AI and Data Talk Series
We are thrilled to announce the AI and Data Talk Series — an engaging lecture series presented by the ACE AI and Data Grand Challenge Research Committee. This series aims to elevate awareness and foster dialogue among a diverse audience, including established researchers, industry professionals, and early career scholars, about the vital intersection of control theory and AI technologies.
Event Details
Start Date: Mid-April
Frequency: Monthly Presentations (Each seminar is 1 hour long)
Location: Online (Zoom links provided upon registration)
Join us for a deep dive into the challenges and innovations within AI and control theory, from theoretical foundations to real-world applications, presented by renowned academics from around the globe.
Register Now to secure your spot and receive event reminders, Zoom links, and post-event materials.
Programme Schedule
Speaker | Date & Time | Title and Details |
Prof. Sebastien Gros | ||
Head of Department, Dept. of Eng. Cybernetics, NTNU, Trondheim, Norway | 15th April at 1:00 PM – 2:00 PM | Reinforcement Learning and Model Predictive Control: what did we learn on AI for decision making Abstract The combination Reinforcement Learning (RL) and Model Predictive Control (MPC) has been extensively studied in the recent literature. It has been shown that MPC (even with inaccurate models) can be a universal approximation for RL, with the benefits over standard Machine Learning tools to be structured, to provide rational decisions, to be able to use system knowledge, and to be equipped with a rich theory of stability and safety. Research on RL and MPC has also allowed to identify the class of problems where “classical” approaches (building the MPC model to fit the data) work well, and by default also the problems where they do not necessarily work, and hence where RL for MPC is effective. This research also suggests tracks to explore for a new paradigm on AI for decision. In this talk, we will briefly introduce these elements. Biography Sebastien Gros received his PhD degree in 2008 at the Automatic Control Lab, EPFL. After a bike trip in full autonomy from Switzerland to the Everest base camp, he worked in the wind industry in 2010-2011. He joined the Optimal Control group at KU Leuven in 2011 as a postdoc where he worked on numerical optimization methods, and NMPC for complex mechanical applications. He then joined the University of Chalmers in 2013 as an Assistant Professor, where he worked on distributed optimization methods, autonomous driving, vehicle control and traffic optimisation. He was promoted to Associate Professor in 2017. He joined the Dept. of Cybernetics at the Norwegian University of Technology (NTNU) in 2019 as a full Professor, and became head of Dept. in 2022. He has been working on learning methods for MPC since 2018, focusing on the combination of Reinforcement Learning and MPC with closed-loop optimality as target. |
Prof. Raphael Jungers | ||
UCLouvain | 12th May at 1:00 PM – 2:00 PM | On the Links Between Binary-Classification Learning and the Scenario Approach |
Prof. Pete Seiler | ||
University of Michigan, Dept. of Electrical Engineering and Computer Science, USA | 12th June at 1:00 PM – 2:00 PM | Extending Traditional Robust Control Methods for V&V of Nontraditional Controllers |
Dr. Matthew Peet | ||
Arizona State University, USA | 15th July at 4:00 PM – 5:00 PM | Learning the Kernel: a convex and scalable framework for classification and regression |
Dr. James Anderson | ||
Columbia University, USA | 15th August at 1:00 PM – 2:00 PM | Randomized Methods in Control or Federated Learning |
Dr. Luca Furieri | ||
University of Oxford, UK | 15th September at 1:00 PM – 2:00 PM | Closing the loop between optimal nonlinear control and learning-based optimization |
Dr. Giordano Scarciotti | ||
Imperial College, UK | 13th October at 12:00 PM – 1:00 PM | One equation to control them all: a data-driven view |
Prof. Chris Freeman | ||
University of Southampton, UK | Potential Date TBC: 12th November at 1:00 PM – 2:00 PM | Iterative learning control with applications to rehabilitation |
Registration
We offer flexible registration options:
- Full Series Registration: Sign up once and gain access to all seminars.
- Individual Session Registration: Select and register only for the sessions that interest you most.
Register Now to secure your spot and receive event reminders, Zoom links, and post-event materials.
Don’t miss this opportunity to connect with leading experts and enhance your understanding of the synergy between AI and control theory.
For any inquiries, please contact us at info@ukcontrol.org.