Yukai Tang

Papers

Total Citations

H-Index

About

Yukai Tang is a rising researcher in robotics and computer vision, with a primary focus on uncertainty quantification for 6D pose estimation. His most-cited work, "CLOSURE: Fast Quantification of Pose Uncertainty Sets" (2024, 4 citations), introduces a novel framework for characterizing pose uncertainty in SE(3) under unknown-but-bounded measurement noise. By modeling noisy inputs such as keypoints and pose hypotheses, Tang develops a method to compute a Pose Uncertainty Set (PURSE)—a subset of SE(3) containing all plausible 6D poses compatible with the measurements. This contribution is critical for safety-critical applications like autonomous manipulation and augmented reality, where reliable pose estimates are essential. Though early in his career, Tang’s work addresses a fundamental gap in robust perception, offering a fast and principled approach to uncertainty quantification that goes beyond traditional probabilistic methods. His research bridges theoretical rigor with practical efficiency, making it highly relevant for students and engineers working on real-world robotic systems. As citations grow, Tang is poised to become a key voice in certifiably robust perception.