Shutong Zhang
Papers
1
Total Citations
24
H-Index
1
About
Shutong Zhang is a rising force in robotics and dexterous manipulation, whose work redefines how machines learn to grasp. Her research centers on differentiable simulation, contact-rich manipulation, and the intersection of machine learning with physical interaction—pushing the boundaries of what robotic hands can achieve. Zhang’s most notable contribution, “Fast-Grasp’D: Dexterous Multi-finger Grasp Generation Through Differentiable Simulation” (2023, 24 citations), tackles a persistent challenge: generating high-quality training data for multi-finger grasping. Traditional methods rely on hard-to-transfer human data or synthetic data with limiting assumptions. By making grasp simulation differentiable and contact dynamics amenable to gradient-based optimization, Zhang’s approach enables robots to learn more robust, adaptable grasps directly through simulation, bypassing data bottlenecks. This work has already garnered attention for its potential to accelerate progress in prosthetics, automation, and human-robot interaction. Though early in her career, Zhang’s innovative methodology—merging simulation fidelity with optimization efficiency—marks her as a key contributor to the next generation of dexterous robotics. Her research promises to unlock more natural, versatile robotic hands, making her a researcher to watch in the field.
Research Focus
Key Achievements
Top Papers
- 1