WUJI

A new humanoid platform for robotics research is coming out of Germany. Agile Robots has introduced Agile ONE SN with NVIDIA, combining Jetson Thor, Isaac GR00T and two WUJI Hand 2s. Production is planned to begin this year, with up to…

China’s @wuji_global has been showcasing their Hand 2; their hardware shows up in a lot of external demos. https://t.co/k8KVQi5a9d

Cool foundation models using wuji hand 2 https://t.co/IKie5FWBYH

What if a robot hand could grip objects with human-like precision? 🤖✋ The WUJI Hand features 20 degrees of freedom, 1 kHz control and a peak fingertip force of 12N bringing increasingly dexterous robotic manipulation closer to reality.…

WUJI is showcasing its dexterous robotic hands at IROS 2026, demonstrating how human hand movements can control a robot through glove-based teleoperation. Its WUJI Hand 2 can also perform precise tasks like pen spinning using a policy…

Pen spinning is a classic test of human finger dexterity. WUJI just trained a robot hand to do it. Their sim-to-real policy, trained entirely in simulation, spins a pen on a physical WUJI Hand 2. At IROS 2026 they also showed glove-based…

Whether you see them in live demos or in other robotics teams’ work, WUJI hands have proven themselves to be among the best on the market. At IROS 2026, WUJI Hand 2 showed off several impressive demos, including cylinder rotation using a…

We eyeballed where the arms went at IROS. It didn't matter. Mounting height did. A 1 cm error cuts success rates by something like 70%. @castorhat's recap covers what mattered for our π0.5 demo, what didn't, and the other site-unseen demos…

Interesting to think of this on terms of how flexibly one can create opposition. A good read https://t.co/FV3fzg0fMp

Latest robot hands: 🇺🇸 Boston Dynamics | new Atlas hand 🇨🇳 Unitree | Dex5-S 🇵🇱 Clone | Torso 3 hand 🇨🇳 Wuji | Hand 2 Four new-generation hands. Four very different design philosophies. https://t.co/Tc2lgJbp4e

DITTO-X makes teleoperation work both ways. You can control a dexterous robot hand, or let the robot move your hand to match its current state before takeover. That makes intervention smoother and turns corrections into new training data..…

A bidirectional teleoperation system for dexterous robot hands. It lets you control a robot hand, and the robot hand can also move your hand. When the robot makes a mistake, it first moves your hand to match its position. That way you can…

A robot hand just learned to spin a pen. 🖊️🤖 WUJI Hand 2 is demonstrating dexterous manipulation by taking a motion learned in simulation and executing it on real hardware. The system combines motion-reference tracking with reinforcement…

Unitree, AGIBOT,Agility,EngineAI, Galbot,RobotEra,ROBOTIS... Beyond these these humanoid robot manufacturers, IROS 2026 brings together nearly the entire global supply chain for physical AI-- data and Data…

A robotic hand that learned to walk on its own fingers. 🤯🤖 Researchers at ETH Zürich’s Soft Robotics Lab transformed an off-the-shelf WUJI robotic hand into a tiny mobile robot. Using reinforcement learning, the hand can: 🦿 Crawl across…

Wuji Hand is a biomimetic robotic hand with 20 active degrees of freedom, designed to reproduce human-like dexterity. Weighing under 600 g, it delivers 15 N fingertip force, 10 kg static grasping load, and precise, responsive motion. Video…

22-motor, 22-DOF hand at $6500 How does @UnitreeRobotics's Dex5-S hand compare with the @wuji_global Hand 2 and @SharpaRobotics SharpaWave? Unitree vs. Wuji vs. Sharpa - All 3 hands put one motor on each degree of freedom: 22, 20, 22 - All…

Researchers have trained a robotic hand to walk on its fingertips without an arm. Using an off-the-shelf WUJI hand equipped with a Raspberry Pi, IMU, and battery, they trained reinforcement-learning policies in NVIDIA Isaac Lab. The…

This is too funny… did Thing from The Addams Family get a twin? 😂 ETH Zurich’s team taught a WUJI robotic hand to crawl around and get back up when it tips over, and yes, it can use a keyboard too. https://t.co/Yx2vbYW3G4…

Thing from The Addams Family has a robotic cousin. @amrhkzp from ETH’s Soft Robotics Lab taught an off-the-shelf WUJI hand to walk on its fingertips, with a Raspberry Pi and battery on its back. It can also recover, interact with a…

Reconstruct 3d hand trajectories and camera poses - open source release from WUJI. https://t.co/BhiLnvaAW7

WuJi just open-sourced its MINT model and EgoPipeline for reconstructing 3D hand + camera motion from first-person video, together with 1,021 hours of structured egocentric data for scaling robot learning. https://t.co/prUYiuzRuo