Xiaoyu Huang

Hello! I am a third-year Ph.D. student at UC Berkeley, where I am fortunate to be advised by Prof. Pieter Abbeel. I am currently also an Applied Scientist Intern at Amazon FAR (Frontier AI & Robotics), working with Angjoo Kanazawa, Carmelo Sferrazza, C. Karen Liu, Guanya Shi, and Rocky Duan. During my first two years, I had the pleasure of working closely with Prof. Koushil Sreenath. Before starting my Ph.D., I received my B.S. in Computer Engineering from Georgia Institute of Technology, where I was fortunate to be advised by Prof. Dhruv Batra.

I study robot learning. My research lies at the intersection of character animation and robotics, driven by the philosophy that robots, especially humanoids, should learn from humans in order to move naturally and efficiently in our world. Following this philosophy, my prior work has enabled humanoid robots to scalably track human motions with state-of-the-art quality including extreme acrobatic skills (BeyondMimic), interact with objects and terrains (OmniRetarget), and ultimately parkour with human-level agility using only perception and proprioception (PHP).