Gazecoppet

摘要

This research aims to naturally evoke human-robot communications in ambient space based on a hierarchical model of gazecommunication. The interactive ambient space is created with our remote gaze-tracking technology based on image analyses and our gaze-reactive robot system. A single remote camera detects the user's gaze in unrestricted situations by using eye-ball estimation. The robot's gaze reacts with both 1) "positive evocation" by direct eye contact with multimodal reactions and 2) "passive evocation" by indirect co-gazing (watching a common object or place) according to the user's conscious/unconscious gaze.