Evaluating imitation and rule-based behaviors of eye contact and blinking using an android for conversation

Abstract

In this paper, we investigate which approach to generate eye behaviors using an android robot makes what impressions on humans and clarify which are the important factors for attractive eye behaviors. Thus, we evaluate the human impression of eye behaviors displayed by an android robot while talking to a human by comparing the motions generated by the two approaches. In the first approach, we develop a method to imitate human eye behavior obtained from eye trackers. In the second approach, we control the eye direction, eye-contact duration, and eyeblinks based on the findings of human eye behavior in psychology and cognitive research. In the experiments, we asked male and female subjects to evaluate their impression by comparing the eye behaviors with an android that controls the eye-contact duration and eyeblinks by editing the imitation parameters or the rule-based behavior. In the experiments, we asked subjects to evaluate their impression of different eye behaviors displayed by an android. The eye behaviors were generated by modifying the imitation parameters or the rule-based behavior, which resulted in different eye-contact duration and eyeblink duration and timing. From the results, we found that (1) the imitation and rule-based behaviors showed no difference in terms of human-likeness, (2) the 3-second eye contact obtained better scores regardless of the imitation or rule-based eye behavior, (3) the subjects might regard the long eyeblinks as voluntary eyeblinks, with the intention to break eye contact, and (4) female subjects preferred short eyeblinks rather than long ones and considered that short eyeblinks might be one of the keys to making eye contact more suitable, in contrast to male subjects who preferred long eyeblinks.