Associations of Gaze and Facial Behaviors with Subjective Perceptions of Facial Expressions in a Human-like Android Robot

Android robots with human-like faces have been developed based on biomimetic principles to reproduce human facial characteristics and expressive behavior. However, the same facial expression may be perceived differently depending on individual perceptual tendencies and conversational context. This study examined whether such subjective evaluations of android facial expressions are reflected in observers’ gaze and facial responses during face-to-face dialogue. Fourteen adults conversed with an android robot and evaluated each facial expression in terms of contextual strangeness and familiarity. Wearable eye tracking was used to measure gaze allocation across facial regions, while participants’ facial movements were extracted from video. Behavioral responses during the 2.5 s following each of the android’s facial-expression events were analyzed. Expressions perceived as strange in the conversational context were associated with reduced mouth-directed gaze and greater activation of several mouth-related blendshapes compared with those perceived as not strange. For unfamiliar expressions, gaze shifted away from the eyes and toward areas outside the face around 1 s after the expression command, whereas familiar expressions showed the opposite pattern. These exploratory findings suggest that subjective perceptions of android facial expressions are reflected in both gaze allocation and facial behavior during interaction.