Smart Urban Mobility

Research Cluster @ Artificial Intelligence Center, CTU in Prague

A.I. for On-demand Mobility Systems

We are developing models that provide insights into the performance of on-demand transportation systems and use them to estimate the impact of their large-scale deployment. Further, we are looking in the potential of advanced optimization techniques, automation, ride-sharing and market-based mechanisms to achieve affordable, efficient, and congestion-free urban traffic.

Research Highlights

Fleet Sizing in Shared Vehicle Systems with Service Quality Guarantees

We have developed a model that allows making principled decisions about the fleet size and the optimal fleet distribution in vehicle sharing system. As a case study, we used the model to compute what would be the minimum fleet size and minimum station capacities that suffice to ensure that the customer will not experience unavailability of bikes to rent or unavailability of free bike docks.

Related Papers

  • M. Čáp, V. Szabolcs, and E. Frazzoli, “Fleet sizing in shared vehicle systems with service quality guarantees,” in IEEE Conference on Decision and Control, 2018.

Capacity-aware Fleet Routing

The large fleets of AMoD systems might play a major role in future traffic flows. We develop routing algorithms to efficiently control the fleet with respect to the limited road infrastructure capacities. We present a new reformulation of congestion-free fleet routing problem that enables to solve instances of realistic sizes that were previously considered intractable.

Related Papers

  • M. Schaefer, M. Čáp, J. Mrkos, J. Vokřínek. “Congestion-Free Fleet Routing for Automated Mobility-on-Demand Systems”.

Simulation

We studied the impact of the mobility on demand systems (MoD) deployment on traffic density. We tested both the system with and without ridesharing on the Prague metropolitan area, where we replaced all vehicles by MoD. Now we are working on the comparison of different ridesharing algorithms. You can explore our open source projects at https://github.com/aicenter.

Related Papers

  • D. Fiedler, M. Čáp, and M. Čertický. “Impact of mobility-on-demand on traffic congestion: Simulation-based study”. In 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017.
  • D. Fiedler, M. Čertický, J. A. Mora and M. Čáp. “The Impact of Ridesharing in Mobility-on-Demand Systems: Simulation Case Study in Prague”. In 2018 IEEE 21th International Conference on Intelligent Transportation Systems (ITSC), 2018.

People

Michal Cap
Martin Schaefer
David Fiedler
Michal Pechoucek

Awards

1st. Place Taxify Challenge 2018

1st. Place Prague 2030

3th Place Smart Mobility Hackathon 2018

  • 3th Place Global Transport Hackathon
  • ...

Our Partners

Join us

We are based in the beautiful city of Prague. Our offices are located in a historical building of one of the oldest technical universities in Europe.

We are looking for colleagues at all levels of seniority (PhDs, postdocs and assistant/associate professors) to join our team. If you find our work interesting, consider joining us!

Contact

martin.schaefer@fel.cvut.cz