Jinglue Hang
Papers
4
Total Citations
69
H-Index
4
About
Jinglue Hang is a leading researcher in the field of intelligent robotic manipulation, with a primary focus on enabling dexterous robotic hands to perform human-like, functional grasps. Their work addresses a critical gap in robotics: moving beyond simple stable grasps to task-oriented, functional grasping that supports post-grasp manipulation. Hang’s major contributions include pioneering semantic hand-object representations that allow robots to understand the purpose of a grasp, not just its physical stability. Their highly cited paper, “Toward Human-Like Grasp: Functional Grasp by Dexterous Robotic Hand Via Object-Hand Semantic Representation” (2023, 27 citations), and the subsequent “FunctionalGrasp” study (2023, 23 citations) have set new standards in the field. Hang also developed the “DexFuncGrasp” dataset (2024, 12 citations), a cost-effective real-simulation annotation system that provides a crucial resource for training dexterous grasp generation models. With a growing citation impact and a clear trajectory toward bridging the gap between robotic and human dexterity, Hang’s work is foundational for the next generation of intelligent, task-aware robotic hands.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Hand-object information embedded dexterous grasping generation7 citations · 2023