Mingliang Fu

Shenyang Institute of Automation, University of Chinese Academy of Sciences

Papers

Total Citations

H-Index

About

Mingliang Fu is a researcher specializing in robotics and human-robot interaction, with a focus on learning from demonstration (LfD) and action recognition. His work bridges the gap between human cognitive strategies and autonomous robotic systems, particularly in obstacle avoidance and movement analysis. In his 2016 study, Fu proposed a novel obstacle avoidance learning framework based on mixture models, enabling robots to imitate human decision-making mechanisms for safer navigation. This work, cited 13 times, laid groundwork for adaptive robotic behavior. He further advanced the field with his 2017 research on robust human action recognition, using dynamic movement features to improve accuracy in interpreting human gestures and motions—a critical component for intuitive human-robot collaboration. Though early in his career, Fu’s contributions are shaping how robots learn from human demonstrations, with potential applications in assistive robotics and autonomous systems. His research highlights the importance of blending statistical modeling with behavioral imitation, offering a pathway toward more responsive and intelligent machines.