Papers
8
Total Citations
159
H-Index
5
About
Chun‐Yi Lee is a leading researcher at the intersection of robotics, computer vision, and artificial intelligence, with a primary focus on bridging the gap between simulation and real-world deployment. His most influential work, "Virtual-to-Real: Learning to Control in Visual Semantic Segmentation" (69 citations), addresses the critical challenge of training robots in safe, simulated environments before transferring skills to physical systems—a paradigm that reduces both cost and risk. Lee has also pioneered efficient deep neural network design for edge computing (50 citations), enabling resource-constrained devices like UAVs to perform complex computations. His recent contributions include CathSim (2024), an open-source simulator for autonomous endovascular surgery, and innovative frameworks for swarm robotics using large language models and diffusion-based networks for precise robotic manipulation. Lee’s work on adversarial exploration strategies for self-supervised learning further demonstrates his commitment to reducing reliance on human demonstrations. With over 150 total citations and a growing portfolio of high-impact publications, Lee is shaping the future of autonomous systems, from industrial automation to medical robotics, making him a key figure in modern robotics research.
Research Focus
Key Achievements
Top Papers
- 1Virtual-to-Real: Learning to Control in Visual Semantic Segmentation69 citations · 2018
- 2
- 3CathSim: An Open-Source Simulator for Endovascular Intervention15 citations · 2024
- 4
- 5Virtual-to-Real: Learning to Control in Visual Semantic Segmentation7 citations · 2018
- 6
- 7Adversarial Exploration Strategy for Self-Supervised Imitation Learning2 citations · 2018
- 8Precise Pick-and-Place using Score-Based Diffusion Networks1 citations · 2024