Jun Ni

University of Michigan–Ann Arbor, South China University of Technology

Papers

Total Citations

258

H-Index

About

Jun Ni is a pioneering figure in robotic metrology and manufacturing automation, whose work has fundamentally advanced the precision and reliability of industrial robotic systems. His primary research areas encompass robot calibration, error compensation, and multi-sensor-based process monitoring. Ni’s most influential contribution is his groundbreaking work on nongeometric error identification and compensation for robotic systems through inverse calibration, a 2000 paper that has garnered over 211 citations and remains a cornerstone in the field. This research addressed critical inaccuracies in robotic positioning by modeling and correcting errors beyond traditional geometric parameters, enabling higher precision in manufacturing environments. He further developed a self-calibration method for robotic measurement systems (1999, 35 citations), offering a practical, easy-to-implement technique for on-floor calibration that reduces downtime and enhances productivity. Ni also explored multi-sensor diagnostics, as seen in his analysis of drill failure modes using a robotic end effector (1996), where he integrated thrust, torque, and lateral vibration measurements to detect and diagnose tool failures—a precursor to modern condition monitoring. More recently, he has advanced cooperative control for multi-robot systems, proposing disturbance observer-based learning tracking control (2020) that leverages neural networks for adaptive, collaborative performance. Ni’s work has left a lasting impact on manufacturing science, bridging theory and practice to improve robotic accuracy and efficiency.