Chengyuan Liu
Papers
3
Total Citations
16
H-Index
3
About
Chengyuan Liu is a rising researcher at the forefront of human-robot interaction and imitation learning, with a focus on making robots more dexterous and collaborative. His work centers on two key challenges: enabling robots to learn from diverse human behaviors and collecting high-quality human demonstration data for robot training. Liu’s major contributions include Co-GAIL (2021), a method for learning robust human-robot collaboration policies from human-human demonstrations, which allows robots to adapt to varied human strategies during online tasks. He also developed ARCap (2025), an augmented reality feedback system for collecting high-quality human demonstrations, and DexCap (2024), a scalable, portable motion capture system for dexterous manipulation. These innovations address critical bottlenecks in robot learning, from data collection to policy generalization. With over 16 citations across his most-cited papers, Liu’s work is gaining traction for its practical impact on real-world robot training. His notable achievements include advancing the scalability of hand motion capture and creating frameworks that enable robots to learn from natural human interactions, positioning him as a key contributor to the next generation of collaborative and dexterous robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration6 citations · 2021
- 3