Zhuonan Yao
Papers
1
Total Citations
8
H-Index
1
About
Zhuonan Yao is a robotics researcher whose work focuses on enabling robots to perform complex deformable object manipulation through learning from human demonstration. His primary research areas include robotic manipulation of non-rigid materials, task modeling for deformable objects, and imitation learning. Yao's most notable contribution is his pioneering work on teaching robots tabletop knotting tasks, a challenging problem in robotics due to the inherent unpredictability of rope deformation. In his 2019 paper "Learning From Observation of Tabletop Knotting Using a Simple Task Model," which has garnered 8 citations, Yao introduced a novel approach that moves beyond traditional teaching-and-playback methods. By developing a simple yet effective task model that captures the essential structure of knotting actions from human demonstrations, he demonstrated how robots can successfully replicate complex rope manipulation tasks despite the material's variability. This work represents an important step toward enabling robots to handle everyday tasks involving cables, wires, and textiles—materials that remain notoriously difficult for automated systems. Yao's research continues to advance the frontier of robotic dexterity in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1Learning From Observation of Tabletop Knotting Using a Simple Task Model8 citations · 2019