Papers
6
Total Citations
136
H-Index
5
About
Xiaocong Li is a researcher at the forefront of intelligent robotics and precision mechatronics, whose work bridges the critical gap between advanced control theory and practical robotic manipulation. His research spans three key areas: data-driven multiobjective control optimization for high-precision systems, robust grasping detection under domain shifts, and adaptive force control for universal robotic grippers. Li’s major contributions include developing a hybrid active-passive robust control framework for flexure-joint gantry robots, achieving exceptional contouring precision for high-speed manufacturing tasks. He also pioneered a grasping detection network that integrates uncertainty estimation for confidence-driven semi-supervised domain adaptation, enabling robots to reliably handle unfamiliar objects with minimal labeled data. His work on variable-stiffness grippers has advanced universal grasping by allowing robots to adapt grip force for objects ranging from fragile to heavy. With over 130 total citations, Li’s most influential paper (53 citations) on data-driven controller optimization for magnetically levitated nanopositioning systems has set new benchmarks for model-free precision control. His 2024 study on learning-based high-precision tracking control for spiral scanning demonstrates his continued leadership in merging machine learning with nanopositioning. Li’s research is essential reading for engineers developing next-generation robotic systems that must operate with both high precision and adaptability in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6