Quanyi Li

Papers

Total Citations

H-Index

About

Quanyi Li is an emerging researcher at the intersection of embodied artificial intelligence, reinforcement learning, and autonomous systems. His work spans several cutting-edge domains, including human-AI collaborative control, legged robot locomotion, and urban robotics simulation — areas that collectively address how intelligent agents can operate safely and effectively in complex, real-world environments. Among his notable contributions, Li's work on Human-AI Shared Control via Policy Dissection introduces an innovative approach enabling humans to intuitively collaborate with AI on challenging control tasks without requiring costly reward function redesign. His research on the Hybrid Internal Model advances legged robot locomotion by addressing the persistent challenge of partial and noisy sensor observations, enabling more robust and agile movement over unpredictable terrain. Most ambitiously, MetaUrban presents a comprehensive simulation platform for studying embodied AI in dynamic urban environments, reflecting growing real-world demand for robots that safely coexist with people on sidewalks and public spaces. Though early in his career — with his cited works accumulating citations reflecting their recency — Li's research tackles foundational problems that will shape the future of autonomous robotics and human-robot interaction, making him a researcher worth following closely as the field rapidly evolves.