Xueyang Yao
Papers
2
Total Citations
16
H-Index
2
About
Xueyang Yao is a leading researcher in imitation learning and robotic manipulation, with a focus on bridging the gap between human demonstrations and autonomous robot performance. Their key contributions center on improving generalization in probabilistic movement primitives, enabling robots to adapt manipulation trajectories to unseen object locations and via-point constraints—a critical advance for real-world tasks. Yao’s 2023 paper on this topic has already garnered 11 citations, reflecting its impact on the field. Additionally, Yao spearheaded the creation of a landmark dataset of 37,000 human-planned robotic grasps with six degrees of freedom (2020), a resource that has become foundational for studying grasp planning failures and advancing data-driven approaches. This work, cited 5 times, highlights Yao’s commitment to addressing practical limitations in deep learning-based grasping, where models still fail roughly once per ten attempts. By combining rigorous empirical analysis with innovative algorithmic solutions, Yao has established themselves as a key figure in making robotic manipulation more robust and generalizable—a vital step toward deploying robots in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1
- 237,000 Human-Planned Robotic Grasps With Six Degrees of Freedom5 citations · 2020