MIE Seminar: Automated Driving from a Control Systems Perspective: Architectures, Learning, and Safety Guarantees

Location: 011 Kariotis Hall

We welcome you to join us for our next MIE Seminar Series of the Spring 2026 semester, featuring Dr. Stefano Di Cairano, Distinguished Research Scientist, Senior Team Leader, Deputy Director, and IEEE Fellow, at Mitsubishi Electric Research Laboratories.

Dr. Di Cairano will present a seminar titled: “Automated Driving from a Control Systems Perspective: Architectures, Learning, and Safety Guarantees.” This seminar explores deployment-ready, control-inspired approaches to autonomous driving—drawing on two decades of academic and industry experience—while highlighting remaining challenges, cross-domain lessons, and a near-deployment application in autonomous logistics.

Abstract:

After years of strong enthusiasm for autonomous vehicles, recent adjustments in targets and expectations have highlighted that significant challenges remain before these technologies can be deployed everywhere at scale. In this talk, I will share some insights from nearly 20 years of work in automated driving across both academia and industry, spanning early prototypes, ADAS technologies, road-tested vehicles, and systems deployed in production and pre-production environments.

The talk will focus on control-inspired approaches that have proven effective for deployment in real-world environments. These include predictive constrained control, statistical sampling–based planning, learning with safety guarantees, and architectural integration based on reachable and invariant sets.

Finally, I will discuss key challenges that still need to be addressed, what lessons can be drawn from related domains—such as fault-tolerant control for spacecraft and planning for autonomous drones—and the underlying research questions that remain open. I will also present a recent application in autonomous logistics, currently approaching deployment, that leverage infrastructure support to address some of these challenges.

Bio: Stefano Di Cairano received the Master’s (Laurea) and the Ph.D. degrees in information engineering in 2004 and 2008, respectively, from the University of Siena, Italy. During 2008-2011, he was with Powertrain Control R&A, Ford Research and Advanced Engineering, Dearborn, MI, USA. Since 2011, he is with Mitsubishi Electric Research Laboratories, Cambridge, MA, USA, where he is currently a Deputy Director, and a Distinguished Research Scientist. His research focuses on optimization-based control and decision-making strategies for automotive, factory automation, transportation, and aerospace. His research interests include model predictive control, constrained control, path planning, hybrid systems, optimization, and particle filtering. He has authored/coauthored more than 300 peer-reviewed papers in journals and conference proceedings and is an inventor in more than 100 patents. Dr. Di Cairano is a Fellow of IEEE, and a winner of the IEEE T-ASE best new application paper award, 2024. He has been the chair of the IEEE CSS Technical Committee on Automotive Controls and of the IEEE CSS Standing Committee on Standards. He was the inaugural Chair of the IEEE Technology Conferences Editorial Board and an Associate Editor of the IEEE Transactions on Control Systems Technology.