Fei Hongyi
Papers
2
Total Citations
68
H-Index
2
About
Fei Hongyi is a leading researcher in the field of robotic dexterous manipulation, with a core focus on integrating tactile sensing and deep learning to enable human-like object handling. His major contributions lie in developing novel frameworks for multi-fingered in-hand manipulation that adapt to diverse object properties. By pioneering the use of Graph Convolutional Networks (GCNs) and distributed tactile sensors, Hongyi has addressed the critical challenge of achieving stable, adaptive grasps with hands that feature sensors of varying sizes and shapes. His work on tactile transfer learning further demonstrates his impact, employing morphology-specific Convolutional Neural Networks (CNNs) to allow a multi-fingered hand to effectively explore and recognize objects through touch alone. With his most-cited paper accumulating 46 citations since 2022, Hongyi’s research is rapidly shaping the future of autonomous robotic interaction. His achievements highlight a path toward robots that can seamlessly manipulate unknown objects, bridging the gap between rigid automation and the nuanced, sensory-rich capabilities of the human hand.
Research Focus
Key Achievements
Top Papers
- 1
- 2