Personalized Robot Tutoring Using the Assistive Tutor POMDP (AT-POMDP)

Selecting appropriate tutoring help actions that account for both a student’s content mastery and engagement level is essential for effective human tutors, indicating the critical need for these skills in autonomous tutors. In this work, we formulate the robot-student tutoring help action selection problem as the Assistive Tutor partially observable Markov decision process (AT-POMDP). We designed the AT-POMDP and derived its parameters based on data from a prior robot-student tutoring study. The policy that results from solving the AT-POMDP allows a robot tutor to decide upon the optimal tutoring help action to give a student, while maintaining a belief of the student’s mastery of the material and engagement with the task. This approach is validated through a between-subjects field study, which involved 4th grade students (n=28) interacting with a social robot solving long division problems over five sessions. Students who received help from a robot using the AT-POMDP policy demonstrated significantly greater learning gains than students who received help from a robot with a fixed help action selection policy. Our results demonstrate that this robust computational framework can be used effectively to deliver diverse and personalized tutoring support over time for students.

[1]  K. VanLehn.  The Relative Effectiveness of Human Tutoring, Intelligent Tutoring Systems, and Other Tutoring Systems , 2011 .

[2]  Brian Scassellati,et al.  Transparent role assignment and task allocation in human robot collaboration , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[4]  Brian Scassellati,et al.  Give Me a Break! Personalized Timing Strategies to Promote Learning in Robot-Child Tutoring , 2017, 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI.

[5]  John R. Anderson,et al.  Knowledge tracing: Modeling the acquisition of procedural knowledge , 2005, User Modeling and User-Adapted Interaction.

[6]  Brian Scassellati,et al.  Social robots for education: A review , 2018, Science Robotics.

[7]  Gita Reese Sukthankar,et al.  Tractable POMDP representations for intelligent tutoring systems , 2013, TIST.

[8]  Cynthia Breazeal,et al.  Affect-Aware Student Models for Robot Tutors , 2016, AAMAS.

[9]  Michelene T. H. Chi,et al.  Eliciting Self-Explanations Improves Understanding , 1994, Cogn. Sci..

[10]  Takayuki Kanda,et al.  Interactive Robots as Social Partners and Peer Tutors for Children: A Field Trial , 2004, Hum. Comput. Interact..

[11]  Thomas L. Griffiths,et al.  Faster Teaching via POMDP Planning , 2016, Cogn. Sci..

[12]  Mark R. Lepper,et al.  The wisdom of practice: Lessons learned from the study of highly effective tutors. , 2002 .

[13]  J. Gregory Trafton,et al.  Effective Tutoring Techniques: A Comparison of Human Tutors and Intelligent Tutoring Systems , 1992 .

[14]  Brian Scassellati,et al.  Shaping productive help-seeking behavior during robot-child tutoring interactions , 2016, 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[15]  Vincent Aleven,et al.  An effective metacognitive strategy: learning by doing and explaining with a computer-based Cognitive Tutor , 2002, Cogn. Sci..

[16]  Morgan Quigley,et al.  ROS: an open-source Robot Operating System , 2009, ICRA 2009.

[17]  Kenneth R. Koedinger,et al.  Individualized Bayesian Knowledge Tracing Models , 2013, AIED.

[18]  Tamara van Gog,et al.  Exploring the Assistance Dilemma: Comparing Instructional Support in Examples and Problems , 2014, Intelligent Tutoring Systems.

[19]  Brian Scassellati,et al.  The Physical Presence of a Robot Tutor Increases Cognitive Learning Gains , 2012, CogSci.

[20]  Brian Scassellati,et al.  The Benefits of Interactions with Physically Present Robots over Video-Displayed Agents , 2011, Int. J. Soc. Robotics.

[21]  Ana Paiva,et al.  iCat, the chess player: the influence of embodiment in the enjoyment of a game , 2008, AAMAS.

[22]  Emma Brunskill,et al.  The Impact on Individualizing Student Models on Necessary Practice Opportunities , 2012, EDM.

[23]  A. Renkl.  Worked-out examples: instructional explanations support learning by self- explanations , 2002 .

[24]  Kurt VanLehn,et al.  The Andes Physics Tutoring System: Lessons Learned , 2005, Int. J. Artif. Intell. Educ..

[25]  Pierre Dillenbourg,et al.  When Children Teach a Robot to Write: An Autonomous Teachable Humanoid Which Uses Simulated Handwriting , 2015, 2015 10th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[26]  Kurt VanLehn,et al.  A Comparison of Decision-Theoretic, Fixed-Policy and Random Tutorial Action Selection , 2006, Intelligent Tutoring Systems.