Xialin He
@Xialin_He
CS Ph.D. student @ UIUC, Undergrade @ SJTU ACM Honors Class
Sim2real for different robot models often needs complex, hand-crafted reward design. We used a Uniform Lipschitz-Constrained Policy to let diverse humanoids work with a simple, universal reward. If you’re tired of complex reward shaping, check out our paper!
Smooth behaviors is vital for successful sim2real transfer of RL policies. This is often achieved with smoothness rewards or low-pass filters, which are not easily differentiable and tend to require tedious tuning. We introduce Lipschitz-Constrained Policies (LCP), a simple and…
There are so many tracking paper nowadays. One policy that can track all fragile motions is impressive. Checkout this GMT paper.
🚀Introducing GMT — a general motion tracking framework that enables high-fidelity motion tracking on humanoid robots by training a single policy from large, unstructured human motion datasets. 🤖A step toward general humanoid controllers. Project Website:…
Really impressive work! Happy to see such exciting abilities in humanoids.
🤖Introducing TWIST: Teleoperated Whole-Body Imitation System. We develop a humanoid teleoperation system to enable coordinated, versatile, whole-body movements, using a single neural network. This is our first step toward general-purpose robots. 🌐humanoid-teleop.github.io
Meet 𝐀𝐌𝐎 — our universal whole‑body controller that unleashes the 𝐟𝐮𝐥𝐥 kinematic workspace of humanoid robots to the physical world. AMO is a single policy trained with RL + Hybrid Mocap & Trajectory‑Opt. Accepted to #RSS2025. Try our open models & more 👉…
HumanUp has been accepted by #RSS2025 looking forward to seeing you in LA this June!
🤖 Want to train a humanoid to stand up safely and smoothly? Try HumanUP: Sim-to-Real Humanoid Getting-Up Policy Learning! 🚀 ✨ HumanUP is a two-stage RL framework that enables humanoid robots to stand up from any pose(facing up and down) with stability and safety. Check out…
Our HumanUP project is now open-source! 🎉 Everyone can now train their own get-up policy for the Unitree G1 robot. Open-source in robotics is incredibly meaningful—it enables more people to reproduce our results and push the field forward. Check it out! 🚀…
🤖 Want to train a humanoid to stand up safely and smoothly? Try HumanUP: Sim-to-Real Humanoid Getting-Up Policy Learning! 🚀 ✨ HumanUP is a two-stage RL framework that enables humanoid robots to stand up from any pose(facing up and down) with stability and safety. Check out…
The next step we will be focusing is how we can integrate all locomotion abilities together
🤖 Want to train a humanoid to stand up safely and smoothly? Try HumanUP: Sim-to-Real Humanoid Getting-Up Policy Learning! 🚀 ✨ HumanUP is a two-stage RL framework that enables humanoid robots to stand up from any pose(facing up and down) with stability and safety. Check out…
This one-take video showcases many different desktop manipulation tasks and is very impressive.
Thrilled to introduce 🦏RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations! Project: humanoid-interaction.github.io RHINO is our recent attempt on human-robot interaction to bring humanoids into human's real life. To do so, we require highly…
New impressive G1 demo everyday
Thrilled to introduce 🦏RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations! Project: humanoid-interaction.github.io RHINO is our recent attempt on human-robot interaction to bring humanoids into human's real life. To do so, we require highly…
Checkout this work on humanoids getting UP! I think the next interesting topic would be learning to do safe falling and integrate all the skills together.
🤖 Want to train a humanoid to stand up safely and smoothly? Try HumanUP: Sim-to-Real Humanoid Getting-Up Policy Learning! 🚀 ✨ HumanUP is a two-stage RL framework that enables humanoid robots to stand up from any pose(facing up and down) with stability and safety. Check out…
I really don’t want to pull the robot up by hand anymore.😅.
🤖 Want to train a humanoid to stand up safely and smoothly? Try HumanUP: Sim-to-Real Humanoid Getting-Up Policy Learning! 🚀 ✨ HumanUP is a two-stage RL framework that enables humanoid robots to stand up from any pose(facing up and down) with stability and safety. Check out…
🤖 Want to train a humanoid to stand up safely and smoothly? Try HumanUP: Sim-to-Real Humanoid Getting-Up Policy Learning! 🚀 ✨ HumanUP is a two-stage RL framework that enables humanoid robots to stand up from any pose(facing up and down) with stability and safety. Check out…
Great whole body motion! First time to see a humanoid can do such whole body task.
🚀 Can we make a humanoid move like Cristiano Ronaldo, LeBron James and Kobe Byrant? YES! 🤖 Introducing ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills Website: agile.human2humanoid.com Code: github.com/LeCAR-Lab/ASAP
Really nice work! Proud to be part of the team!
For more illustrations, see our YouTube video: youtu.be/6H2MkMetmFk Our team: Zixuan @C___eric417, Wenhao, Tianyi, Xialin @Xialin_He, Ying @Ying_yyyyyyyy, Jason @xbpeng4, Jiajun @jiajunwu_cs
I'm excited that OmniH2O has been accepted to CoRL 2024, and I'm also very happy that we have released OmniH2O fully open-sourced. I hope more people can use our code for their own research. I believe open-source is a very important step in the robotics field.
Excited to announce that OmniH2O (👉omni.human2humanoid.com) is accepted at CoRL2024! 🚀 Check out our fully open-source code: github.com/LeCAR-Lab/huma…, featuring simulation training, motion data retargeting, and real-world deployment. Have fun with your humanoids!
Finally! Love to see this work out! It’s an honor to work with this team! OmniH2O is a framework for robust and scalable humanoid teleoperation and autonomy! Check out our website: omni.human2humanoid.com
Introduce OmniH2O, a learning-based system for whole-body humanoid teleop and autonomy: 🦾Robust loco-mani policy 🦸Universal teleop interface: VR, verbal, RGB 🧠Autonomy via @chatgpt4o or imitation 🔗Release the first whole-body humanoid dataset omni.human2humanoid.com