Engaging children in math education using a socially interactive humanoid robot

Studies have shown that teaching processes, which incorporate robotic-based engagement methods, can approach the effectiveness of human tutors. Not only have these socially-engaging robots been used in education, but also as weight-loss coaches, play partners, and companions. As such, in this paper we investigate the process of embedding social interaction within a humanoid-student learning scenario in order to reengage children during high-demand cognitive tasks.We discuss the overall system approach and the forms of multi-modal verbal and nonverbal (i.e. gestural) cues used by the robotic agent. Results derived from 20 children, age 13 through 18, engaging with the robot during a tablet-based algebra exam show that, while various forms of social interaction increase test performance, combinations of verbal cues result in a slightly better outcome with respect to test completion time.