Interactive task training of a mobile robot through human gesture recognition

This paper describes a demonstration-based programming system in which a mobile robot observes the actions of a human performing a multi-step task. From these observations, the robot determines which of its pre-learned capabilities are required to replicate the task and in what sequence they must be ordered. The focus of this paper is on the hidden Markov model method used to learn and classify the actions as "gestures". A preliminary system demonstration is also described in which the robot observes the human performing a block distribution task. During the demonstration, the robot actively follows the demonstrator to maintain its vantage point and to infer spatial relationships.