Control, Optimization, and Learning Methods for Emerging Mobility Systems


1. Andreas Malikopoulos

Terri Connor Kelly and John Kelly Career Development Associate Professor

Department of Mechanical Engineering

University of Delaware

2. Christos G. Cassandras

Distinguished Professor of Engineering

Head, Division of Systems Engineering

Boston University


Emerging mobility systems, e.g., connected and automated vehicles (CAVs), shared mobility, provide the most intriguing opportunity for enabling users to better monitor transportation network conditions and make better operating decisions to improve safety and reduce pollution, energy consumption, and travel delays. Emerging mobility systems are typical cyber-physical systems where the cyber component (e.g., data and shared information through vehicle-to-vehicle and vehicle-to-infrastructure communication) can aim at optimally controlling the physical entities (e.g., CAVs, non-CAVs). The cyber-physical nature of such systems is associated with significant control challenges and gives rise to a new level of complexity in modeling and control. As we move to increasingly complex emerging mobility systems, new control, optimization, and learning approaches are needed to optimize the impact on system behavior of the interplay between vehicles at different traffic scenarios. It is expected that CAVs will gradually penetrate the market, interact with non-CAVs and contend with vehicle-to-vehicle and vehicle-to-infrastructure communication limitations, e.g., bandwidth, dropouts, errors and/or delays. New system approaches are needed to accommodate the challenges associated with the partial penetration of CAVs and communication limitations.

Objectives and expected outcome

The workshop intends to stimulate a discussion about a feasible research roadmap at the intersection of control, optimization, and learning that would result in new approaches for addressing the following technical challenges in emerging mobility systems. First, any potential limitations in the information (e.g., bandwidth, dropouts, and errors or delays) that CAVs receive from each other and the infrastructure could have a major impact on the performance. Second, different CAV penetration rates can significantly alter mobility system efficiency. Third, managing online vehicle-level operation for the controller can involve significant computational challenges. Finally, improving robustness and safety of CAVs constitutes a major technical challenge which has attracted considerable attention.

Expected attendance

The workshop is expected to attract an audience from many different technical communities because of the breadth of the topic and its intrinsic multidisciplinary.



UTC (Coordinated Universal Time), December 13 (Sun), 2020

1:00pm Welcoming remarks from the organizers

1:00pm-1:30pm Title: "Micro-Macro Modeling for Vehicular Traffic Control" — Antonella Ferrara

1:30pm-2:00pm Title: "Controlling Traffic Using Connected Vehicle Platoons" — Kalle Johansson

2:00pm-2:30pm Title: "A Decentralized Optimization Framework for the Internet of Cars" — Christos Cassandras

2:30pm-3:00pm Title: "Impact of V2X on Platoon Control of Connected Automated Vehicles" — Rong Su

3:00pm-3:30pm Title: "Safe Autonomy with Deep Learning in the Feedback Loop" — George Pappas

3:30pm-4:00pm Title: "Optimal Path Planning with Provable Safety for Connected and Automated Vehicles" — Andreas Malikopoulos

4:00pm-4:30pm Title: "Autonomous Mobility-on-Demand Systems for Future Urban Mobility" — Marco Pavone

4:30pm - 5:00pm Discussion