Papers
12
Total Citations
435
H-Index
9
About
Yuqiang Wu is a robotics researcher whose work spans flexible-joint robot control, teleoperation, human-robot collaboration, and skill learning from demonstration. His research bridges fundamental control theory and applied robotics, with particular emphasis on developing intelligent systems that can interact safely and effectively with humans in real-world environments. Wu's most influential contribution, "End-Effector Force Estimation for Flexible-Joint Robots With Global Friction Approximation Using Neural Networks" (2018, 107 citations), introduced a sophisticated disturbance observer leveraging joint torque sensors and neural networks to achieve precise contact force estimation — a critical capability for safe human-robot interaction. His work on the Mobile Collaborative Robotic Assistant (MOCA) platform, including a widely recognized teleoperation interface (2019, 103 citations) and ergonomic multi-human control frameworks, demonstrated practical advances in mobile manipulation and collaborative robotics at the Istituto Italiano di Tecnologia. Beyond hardware control, Wu has made notable contributions to robot learning, developing frameworks for autonomous impedance regulation through imitation learning and Riemannian-based dynamic movement primitives that enable robots to acquire nuanced human-like stiffness properties during manipulation tasks. His work on quadruped locomotion further reflects his broad interest in compliant, robust robotic systems. Collectively, Wu's research has accumulated hundreds of citations, establishing him as a meaningful contributor to modern collaborative and intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8An Intuitive Formulation of the Human Arm Active Endpoint Stiffness27 citations · 2020
- 9
- 10Development of an industrial robot controller with open architecture5 citations · 2017