Yingyi Kuang

Papers

Total Citations

H-Index

About

Yingyi Kuang is a robotics researcher whose work bridges the critical gap between human dexterity and robotic manipulation. Her primary research areas include human-object interaction, robot manipulation, and reinforcement learning for multi-goal tasks. Kuang’s most notable contribution is her comprehensive study of how humans use their hands during object interaction, which she translates into actionable frameworks for robotic systems—work that has garnered 24 citations and is foundational for enabling robots to operate effectively in human-centric environments. Additionally, she has advanced reinforcement learning by developing a Goal Density-based Hindsight Experience Prioritization method, which significantly accelerates learning in sparse-reward, multi-goal manipulation tasks, earning 11 citations. This innovation addresses a key bottleneck in robotics: the need for millions of data points before a stable policy emerges. Kuang’s research is particularly impactful for students and engineers working on autonomous systems, as it provides both theoretical insights and practical algorithms for creating more adaptive, human-like robotic hands. Her work stands out for its focus on real-world applicability, pushing the boundaries of what robots can achieve in unstructured human spaces.