I am interested in quantifying the uncertainty over the evolution of dynamical systems. This is useful for generating reliable predictions as well as building robust control systems. By forcing our controllers to learn in a variety of settings - not just the most likely, or those contained in the data - we perform better when presented with new ones.
I am also generally interested in problems of inference from noisy data and variational inference methods.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems