← Search

Xueyang Yao

2 accepted papers

2024

Improved Generalization of Probabilistic Movement Primitives for Manipulation Trajectories

RA-L 2024

Imitation learning methods have proven effective in learning robotic tasks by leveraging multiple human-controlled demonstrations. However, existing approaches often struggle to generalize across a wide range of tasks, such as extrapolating to unseen object locations, incorporating via-point modulat

Cited by 10SourceScholar
2020

37, 000 Human-Planned Robotic Grasps With Six Degrees of Freedom

RA-L 2020

Much recent work in grasp planning has focused on data-driven approaches, using deep learning to map from images to gripper configurations. However, this approach typically fails about once per ten attempts, limiting its practicality. We sought to better understand the degree to which such failures

Cited by 4SourceScholar