Zhefan Ye
Papers
4
Total Citations
42
H-Index
4
About
Zhefan Ye is a robotics researcher whose work lies at the intersection of perception, manipulation, and security. His primary research focuses on developing robust perception systems for robots operating in uncertain and adversarial environments. Ye’s most influential contribution is the GRIP framework (Generative Robust Inference and Perception), which enables semantic robot manipulation even under adversarial conditions—a critical step toward deploying autonomous systems in real-world, high-stakes settings. His work on robust object estimation using generative-discriminative inference addresses fundamental vulnerabilities in CNN-based perception, proposing methods to make robots more resilient to uncertainty and attack. More recently, Ye has explored human-in-the-loop pose estimation via shared autonomy, tackling the challenge of dexterous manipulation by balancing human input with robotic automation. With his top-cited paper accumulating 26 citations, Ye’s research is steadily gaining recognition for its practical relevance to secure, reliable robotics. His contributions are particularly valuable for students and researchers interested in perception under uncertainty, adversarial machine learning, and human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Human-in-the-loop Pose Estimation via Shared Autonomy4 citations · 2021