Xuechun Qiao
Papers
4
Total Citations
20
H-Index
3
About
Xuechun Qiao is pioneering the integration of machine learning with industrial robotics to create systems that are not only precise but also adaptive in real time. Their research centers on robot dynamics identification, adaptive control, and advanced sensor calibration—critical areas for enabling robots to handle unstructured environments and complex tasks. Qiao’s most impactful work, "Deep adaptive control with online identification for industrial robots" (2022, 10 citations), introduces a framework that combines deep learning with real-time parameter estimation, allowing robots to adjust their control strategies on the fly without manual retuning. This is complemented by a two-stage Bayesian approach for rapid dynamics identification (2024), which significantly reduces the computational burden of model updating. In sensor innovation, Qiao developed the "Fibertouch" tactile sensor (2025), a fiber-optic system paired with deep learning demodulation for dexterous robotic hands, and the SDI method (2024) for sparse drift identification in force/torque sensor calibration. These contributions directly address the industry’s need for robust, self-calibrating robots. With a growing citation footprint, Qiao is establishing a reputation for bridging theoretical control methods with practical, deployable solutions in industrial automation.
Research Focus
Key Achievements
Top Papers
- 1Deep adaptive control with online identification for industrial robots10 citations · 2022
- 2
- 3
- 4