Yueyan Peng

Papers

Total Citations

H-Index

About

Yueyan Peng is a robotics researcher whose work lies at the intersection of meta-learning, imitation learning, and 6D pose estimation for robotic manipulation. Their research addresses fundamental challenges in enabling robots to learn and adapt to new tasks with minimal demonstrations, particularly in cluttered industrial environments. Peng’s most cited work, “Learning With Dual Demonstration Domains: Random Domain-Adaptive Meta-Learning” (2022, 8 citations), introduces a novel meta-learning framework that allows robots to generalize across different demonstration domains, significantly improving their ability to learn from limited examples. Their earlier paper on “Vision-Based One-Shot Imitation Learning Supplemented with Target Recognition via Meta Learning” (2021, 5 citations) proposes an end-to-end approach that separates object recognition from action execution, enabling robots to imitate tasks after seeing just a single demonstration. In the domain of industrial robotics, Peng’s work on “6D Hybrid Pose Estimation in Cluttered Industrial Scenes for Robotic Grasping” (2022, 4 citations) tackles the persistent challenges of occlusion, symmetry, and texture-less objects, providing robust solutions for real-world manufacturing applications. With a growing citation record and contributions that bridge cutting-edge machine learning techniques with practical robotic systems, Peng is establishing themselves as an emerging voice in the field of robot learning and autonomous manipulation.