Yuh-Lin Chang

Papers

Total Citations

H-Index

About

Yuh-Lin Chang is a pioneering researcher in robotics and computer vision, whose work has fundamentally advanced the calibration of vision-based robotic systems. His primary research areas include hand-eye coordination, adaptive self-calibration, and recursive camera calibration for robot platforms. Chang's most significant contribution is the development of an adaptive self-learning process for dynamically calibrating the transformation between camera space and robot space, introduced in his seminal 1989 paper (35 citations). This work enabled robots to continuously learn and adjust their visual feedback without human intervention, a breakthrough for autonomous systems. He further extended this research by addressing recursive calibration techniques (2003, 8 citations), which allow for real-time camera updates that enhance image processing and enable in-situ calibration. Chang also tackled the challenging problem of calibrating mobile cameras' extrinsic parameters relative to their platforms (2002, 5 citations), overcoming limitations of traditional hand-eye algorithms that required fixed robot hands. His cumulative work has laid the foundation for modern autonomous robotics, influencing fields from industrial automation to mobile robotics. With a career spanning over two decades, Chang's innovative calibration methods remain essential reading for researchers developing self-adaptive robotic systems.