Dongzhe Zheng
Papers
4
Total Citations
35
H-Index
3
About
Dongzhe Zheng is a pioneering robotics researcher whose work sits at the intersection of tactile sensing, deformable object manipulation, and visual-physical modeling. His most impactful contribution, "Capturing forceful interaction with deformable objects using a deep learning-powered stretchable tactile array" (2024, 24 citations), introduces a groundbreaking visual-tactile system that reconstructs full hand-object states during manipulation—a critical advance for virtual reality, telemedicine, and robotics. This work addresses the long-standing challenge of occluded object deformations by integrating deep learning with stretchable tactile arrays. Zheng further advances the field through "Differentiable Cloth Parameter Identification and State Estimation in Manipulation" (2024, 6 citations), which tackles the near-infinite degrees of freedom problem in cloth dynamics. His UniFolding system (2023, 3 citations) demonstrates remarkable sample efficiency and scalability in robotic garment folding through the UFONet neural network, while his latest work, ArtGS (2025, 2 citations), extends 3D Gaussian Splatting to enable interactive visual-physical modeling of articulated objects. Collectively, Zheng's research bridges the gap between perception and physical interaction, creating systems that understand and manipulate the complex, deformable world around us—a vision that promises to transform how robots handle everything from surgical tools to household fabrics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4