• p. sakthiprakash
• p. sakthiprakash

Abstract Background: In robotics and artificial intelligence (AI) have played the main role in education sector, particularly the development of robotic educators. These organizations seek to transform traditional teaching by delivering lessons on digital whiteboards as well as adapting teaching strategies based on student engagement and attention. Despite progress, the contest of seamlessly integrating hardware components and AI-driven software to create adaptive, real-time teaching systems seems to be a research attention. Methods: This study refer to an embedded based teaching contruction that combines embedded based hardware with Python software and uses reinforcement learning techniques to provide adaptive and personalised instruction. The evaluation of the proposed AI-powered robotic educator system was conducted using a custom-built dataset designed to mimic real-world classroom environments. This dataset encompasses visual cues from students, captured through a web camera, to analyze engagement and attention levels effectively. The system uses Convolutional Neural Networks (CNNs) technique for real-time attention analysis, allowing the robot to evaluate student engagement by monitoring visual cues such as eye gaze and facial expressions. The robotic educator uses Open-CV is used for video input processing and dynamically adjusts its teaching policies, such as lesson pace and delivery, based on the reinforcement learninglooping technique. The prototypical also allows for interactive digital board presentations, resulting in an adaptable classroom environment. Results: The real time based conducted experimental results presented those robotic command system outcomes. The reinforcement learning model allowed the robot to effectively adapt its teaching style, resulting in a 35% increase in student engagement and a 25% improvement in academic performance over traditional methods. Furthermore, the digital board integration better the clarity as well as accessibility of lessons, contributing to improved comprehension and retention among students. Conclusion: This study illustrates the educational scheme by using robotics and AI in education. By combining RL for personalised instruction after that the remaing part of technique as deep learning CNNs for real-time visual representations attention analysis (inspecting by we camera), the proposed model provides an adaptive teaching solution. The findings demonstrate such systems' ability to increase educational results and pave route for the widespread use of robotic educators in modern classrooms in both schools and colleges

Keywords: Embedded system, Reinforcement Learning Models based robotic educator, python besides Computer Vision (open-cv), education knowledge, python and Convolutional Neural Networks.

"Integrating Embedded Systems, Reinforcement Learning Models, and OpenCV-Based Web Camera Interaction for Personalized Teaching", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.c406-c413, December-2024, Available :http://www.jetir.org/papers/JETIR2412244.pdf

"Integrating Embedded Systems, Reinforcement Learning Models, and OpenCV-Based Web Camera Interaction for Personalized Teaching", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppc406-c413, December-2024, Available at : http://www.jetir.org/papers/JETIR2412244.pdf