HUMAN ACTION LEARNING VIA HIDDEN MARKOV MODEL

To successfully interact with and learn from humans in cooperative mod es, robots need a mechanism for recognizing, characterizing, and emula ting human skills, In particular, it is our interest to develop the me chanism for recognizing and emulating simple human actions, i.e., a si mple activity in a manual operation where no sensory feedback is avail able. To this end, we have developed a method to model such actions us ing a hidden Markov model (HMM) representation. We proposed an approac h to address two critical problems in action modeling: classifying hum an action-intent, and leaning human skill, for which we elaborated on the method, procedure, and implementation issues in this paper, This w ork provides a framework for modeling and learning human actions front observations. The approach can be applied to intelligent recognition of manual actions and high-level programming of control input within a supervisory control paradigm, as well as automatic transfer of human skills to robotic systems.