Tony Zheng
Papers
1
Total Citations
3
H-Index
1
About
Tony Zheng is a robotics researcher whose work lies at the intersection of machine learning, control theory, and physical interaction. His most cited paper, "Learning to Play Cup-and-Ball with Noisy Camera Observations" (2020), tackles the challenge of enabling robots to perform precise, dynamic manipulation tasks under real-world uncertainty. By developing a learning-based control strategy that fuses noisy visual feedback with model-based reasoning, Zheng demonstrated how robots can master complex, nonlinear tasks—like the classic cup-and-ball game—that require handling contact forces and precise terminal positioning. While his citation count is still growing, this work has been recognized for its elegant approach to bridging simulation and reality in robotic skill acquisition. Zheng’s research is particularly relevant for students and engineers interested in reinforcement learning for robotics, sensorimotor control, and the practical deployment of AI in unstructured environments. His contributions highlight a key frontier in robotics: teaching machines to learn dexterous, goal-oriented behaviors from imperfect sensory data, moving beyond rigid, pre-programmed motions toward adaptive, human-like manipulation.
Research Focus
Key Achievements
Top Papers
- 1Learning to Play Cup-and-Ball with Noisy Camera Observations3 citations · 2020