Quanzhou Li

University of Toronto

Papers

2

Total Citations

47

H-Index

2

About

Quanzhou Li is a leading researcher in robot learning and manipulation, with a focus on bridging the gap between human demonstrations and robotic skill acquisition. His most notable contribution is the "Learning by Watching" (LbW) framework, which enables robots to physically imitate complex manipulation skills directly from human videos. This work, published in 2021 and garnering over 43 citations, addresses a fundamental challenge in robotics: how to transfer dexterous human behaviors to robots without explicit mathematical programming. By leveraging natural visual data, LbW allows robots to learn a wide range of tasks through observation alone, significantly reducing the need for manual specification. Li’s research has profound implications for making robotic systems more accessible and adaptable in real-world environments, from manufacturing to domestic assistance. His work stands out for its practical approach to imitation learning, offering a scalable pathway for robots to acquire skills by simply watching humans. Li’s contributions are shaping the future of autonomous manipulation, inspiring new directions in learning from visual demonstrations.

Research Focus

Key Achievements

2
H-Index
2
Papers
47
Total Citations
24
Avg Citations/Paper
🏆 Most Cited Paper
Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos
43 citations · 2021
📈 Most Prolific Year: 2021 (2 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: University of Toronto

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago