🤖✨Excited to share our new work:
OMG: Omni-Modal Motion Generation for Generalist Humanoid Control
What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]
Video model will be the data factory for robotics! We have released code and a loco-manipulation dataset of more than 20k sequences generated by GRAIL. Check it out!
Humanoid robotics is hitting a data wall. Teleop and mocap took us far, but they don’t scale to every object, terrain, and behavior.
We’re releasing GRAIL: research.nvidia.com/labs/dai… — a fully digital pipeline for generating loco-manipulation data before the robot moves. 🧵(1/8)
Human demos contain rich hand-object skills. The challenge is the embodiment gap. Human and robot hands differ in shape, joints, and contacts.
Introducing ConTrack, our latest work that turns contact-rich human hand-object demos into robot motions.
Can humanoids perform agile, autonomous, long-horizon parkour—based on what they see in the world?
We present 𝗣𝗲𝗿𝗰𝗲𝗽𝘁𝗶𝘃𝗲 𝗛𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗣𝗮𝗿𝗸𝗼𝘂𝗿 (𝗣𝗛𝗣): a framework that chains dynamic human skills using onboard depth perception for long-horizon traversal.
1/6
Played their prototype a few weeks ago—very impressive. Low backlash, highly backdrivable, and relatively low gear ratios.
It gave me the same feeling I had when I first touched the Unitree G1 in 2024: a strong sense that an inflection point is coming.
I think 2026 will be the breakthrough year for dexterous hands, much like 2024 was for humanoids. There are already so many great teams building in this space—Sharpa, WuJi, RobotEra, just to name a few.
We release Wuji MJLab, an open-source MuJoCo environment for dexterous hand manipulation.
It includes a cube reorientation task, a sim2real pipeline, and the setup needed to reproduce the system.
We will be at ICRA booth 121 with a live demo and welcome discussions on dexterous manipulation.
Code: github.com/wuji-technology/w…
Contributors: Jielin Wu, @yaoshzh, @BergerHunger, Li Chengmeng.
This project is based on @kevin_zakka’s mjlab project.