Infant-like social interactions between a robot and a human caregiver.

From birth, human infants are immersed in a social environment that allows them to learn by leveraging the skills and capabilities of their caregivers . A critical pre-cursor to this type of social learning is the ability to m aintain interaction levels that are neither overwhelming nor under-stimulat ing. In this paper, we present a mechanism for an autonomous robot to regul ate the intensity of its social interactions with a human. Similar to the f eedback from infant to caregiver, the robot uses expressive displays to mod ulate the interaction intensity. This mechanism is integrated within a gene ral framework that combines perception, attention, drives, emotions, behavi or selection, and motor acts. We present a specific implementation of this architecture that enables the robot to react appropriately to both social s timuli (faces) and non-social stimuli (moving toys) while maintaining a sui table interaction intensity We present results from both face-to-face inter actions and interactions mediated through a toy.