Introduction of local interaction to head-motion based robot control

Abstract

This research implements an idea of motion display that functions the display itself as the communication media which mimics the motion of human head to enhance presence in remote communication. In order to mimic the head motion, a facial behavior analysis tool based on image processing was implemented, and its result was applied to HMoD (Head Motion Display robot) to mimic the physical motion. Even though HMoD mimics the head motion, a reaction delay was recognized in video communication. Furthermore, HMoD did not make appropriate reaction if the communication partner actively reacts the head. In order to solve these problems, this study proposes a voice signal during the video conversation as the driving force of local interaction. First, image processing based motion display control is presented. Then, voice signal based motion display control is proposed and explained. Finally, this paper proposes the idea of combination of these two signals to improve the interaction.