Papers
3
Total Citations
26
H-Index
2
About
Yuzhi Lai is an emerging researcher specializing in human–robot interaction (HRI), multimodal communication, and the application of large language models (LLMs) to assistive robotics. His work addresses a critical challenge facing aging societies: enabling intuitive, accessible interaction between elderly users and service robots without requiring complex gestures or specialized syntax knowledge. Lai's most significant contributions center on developing zero-shot HRI frameworks that leverage natural voice and deictic posture — pointing gestures — to allow robots to interpret and execute commands involving previously unseen objects. His NVP-HRI system and its multimodal fusion counterpart both demonstrate how LLMs can bridge the gap between natural human communication and robot understanding, eliminating the need for pre-trained object libraries or rigid command structures. Each of these groundbreaking papers has already attracted 12 citations since their 2025 publication, reflecting rapid recognition within the robotics community. His earlier 2024 work on intuitive multi-modal HRI laid conceptual groundwork for these advances. Together, Lai's research represents a meaningful step toward democratizing human–robot interaction, making service robots genuinely accessible to vulnerable populations who stand to benefit most from this technology.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Intuitive Multi-modal Human-Robot Interaction via Posture and Voice2 citations · 2024