Bondhu: An IoT-Enabled Humanoid Robot with Real-Time Voice Controland Face Recognition Capabilities

الملخص

The convergence of the Internet of Things (IoT), computer vision, and natural language processing (NLP) has hastened the development of intelligent robotic systems capable of interacting with humans and the environment seamlessly. This paper presents a novel IoT-based robotic platform incorporating real-time voice control and adaptive face recognition to improve autonomy, contextual awareness, and user interaction. The system architecture includes an Arduino UNO microcontroller, servo actuators, microphone, speaker, LCD display, camera module, and onboard processing unit for local processing. The robot can recognize voice commands and change its behavior dynamically based on the recognized person using speech recognition and deep learning-based face recognition, which makes the operation hands-free and intuitive. Onboard speech emotion recognition was achieved using Edge Impulse, and cloud-based environmental monitoring and data analysis were realized using ThingSpeak and Microsoft Power BI. Experimental trials validate high command recognition accuracy, strong face detection under varying light conditions, and successful completion of high-level tasks such as object detection, navigation, and human interaction. This architecture is modular, low-cost, and extensible, with excellent potential value for application in assistive robotics, home automation, and factory automation. This research brings human-robot interaction to the next level by showing how IoT and AI can be integrated in a comprehensive manner to create smart, interactive robots.