OGST - Aditi Ramachandran
Title: Fostering Learning Gains Through Personalized Robot-Child Tutoring Interactions
Advisor: Brian Scassellati
Abstract: Existing intelligent tutoring systems that offer personalization are typically very content-dependent. We aim to personalize the pace of a robot-child tutoring interaction by utilizing the relative difficulties of the exercises to vary the sequence of problems, with the goal of keeping engagement sustained throughout the interaction. We hypothesize that a robotic tutoring system that can leverage a child’s affective signals as well as their learning progress will lead to greater engagement and learning gains from the child in a one-on-one tutoring interaction. We discuss an initial framework to address this hypothesis. We outline the various components of creating an adaptive robot tutoring system, including our proposed modeling approach, leveraging knowledge from the field of intelligent tutoring systems, and additional challenges we are working towards overcoming.