Papers
3
Total Citations
182
H-Index
3
About
Ning Jin is a robotics researcher whose work lies at the intersection of manipulation, deformable object modeling, and human-machine interaction. Her most significant contribution is in the domain of deformable linear object manipulation, where she pioneered a self-supervised learning framework for state estimation. This approach, detailed in her highly cited 2020 paper (165 citations), leverages a state-space representation of the physical system, enabling robots to visually estimate and control the shape of cables, ropes, and wires without extensive manual labeling. By incorporating physics priors into the dynamics model, Jin’s method achieves robust, model-based manipulation that is both data-efficient and generalizable. Her earlier work (2019, 10 citations) laid the groundwork for this paradigm. More recently, Jin has expanded into human-machine interaction, developing quasi-homogeneous iontronic sensors with an ultrawide sensing range (2024, 7 citations), demonstrating her versatility in bridging soft sensing with robotic control. Her research is notable for its practical impact on manufacturing and assistive robotics, where precise handling of deformable objects remains a critical challenge.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3