Tiancheng Zhang
University of Michigan–Ann Arbor, Xi’an Jiaotong-Liverpool University
Papers
3
Total Citations
12
H-Index
2
About
Tiancheng Zhang is a robotics researcher whose work sits at the intersection of safe motion planning, robust control, and 3D perception for manufacturing. His primary contributions address one of the field’s most pressing challenges: enabling robotic manipulators to operate safely in real time under real-world uncertainty. In his highly cited 2023 and 2025 papers—“Can’t Touch This” and “Can Not Touch This”—Zhang proposes Autonomous Robust Manipulation via Optimization with Uncertainty (ARM-OU), a framework that guarantees collision avoidance and joint-limit compliance even when the mass and inertia of objects or the robot itself are unknown. These works have accumulated 10 citations in just two years, signaling strong early impact in the safety-critical robotics community. Earlier, Zhang explored deep learning for 3D point cloud recognition in manufacturing, developing a lightweight architecture based on PointNet that efficiently handles object classification and pose estimation. This work bridges perception and control, aiming to make industrial robots more adaptable. With a clear trajectory from perception to real-time robust manipulation, Zhang is establishing himself as a rising voice in autonomous, uncertainty-aware robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3