Papers
6
Total Citations
62
H-Index
3
About
Joong-Jae Lee is a leading researcher in humanoid robotics, with a primary focus on robot vision, calibration, and human-robot interaction. His most significant contribution lies in advancing **head-eye calibration** for humanoid robots, developing methods that precisely align a robot’s visual sensors with its physical movements. His seminal 2010 paper on the "Minimum Variance method" for robot head-eye calibration (27 citations) introduced a robust technique for estimating the transformation between a robot's coordinate frame and its camera, a foundational step for reliable vision-guided behavior. Lee further refined this work in 2018 with a stereo camera approach using surface normal vectors, offering a globally optimal and intuitive calibration solution. Beyond calibration, he contributed to the design of the **MAHRU-M** mobile humanoid platform (2011, 20 citations), which featured a dual-network control system for coordinated task execution. His research also explores cognitive robotics, including vision-based attentiveness determination using Hidden Markov Models (2019), aiming to enable robots to identify and respond to human focus during interaction. With a career spanning distributed control systems and visual servoing, Lee’s work has been instrumental in bridging the gap between mechanical precision and intelligent, interactive behavior in humanoid robots.
Research Focus
Key Achievements
Top Papers
- 1Robot Head-Eye calibration using the Minimum Variance method27 citations · 2010
- 2
- 3
- 4
- 5
- 6Coordinated task execution by humanoid robot2 citations · 2009