CS-ECE Colloquium: Machine Learning for Estimating Robust Control Laws

This talk will provide an overview of techniques developed in my group to enable robots to react rapidly in the face of changes in the environment when manipulating objects. Learning is guided by observing humans' elaborate manipulatory skills. I will stress how important it is to model the various ways with which humans perform the same task. This multiplicity of solutions is the key to generate robust and flexible robotic controllers capable of adapting their strategies in the face of unexpected changes in the environment. I will review methods we have developed to allow instantaneous reactions to perturbation. These methods are based on autonomous dynamical systems as core controller. Machine learning techniques are developed to identify the control law while ensuring stability of the learned dynamics. I will present applications of these learned control laws for compliant control during human-robot collaborative tasks and for performing sport tasks, such as when playing golf with moving targets. The talk will conclude with examples in which robots achieve super-human capabilities for catching fast moving objects with a dexterity that exceeds that displayed by human beings