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
Predicting trajectories from templates
Using stored examples (templates) to solve complex dynamic tasks has appeared in many areas of engineering. This approach allows for fast inference without model reconstruction. However, a general theory of control, estimation and prediction from templates is still largely undeveloped.
In this talk, we will focus on predicting the evolution of unknown dynamical systems from observed past data windows and templates. Specifically, we first construct a library of prototypical trajectories (templates), generated by different systems. We then combine these templates to build a new repertoire of sample trajectories that can successfully predict the future even when the observed past windows do not belong to any system in the original library. This demonstrates a form of generalization across dynamical behaviors.
Bio: Claudio De Persis is a professor with the Engineering and Technology Institute at the University of Groningen, the Netherlands, since 2011. He received his Ph.D. degree in engineering from the University of Rome “la Sapienza” in 2000. He was a postdoctoral researcher with Washington University in St. Louis (2000-2001) and Yale University (2001-2002). He held faculty positions at University of Rome “la Sapienza” (2002-2009) and Twente University, Enschede (2009-2011).
De Persis’ research field is automatic control and its applications. He works on the automatic design of controllers from data by integrating control theory and data science and proposing methods that reduce control design to the solution of data-dependent convex programs.