Chieh-Hsin Liu
Papers
3
Total Citations
70
H-Index
2
About
Chieh-Hsin Liu is a leading researcher in embodied AI and robot learning, with a focus on bridging the gap between simulation and real-world dexterous manipulation. Their work centers on developing high-fidelity simulation environments and benchmarks that enable robots to master complex, human-centered tasks. Liu’s major contributions include co-creating **iGibson 2.0** (62 citations), an object-centric simulation platform that revolutionized robot learning for everyday household activities by emphasizing interactive, physics-realistic environments beyond simple motion. They further advanced the field with **BEHAVIOR-1K**, a landmark benchmark featuring 1,000 everyday activities grounded in human surveys, providing a comprehensive testbed for embodied AI. In **Sequential Dexterity**, Liu pioneered a method for chaining dexterous policies to handle long-horizon manipulation tasks, demonstrating how robotic hands can seamlessly transition between diverse subtasks—a critical step toward practical home assistants. Their work has been instrumental in shifting robotic simulation from narrow, contact-based tasks to rich, human-centric challenges. With a growing citation impact and a focus on realistic, scalable benchmarks, Liu is shaping the future of robots that can truly assist in daily life.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3