Do people spontaneously take a robot's visual perspective?

Abstract

Visual perspective taking plays a fundamental role in both human-human interaction and human-robot interaction (HRI). In three experiments, we took a novel approach to the topic of visual perspective taking in HRI, examining whether, and under what conditions, people spontaneously take a robot's visual perspective. Using two different robot models, we found that specific behaviors performed by a robot-namely, object-directed gaze and goal-directed reaching-led many human viewers to take the robot's visual perspective, though slightly fewer than when the same behaviors were performed by a person. However, we found no difference in people's perspective-taking tendency toward robots that differed in their human-likeness. Also, reaching became an especially effective perspective-taking trigger when it was displayed in a video rather than in a photograph. Taken together, these findings suggest that certain nonverbal behaviors in robots are sufficient to trigger the mechanism of mental state attribution-visual perspective taking in particular-in human observers. Therefore, people's spontaneous perspective-taking tendencies should be taken into account when designing intuitive and effective human-centered robots.