Samuel Spaulding

Personalizing robot tutors to individuals' learning differences

In education research, there is a widely-cited result called “Bloom’s two sigma” that characterizes the differences in learning outcomes between students who receive one-on-one tutoring and those who receive traditional classroom instruction [1]. Tutored students scored in the 95th percentile, or two sigmas above the mean, on average, compared to students who received traditional classroom instruction. In human-robot interaction research, however, there is relatively little work exploring the potential benefits of personalizing a robot’s actions to an individual’s strengths and weaknesses. In this study, participants solved grid-based logic puzzles with the help of a personalized or non-personalized robot tutor. Participants’ puzzle solving times were compared between two non-personalized control conditions and two personalized conditions (n=80). Although the robot’s personalizations were less sophisticated than what a human tutor can do, we still witnessed a “one-sigma” improvement (68th percentile) in post-tests between treatment and control groups. We present these results as evidence that even relatively simple personalizations can yield significant benefits in educational or assistive human-robot interactions. Categories and Subject Descriptors I.2.9 [Artificial Intelligence]: Robotics; J.4 [Computer Applications]: Social And Behavioral Sciences—Psychology General Terms Experimentation

Tega: A Social Robot

Tega is a new expressive “squash and stretch”, Android-based social robot platform, designed to enable long-term interactions with children.

Affect and Inference in Bayesian Knowledge Tracing with a Robot Tutor

In this paper, we present work to construct a robotic tutoring system that can assess student knowledge in real time during an educational interaction. Like a good human teacher, the robot draws on multimodal data sources to infer whether students have mastered language skills. Specifically, the model extends the standard Bayesian Knowledge Tracing algorithm to incorporate an estimate of the students affective state (whether he/she is confused, bored, engaged, smiling, etc.) in order to predict future educational performance. We propose research to answer two questions: First, does augmenting the model with affective information improve the computational quality of inference? Second, do humans display more prominent affective signals in an interaction with a robot, compared to a screen-based agent? By answering these questions, this work has the potential to provide both algorithmic and human-centered motivations for further development of robotic systems that tightly integrate affect understanding and complex models of inference with interactive, educational robots.