A Storytelling Robot: Modeling and Evaluation of Human-like Gaze Behavior

Abstract

Engaging storytelling is a necessary skill for humanoid robots if they are to be used in education and entertainment applications. Storytelling requires that the humanoid robot be aware of its audience and able to direct its gaze in a natural way. In this paper, we explore how human gaze can be modeled and implemented on a humanoid robot to create a natural, humanlike behavior for storytelling. Our gaze model integrates data collected from a human storyteller and a discourse structure model developed by Cassell and her colleagues for humanlike conversational agents. We used this model to direct the gaze of a humanoid robot, Honda? ASIMO, as he recited a Japanese fairy tale using a pre-recorded human voice. We assessed the efficacy of this gaze algorithm in an experiment that was motivated by results in the literature on human-human communication. Those results suggest that more frequent gaze toward the listener should have a positive affect. We manipulated the frequency of ASIMO? gaze between two participants and used pre and post questionnaires to determine that participants evaluated the robot more positively and performed better in a recall task when ASIMO looked at them more. This experiment provides an evaluation of our gaze algorithm and also adds to the growing evidence that there are many commonalities between human-human communication and human-robot communication.