Hengxu Yan
Papers
4
Total Citations
232
H-Index
3
About
Hengxu Yan is a leading researcher in robotic manipulation, with a primary focus on developing robust, human-like grasping systems for both static and dynamic environments. His most significant contribution is the **AnyGrasp** framework, a groundbreaking approach to grasp perception that operates seamlessly across spatial and temporal domains. This work, which has garnered over 210 citations, addresses the critical challenge of enabling robots to grasp objects with the same promptness, accuracy, and flexibility as humans. Yan’s research extends to **reactive grasping** for dynamic objects, where he introduced a target-referenced method that ensures semantic consistency in predicted grasps, a key advancement over prior temporal-smoothing techniques. More recently, he has explored efficient representations for multi-finger grasping, tackling the complexity of handling diverse objects in cluttered, real-world settings. Yan’s work is foundational for advancing prehensile manipulation, bridging the gap between robotic and human dexterity, and his high-impact publications reflect his role as a key innovator in the field of robotic perception and control.
Research Focus
Key Achievements
Top Papers
- 1AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains210 citations · 2023
- 2Target-referenced Reactive Grasping for Dynamic Objects16 citations · 2023
- 3
- 4A Surprisingly Efficient Representation for Multi-Finger Grasping2 citations · 2024