DDLC Seminar: Stefano Di Cairano (Mitsubishi)
Data Driven Learning and Control seminar series is organized by the Information and Decision Science Lab at Cornell University and aims to explore the latest advancements and interdisciplinary approaches to data-driven learning and control systems.
Watch on YouTube Live
Decision making for automated driving: from Control, to Optimization, to Data-driven Methods
Decision making in automated driving for single and connected vehicles is a challenging task that involves discrete decisions, i.e., the next action to be taken, and continuous decisions, i.e., the trajectory to execute to achieve the action. As a single problem, decision making is often too computationally challenging to solve in real-time in complex environments, especially in the computational platform of productions vehicles. However, by decomposing the problem and solving it via a combination of method, the solution becomes feasible even in limited platforms.
In this talk I am going to review different approaches for solving the decision making problem for automated driving, from reachable sets to fast mixed integer solvers, to safety-assured machine learning. Then, I will briefly discuss some extensions of the approach to optimize mixed human-autonomous traffic by concurrently managing automated vehicle and traffic lights phasing.
Bio:
Stefano Di Cairano received the master’s degree in information engineering from the University Siena in 2004 and his Ph.D. in computer engineering from Siena in 2008. From 2008 to 2011, he was at Powertrain Control R&A, Ford Research, and Advanced Engineering, Dearborn, MI. Since 2011, he has been with the Mitsubishi Electric Research Laboratories, Cambridge, MA, where he is currently a distinguished research scientist and a senior team leader. He has authored/coauthored more than 200 peer-reviewed papers in journals and conference proceedings and 70 patents. His research is on optimization-based control strategies for complex mechatronic systems, in automotive, factory automation, transportation, and aerospace. His research interests include model predictive control, constrained control, particle filtering, hybrid systems, and optimization. He was the chair of the IEEE CSS Technical Committee on Automotive Controls and the IEEE CSS Standing Committee on Standards. He is currently the inaugural chair of the IEEE CSS Technology Conferences Editorial Board. He was an associate editor of the IEEE Transactions on Control Systems Technology.