Our research focuses on artificial intelligence (AI) for robotics, with an emphasis on robotic manipulation in complex, unstructured environments. We integrate vision-language models and context-aware learning to enable robust and adaptable robotic behavior. We are also actively exploring surgical scene understanding, including instrument segmentation, surgical workflow recognition, and anticipation.
Background
Research Interests: Robotic manipulation and embodied intelligence, Surgical video analysis and instrument segmentation, Vision-language integration, Context-aware and generative learning, Scalable data generation and scene understanding.
Miscellany
Lab Activities include KRoC 2025, Microsurgery Workshop 2024, KRoC 2024.