Yinghan Chen
Papers
1
Total Citations
11
H-Index
1
About
Yinghan Chen is a robotics researcher whose work focuses on advancing imitation learning for robotic manipulation. Their key contributions lie in developing methods that enable robots to learn complex manipulation tasks from human demonstrations while achieving robust generalization to novel scenarios. Chen's most cited work, "Improved Generalization of Probabilistic Movement Primitives for Manipulation Trajectories" (2023), addresses a critical limitation in existing imitation learning approaches: the inability to extrapolate beyond demonstrated conditions, such as unseen object locations or via-point modulations. By enhancing probabilistic movement primitives, Chen's research allows robots to adapt learned trajectories to new environments without requiring exhaustive retraining. This work has garnered 11 citations, reflecting its growing influence in the field. Chen's research is particularly valuable for real-world applications where robots must operate flexibly in dynamic settings. Their contributions represent an important step toward more adaptable and generalizable robotic systems, bridging the gap between controlled demonstrations and practical deployment in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1