Human-Robot Interaction: A ROS2-Based Approach with Voice and Vision Integration

This project enhances human-robot interaction (HRI) by incorporating cutting-edge sensory feedback systems, real-time processing, and an intuitive architecture. A modular, scalable system architecture, developed using ROS2, integrates voice and vision systems to enable robots to execute commands precisely and interact seamlessly with users. Key contributions of this research include the fusion of voice and vision capabilities, the creation of a real-time audio segmentation algorithm, and the design of a flexible state machine controller. These outcomes highlight the potential of advanced HRI technologies and lay a strong foundation for future innovations.