Xialin He

I am a senior year undergraduate student at ACM Honors Class, Shanghai Jiao Tong University and I am fortunate to work with Prof. Xiaolong Wang at UCSD Wang Lab as a research intern. During my time there, I also have the opportunity to collaborate closely with Prof. David Held.

During my junior year, I was privileged to delve into the application of Reinforcement Learning in Quadruped Robot's locomotion while collaborating with the SJTU APEX lab under the guidance of Prof. Weinan Zhang.

My research interests lie in Reinforcement Learning, Robot Learning, Computer Vision and Control theory.

If you are interested in my work, feel free to to contact me for further discussions or potential collaborations.

Email  /  GitHub  /  Google Scholar  / 

profile photo hover photo


project image

OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning

Tairan He*, Zhengyi Luo*, Xialin He*, Wenli Xiao, Chong Zhang, Weinan Zhang, Kris Kitani, Changliu Liu, Guanya Shi
in submission
arxiv / video / dataset / website /

We present OmniH2O (Omni Human-to-Humanoid), a learning-based system for whole-body humanoid teleoperation and autonomy. Using kinematic pose as a universal control interface, OmniH2O enables various ways for a human to control a full-sized humanoid with dexterous hands and also enables full autonomy by learning from teleoperated demonstrations or integrating with frontier models such as GPT-4o

project image

Visual Manipulation with Legs

Xialin He*, Chengjing Yuan*, Wenxuan Zhou, Ruihan Yang, David Held, Xiaolong Wang
in submission
website /

We propose a system that enables quadruped to manipulate objects with legs. We use reinforcement learning to train a policy to interact with the object based on point cloud observations, which demonstrates advanced manipulation skills with legs that has not been shown in previous work.

project image

sim-to-real transfer for quadrupedal locomotion via terrain transformer

Hang lai, Weinan Zhang, Xialin He, Chen Yu, Zheng Tian, Yong Yu, Jun Wang
arxiv / code / website /

we propose Terrain Transformer (TERT), a simple yet effective method to leverage Transformer for quadrupedal locomotion over multiple terrains, including a two-stage training framework to incorporate Transformer with privileged learning.


project image

University of California, San Diego

San Diego, USA

Research Intern in Electrical and Computer Engineering Department, Jun 2023 - Dec 2023
project image

Shanghai Jiao Tong University

Shanghai, China

B.S. in Computer Science(ACM Honors Class), Sep 2020 - present

Design and source code from Leonid Keselman