Motion coaching with emphatic motions and adverbial expressions for human beings by robotic system -Method for controlling motions and expressions with sole parameter-

Abstract

Whole-body gestures and verbal expressions should be bound according to given tasks and the current situation in intelligent human-robot interaction systems. Moreover, modification of expressions, such as emphasis of motions and change in verbal expressions, plays an important roll for successfully completing tasks according to user reaction. Slight differences in motions can be conveyed by binding an emphasized motions and an verbal expression. In robotics, however, even though the synthesis of gestures and speech has been discussed, how to bind synthesized emphatic motions and verbal expressions from an engineering point of view has not been adequately discussed. Synthesis of motion and speech requires recognition of user reaction, we therefor should integrate 1) recognizing reaction, 2) planning to complete tasks, 3) modification of motions and speech, and 4) maintaining a bi-directional interaction loop consisting of processes 1)–3). Thus, using a phase space, we propose a method for binding emphatic motions and adverbial expressions, and for evaluating and controlling these four required processes by using a sole scalar parameter. In the phase space, variety of motion patterns and verbal expressions can be expressed as static points. To evaluate the feasibility of the proposed method, we also propose a bi-directional motion coaching system using the method. We show the feasibility and effectiveness of robotic motion coaching systems through experiments of actual sport coaching tasks for beginners. From the results of participants' improvements in motion learning, we discuss and conclude the factors affecting such motion coaching systems that realizes binding and controlling emphatic motions and adverbial expressions using a sole scalar parameter in a phase space.