FML-based Intelligent Agent for Robotic e-Learning and Entertainment Application
Chang-Shing Lee, Mei‐Hui Wang, Yi-Lin Tsai, Rin-Pin Chang, Lian‐Chao Li, Noriko Takese, Shion Yamamoto, Naoyuki Kubota · 2019
This paper proposes a fuzzy markup language (FML)-based intelligent agent for robotic e-learning and entertainment application. We develop a robotic partner system with a robot teacher iPhonoid to interact with students in the classroom to collect students' feedback on the developed iOS app. In this way, the human teachers can make sure that students in their classes whether understand the lesson or not. In addition, we future embed the developed feedback app function to the novel FML-based intelligent agent with the robot Zenbo for music listening application and edutainment. The developed agent converts human brainwaves into physiological indices and infers subjects' feeling while they are listening to music based on the constructed knowledge base (KB) and rule base (RB) of FML. Then the human sends real-time feedback to the FML-based intelligent agent. Furthermore, the genetic algorithm is utilized for personalized learning the KB and RB of FML tool. The experimental results show that the proposed approach is feasible for e-learning and music application. In the future, we will introduce the robot partner system into the teaching field to have more interaction with children to increase their learning simulations.