I am interested in quantifying model uncertainty in dynamical systems. This is useful for generating reliable predictions as well as building robust control systems. By sampling a variety of scenarios from our model - not just the most likely, or those contained in the data - we can expose our control system to a wider variety of settings, leading to better performance in new ones. I am also generally interested in the problem of inference from noisy or incomplete data and in 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