Melanie Zeilinger

University of Freiburg and ETH Zurich

Tuesday, February 05, 2019, 11:00 - 12:00

Room 01-012, Georges-Köhler-Allee 102, Freiburg 79110, Germany

A new opportunity for pushing the performance of emerging complex, large-scale and variable control systems to the next level is offered by the capability of learning from data during closed-loop operation.  Safety concerns when integrating learning in a closed-loop, automated decision-making process, however, represent a key limitation for leveraging this potential in many industrial applications.

In this talk, I will present techniques based on Model Predictive Control (MPC) concepts in order to ensure satisfaction of safety constraints while learning from data. I will first present a cautious MPC controller that can leverage data, but also takes into account residual model uncertainty to systematically improve performance and constraint satisfaction properties by integrating a Gaussian process model, where the specific focus will be on approximations enabling the approach for fast dynamical systems.  Second, a framework for augmenting any learning-based controller with safety certificates is presented. Future constraint satisfaction under the learning-based input is verified, and the control input modified if required, based on robust MPC techniques. The ideas will be highlighted with examples from vehicle control.