Ruiqi Yu

Papers

Total Citations

H-Index

About

Ruiqi Yu is a rising star in legged robotics, whose work bridges the critical gap between robust locomotion and real-world deployment. His primary research focuses on developing learning-based control frameworks for both quadrupedal and humanoid robots, with a particular emphasis on mastering extreme terrain and understanding the role of state estimation. Yu’s most notable contribution is the **PIE (Parkour With Implicit-Explicit Learning) framework**, which enables legged robots to perform highly agile parkour maneuvers—such as jumping, climbing, and traversing complex obstacles—by integrating implicit and explicit learning to handle unreliable perceptual data. This work has already garnered 25 citations since its 2024 publication, signaling its immediate impact. Additionally, his research into humanoid locomotion provides a rare, analytical deep dive into how key state estimation factors influence the robustness of learned policies, offering foundational insights for the field. By systematically addressing the “black box” of estimation in learning-based control, Yu is helping to make humanoid robots more reliable outside the lab. His work is essential reading for anyone interested in the future of agile, perceptive, and truly autonomous legged machines.