Robots and Children that Learn Together : Improving Knowledge Retention by Teaching Peer-Like Interactive Robots

2025-06-23

AI Summary

Prior studies predominantly rely on scripted or “Wizard-of-Oz” simulations, lacking empirical investigation of autonomous social robots serving as peer tutors in real classroom settings with live, bidirectional interaction. Method: This work proposes an interactive reinforcement learning (IRL)-based peer-teaching framework, enabling the first parallel deployment of multiple autonomous social robots in elementary classrooms to support children’s language learning through “teaching the robot.” Robots dynamically adapt their behavior in real time using children’s feedback as reward signals, fostering bidirectional cognitive co-regulation. Contribution/Results: Children teaching the robots demonstrated significantly greater knowledge retention in vocabulary and grammatical reasoning tasks than controls—especially those with low prior knowledge. Concurrently, teaching engagement and metacognitive investment increased. This study advances the “learning-by-teaching” paradigm toward scalable, deployable educational robotics applications.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Natural Language Processing: Safety and Robustness
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Social networks and social learning

Abstract

Despite growing interest in Learning-by-Teaching (LbT), few studies have explored how this paradigm can be implemented with autonomous, peer-like social robots in real classrooms. Most prior work has relied on scripted or Wizard-of-Oz behaviors, limiting our understanding of how real-time, interactive learning can be supported by artificial agents. This study addresses this gap by introducing Interactive Reinforcement Learning (RL) as a cognitive model for teachable social robots. We conducted two between-subject experiments with 58 primary school children, who either taught a robot or practiced independently on a tablet while learning French vocabulary (memorization) and grammatical rules (inference). The robot, powered by Interactive RL, learned from the child's evaluative feedback. Children in the LbT condition achieved significantly higher retention gains compared to those in the self-practice condition, especially on the grammar task. Learners with lower prior knowledge benefited most from teaching the robot. Behavioural metrics revealed that children adapted their teaching strategies over time and engaged more deeply during inference tasks. This work makes two contributions: (1) it introduces Interactive RL as a pedagogically effective and scalable model for peer-robot learning, and (2) it demonstrates, for the first time, the feasibility of deploying multiple autonomous robots simultaneously in real classrooms. These findings extend theoretical understanding of LbT by showing that social robots can function not only as passive tutees but as adaptive partners that enhance meta-cognitive engagement and long-term learning outcomes.

Problem

• Exploring Learning-by-Teaching with autonomous social robots in classrooms
• Developing Interactive Reinforcement Learning for teachable peer-like robots
• Assessing robot-assisted learning impact on children's knowledge retention

Innovation

• Interactive Reinforcement Learning for teachable robots
• Real-time adaptive learning from child feedback
• Multiple autonomous robots in real classrooms