Yao-Xiang Ding
Papers
3
Total Citations
17
H-Index
2
About
Yao-Xiang Ding is a robotics researcher whose work focuses on enabling humanoid robots to perform essential, real-world behaviors with greater autonomy and stability. His primary research areas include bipedal locomotion, balance recovery, and motion learning for humanoid platforms. Ding’s most notable contribution is his work on learning push recovery for bipedal humanoid robots using Dynamical Movement Primitives, a method that allows robots to dynamically adapt to external perturbations—a critical challenge for robots operating in complex, unstructured environments. This paper has garnered 12 citations, reflecting its relevance to the field. He also developed a multi-stage learning approach for efficiently teaching humanoid robots stand-up behavior, reducing reliance on time-consuming key-frame planning and expert knowledge. Additionally, Ding has explored environmental perception using Gaussian process regression, aiming to help humanoids better interpret and act within unpredictable real-world settings. His work bridges the gap between classical motion planning and modern learning-based methods, contributing to more resilient and intelligent humanoid systems. For students and researchers in robotics, Ding’s research offers practical insights into how humanoid robots can learn to move, recover from falls, and perceive their surroundings—key steps toward deploying robots in everyday human environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Humanoid environmental perception with Gaussian process regression2 citations · 2016