Papers
5
Total Citations
66
H-Index
4
About
Yinlin Li is a leading researcher in robotic manipulation, with a focus on multifingered dexterous hands, pre-grasp manipulation, and egocentric perception. Their work bridges biological inspiration and machine learning to solve fundamental challenges in robot grasping. Li’s 2022 survey on multifingered robotic manipulation (28 citations) provides a comprehensive overview of biological results, structural evolutions, and learning methods, highlighting the enduring complexity of achieving human-like dexterity. A key contribution is their pioneering work on pre-grasp manipulation for flat objects—such as books and disks—in cluttered environments, where they introduced sliding primitives and binary mask learning to enable robots to rearrange and grasp objects that are otherwise inaccessible due to gripper width limits. Li has also advanced hand segmentation in egocentric images using unsupervised and semi-supervised methods with noisy label learning (25 citations), improving human-robot interaction. Their research on grasp type understanding, including classification and clustering, further supports robot self-learning. With a growing citation impact and a focus on practical, real-world manipulation, Li’s work is shaping the next generation of autonomous robotic hands.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Grasp type understanding — classification, localization and clustering3 citations · 2016