Skip to main content Skip to navigation

A Study on AI-FML Robotic Agent for Student Learning Behavior Ontology Construction

Project Overview

The document explores the implementation of a generative AI-FML robotic agent aimed at enhancing educational outcomes in English speaking and listening domains by constructing a student learning behavior ontology. It details the architecture of the robotic agent, which integrates perception, cognition, and computational intelligence to facilitate student interaction. The study highlights the agent's deployment in co-learning environments in Taiwan and Japan, where it has been successfully tested. Key applications of this technology include fostering collaborative learning experiences and adapting to individual student needs, ultimately aiming to improve engagement and comprehension in language acquisition. The findings indicate that such AI-driven tools can significantly enrich the learning experience by promoting active participation and personalized learning pathways. Overall, the document underscores the potential of generative AI in transforming educational practices through innovative, interactive technologies that support both teachers and students in achieving better learning outcomes.

Key Applications

AI-FML robotic agent for student learning behavior ontology construction

Context: Applied in English speaking and listening domains in elementary and junior high schools in Taiwan and Japan.

Implementation: The AI-FML robotic agent interacts with students through a cloud-based system, allowing real-time feedback and assessment of student learning behavior.

Outcomes: Students engaged in co-learning with the robot, leading to enhanced learning experiences and improved performance in speaking and listening.

Challenges: Potential limitations in accurately recognizing speech and adapting to diverse learning needs.

Implementation Barriers

Technical Barrier

Challenges in speech recognition and effective adaptation to various student learning behaviors.

Proposed Solutions: Improving the AI algorithms for better accuracy in recognizing speech and personalizing learning experiences.

Implementation Barrier

Need for adequate resources and training for teachers to effectively integrate the robotic agent into the classroom.

Proposed Solutions: Providing professional development and ongoing support for teachers.

Project Team

Chang-Shing Lee

Researcher

Mei-Hui Wang

Researcher

Wen-Kai Kuan

Researcher

Zong-Han Ciou

Researcher

Yi-Lin Tsai

Researcher

Wei-Shan Chang

Researcher

Lian-Chao Li

Researcher

Naoyuki Kubota

Researcher

Tzong-Xiang Huang

Researcher

Eri Sato-Shimokawara

Researcher

Toru Yamaguchi

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Chang-Shing Lee, Mei-Hui Wang, Wen-Kai Kuan, Zong-Han Ciou, Yi-Lin Tsai, Wei-Shan Chang, Lian-Chao Li, Naoyuki Kubota, Tzong-Xiang Huang, Eri Sato-Shimokawara, Toru Yamaguchi

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies