Robots in the classroom: Learning to be a Good Tutor

To broaden the adoption and be more inclusive, robotic tutors need to tailor their behaviours to their audience. Traditional approaches, such as Bayesian Knowledge Tracing, try to adapt the content of lessons or the difficulty of tasks to the current estimated knowledge of the student. However, these variations only happen in a limited domain, predefined in advance, and are not able to tackle unexpected variation in a student's behaviours. We argue that robot adaptation needs to go beyond variations in preprogrammed behaviours and that robots should in effect learn online how to become better tutors. A study is currently being carried out to evaluate how human supervision can teach a robot to support child learning during an educational game using one implementation of this approach.

[1]  Ana Paiva,et al.  Modelling empathic behaviour in a robotic game companion for children: An ethnographic study in real-world settings , 2012, 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[2]  B. Bloom.  The 2 Sigma Problem: The Search for Methods of Group Instruction as Effective as One-to-One Tutoring , 1984 .

[3]  Brian Scassellati,et al.  Personalizing Robot Tutors to Individuals’ Learning Differences , 2014, 2014 9th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[4]  Ana Paiva,et al.  Learning by Teaching a Robot: The Case of Handwriting , 2016, IEEE Robotics & Automation Magazine.

[5]  Pieter Abbeel,et al.  Apprenticeship learning via inverse reinforcement learning , 2004, ICML.

[6]  Tony Belpaeme,et al.  The Robot Who Tried Too Hard: Social Behaviour of a Robot Tutor Can Negatively Affect Child Learning , 2015, 2015 10th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[7]  Cynthia Breazeal,et al.  Bayesian Active Learning-Based Robot Tutor for Children's Word-Reading Skills , 2015, AAAI.

[8]  Stefan Kopp,et al.  Adaptive Robot Language Tutoring Based on Bayesian Knowledge Tracing and Predictive Decision-Making , 2017, 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI.

[9]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[10]  Tony Belpaeme,et al.  A touchscreen-based ‘Sandtray’ to facilitate, mediate and contextualise human-robot social interaction , 2012, 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[11]  Tony Belpaeme,et al.  Supervised autonomy for online learning in human-robot interaction , 2017, Pattern Recognit. Lett..

[12]  Tony Belpaeme,et al.  SPARC: Supervised Progressively Autonomous Robot Competencies , 2015, ICSR.

[13]  Tony Belpaeme,et al.  Toward Supervised Reinforcement Learning with Partial States for Social HRI , 2017, AAAI Fall Symposia.

[14]  Stefan Kopp,et al.  Guidelines for Designing Social Robots as Second Language Tutors , 2018, International Journal of Social Robotics.

[15]  Ginevra Castellano,et al.  Discovering social interaction strategies for robots from restricted-perception Wizard-of-Oz studies , 2016, 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI).