Xianfeng Ye
Papers
1
Total Citations
16
H-Index
1
About
Xianfeng Ye is a robotics researcher whose work centers on intelligent grasping, active learning, and scene understanding in cluttered environments. His most cited paper, "Discriminative Active Learning for Robotic Grasping in Cluttered Scene" (2023, 16 citations), tackles a critical bottleneck in deep learning-based grasp detection: the prohibitive cost of data annotation. Ye proposes a discriminative active learning framework that intelligently selects the most informative unlabeled samples for human labeling, dramatically reducing the need for massive annotated datasets while maintaining high grasp success rates. This work addresses the fundamental challenge of generalizing robotic manipulation across diverse, unseen object shapes. By bridging active learning and robotic grasping, Ye's contributions enable more sample-efficient, cost-effective training pipelines—a crucial step toward deploying adaptable robots in real-world settings like warehouses and homes. His research highlights the synergy between machine learning efficiency and physical robot performance, positioning him as a key voice in making robotic manipulation more practical and scalable.
Research Focus
Key Achievements
Top Papers
- 1Discriminative Active Learning for Robotic Grasping in Cluttered Scene16 citations · 2023