Wenli Xiao

I am a master student at CMU Robotics Intitute (MSR) advised by Prof. Guanya Shi and Prof. John Dolan.

I am currently doing research intern at NVIDIA GEAR Lab working with Dr. Jim Fan and Prof. Yuke Zhu on foundation model for humanoids.

Email  /  Google Scholar  /  Twitter  /  Github

profile photo
Research - Humanoid Whole-Body Control

WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts
Chong Zhang*, Wenli Xiao*, Tairan He, Guanya Shi
CoRL 2024
RSS 2024, Task Specification for General-Purpose Intelligent Robots Workshop

arXiv / website / video / introduction / twitter

TL;DR: WoCoCo is the first unified RL framework to learn whole-body humanoid control with sequential contacts.

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
CoRL 2024
arXiv / website / video / Twitter

TL;DR: OmniH2O provides the first universal whole-body humanoid control interface that enables diverse teleoperation and autonomy methods.

Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation
Tairan He*, Zhengyi Luo*. Wenli Xiao, Chong Zhang, Kris Kitani, Changliu Liu, Guanya Shi
IROS 2024 (Oral presentation)
ICRA 2024, Agile Robotics Workshop (Spotlight)

arXiv / website / video

TL;DR: H2O enables real-time whole-body teleoperation of a full-sized humanoid to perform tasks like pick and place, walking, kicking, boxing, etc.

Research - Agile Robot Mobility

Safe Deep Policy Adaptation
Wenli Xiao*, Tairan He*, John Dolan, Guanya Shi
ICRA 2024
CoRL 2023 Deployable Workshop

arXiv / website / video / code / twitter

This paper jointly tackles policy adaptation and safe reinforcement learning with safety guarantees. Comprehensive experiments on (1) classic control problems (Inverted Pendulum), (2) simulation benchmarks (Safety Gym), and (3) a real-world agile robotics platform (RC Car) demonstrate great superiority of SafeDPA in both safety and task performance, over state-of-the-art baselines.

Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
Tairan He*, Chong Zhang* Wenli Xiao, Guanqi He, Changliu Liu, Guanya Shi
RSS 2024 (Outstanding Student Paper Award Finalist - Top 3)
ICRA 2024, Agile Robotics Workshop (Spotlight)

arXiv / website / video

Legged robots navigating cluttered environments must be jointly agile for efficient task execution and safe to avoid collisions with obstacles or humans. Existing studies either develop conservative controllers (< 1.0 m/s) to ensure safety, or focus on agility without considering potentially fatal collisions. This paper introduces Agile But Safe (ABS), a learning-based control framework that enables agile and collision-free locomotion for quadrupedal robots.

Education
Carnegie Mellon University, Pittsburgh, PA, USA
MS, Robotics • Sep. 2023 to May. 2025 (expected)
UC Berkeley, Berkeley, CA, USA
EECS Visiting • Jan. 2022 to May. 2022
The Chinese University of Hong Kong, Shenzhen, China
B.S. in Electric Information Engineering • Sep. 2019 to Jun. 2023
Experiences
Robotics Institute Summer Scholar (RISS), Carnegie Mellon University
Research Intern • June. 2022 to Aug. 2023
Advisor: Prof. John Dolan and Yiwei Lyu
RISE Lab, UC Berkeley
Research Intern • March. 2022 to May. 2022
Advisor: Prof. Joseph E. Gonzalez and Tianjun Zhang
NCEL Lab, Shenzhen Institute of Artificial Intelligence and Robotics for Society (Shenzhen AIRS)
Research Intern • Aug. 2020 to March. 2022
Advisor: Prof. Jianwei Huang and Prof. Bing Luo





Updated at June. 2024
Thanks Jon Barron for this amazing template