Proposal of Learning Support Model for Teacher-Type Robot Supporting Learning According to Learner’s Perplexed Facial Expressions

The introduction of ICT into education in educational settings has become increasingly common. Among these, the research and development of educational support robots have attracted attention. Conventional robots provide academic support through button operation by the learner. However, it has been reported that excessive requests for academic support can be problematic in environments in which learners can freely request academic support. To solve this problem, we developed a perplexion estimation method that estimates the state of perplexion from the learner’s facial expression. When educational support is provided using the proposed method, the robot can autonomously provide academic support. Simulation experiments demonstrated that the perplexion estimation method has the potential to accurately estimate the learner’s state. However, there is still no dedicated model for educational support robots that utilizes the perplexion estimation method. Therefore, this paper proposes an apprenticeship promotion model that integrates a learning support method based on cognitive apprenticeship theory and our perplexion estimation method. We then verified the learning effects of the robot equipped with the proposed model on the learner through participant experiments. The experimental results suggest that the robot equipped with the proposed model not only provides the same learning effect to university students as a conventional robot, but also can autonomously provide academic support at the optimal timing.