Research
My ultimate goal is to build deployable robotic systems and facilitate robots working in our daily lives!
My research focuses on using data-driven approaches and combining large-scale (Reinforcement) Learning-based methods with control-theoretical frameworks to tackle: 1) safety, 2) agility, and 3) adaptivity, to make robots more deployable.
I am passionate about real robots and have extensive experience with 1/10 Racing Cars, quadrupedal robots, and Humanoids! (*equal contribution)
|
|
WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts
Chong Zhang*, Wenli Xiao*, Tairan He, Guanya Shi
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.
|
|
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.
|
|
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
2024, Under Review
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.
|
|
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.
|
|
Model-based Dynamic Shielding for Safe and Efficient
Multi-Agent Reinforcement Learning
Wenli Xiao, Yiwei Lyu, John Dolan
AAMAS 2023 (oral presentation)
arXiv
We propose the Model-based Dynamic Shielding (MBDS)
framework to address the safety challenges in Multi-Agent
Reinforcement Learning (MARL), while providing formal
guarantees through the application of Linear Temporal
Logic (LTL) in its construction.
|
|
Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks
Bing Luo, Wenli Xiao, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas
IEEE Transactions on Mobile Computing
arXiv /
code
TL;DR: This paper design an adaptive client sampling algorithm for FL over wireless networks that tackles both system and statistical heterogeneity to minimize the wall-clock convergence time.
|
|
Tackling system and statistical heterogeneity for
federated learning with adaptive client sampling
Bing Luo, Wenli Xiao, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas
INFOCOM 2022
arXiv /
This paper presents an adaptive client sampling algorithm
that minimizes wall-clock convergence time in Federated
Learning by addressing system and statistical
heterogeneity, resulting in up to 73% less time spent
compared to baselines (weighted sampling, uniform
sampling, .etc).
|
Carnegie Mellon University, Pittsburgh, PA, USA
MS, Robotics • Sep. 2023 to May. 2025 (expected)
|
![](images/cmu-logo.jpg) |
UC Berkeley, Berkeley, CA, USA
Visiting Student • Jan. 2022 to May. 2022
|
![](images/berkeley-logo.png) |
The Chinese University of Hong Kong, Shenzhen, China
B.S. in Electric Information Engineering • Sep. 2019 to Jun. 2023
|
![](images/cuhksz-logo.jpeg) |
|