Fostering Learning Gains Through Personalized Robot-Child Tutoring Interactions

Abstract

Social robots can be used to tutor children in one-on-one interactions. It would be most beneficial for these robots to adapt their behavior to suit the individual learning needs of children. Each child is different; they learn at their own pace and respond better to certain types of feedback and exercises. Furthermore, being able to detect various affective signals during an interaction with a social robot would allow the robot to adaptively change its behavior to counter negative affective states that occur during learning, such as confusion or boredom. This type of adaptive behavior based on perceived signals from the child (such as facial expressions, body posture, etc.) will create more effective tutoring interactions between the robot and child. We propose that a robotic tutoring system that can leverage both affective signals as well as progress through a learning task will lead to greater engagement and learning gains from the child in a one-on-one tutoring interaction.