This paper introduces an educational software platform for a small teddy-bear-like robot, RobotPHONE. Utilizing back-drivability of the three joints (totally 6 DOFs) of the robot, the platform enables the robot to learn correspondences between gestures (posed by a human teacher) and voice (given by a human). Because the motion and the voice can be symmetrically produced and recognized, the robot would be an ideal tool for the research and education in learning and development.
展开▼