<![CDATA[The rapid advancement of artificial intelligence (AI) has driven significant developments in social robotics, particularly in enabling more natural and intuitive human-robot interaction (HRI). However, current social robots often struggle to interpret multimodal human input effectively, leading to limited contextual understanding and reduced interaction quality. This study addresses these challenges by integrating computer vision (CV) and natural language processing (NLP) to enhance robots’ perceptual and communicative capabilities. The primary aim is to design and evaluate an interaction framework that allows social robots to recognize human emotions, gestures, and spoken language more accurately, thereby improving the fluency of HRI. A mixed-methods approach was employed, combining experimental implementation with qualitative user studies. The system architecture integrates real-time image recognition, gesture tracking, and speech understanding modules, which were tested through laboratory simulations involving 50 participants in controlled social scenarios. The results demonstrate that robots equipped with CV and NLP modules achieved a 30% improvement in gesture recognition accuracy, a 25% increase in contextual language understanding, and significantly higher user satisfaction scores compared to baseline models. Users reported that the robots exhibited more human-like responsiveness and adaptability in conversational settings. These findings suggest that combining computer vision and NLP substantially improves the naturalness and intuitiveness of human-robot interactions. This research highlights the importance of multimodal AI integration for the next generation of socially intelligent robots and paves the way for applications in healthcare, education, and service industries.]]>
