A Practical Approach to Child-Robot Interaction in the Classroom

Abstract

Although innovation and the support of new technologies are urgently needed to ease the burden on the education system, social robots in schools assisting teachers with educational tasks are still rare. Child-Robot Interaction (CRI) could add an embodied social component to modern multi-modal and multi-sensory learning environments already in use. I connected the social robot Pepper to the Large Language Model (LLM) ChatGPT so that the robot was able to talk about all kinds of topics. In addition, I provided applications with a variety of tasks for interaction with children of different age groups and tested the interaction in real school environments. My goal was to identify suitable application scenarios through practical tests together with interested teachers.