• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Report

WUJI Hand 2 spins a pen using a policy trained in simulation

A post describes a sensor glove for live control and a camera tracking markers on a 3D-printed pen.

2 Sources, 1h ago, first seen 1h ago

TLDR

A post says WUJI trained its 20-joint Hand 2 to spin a pen in simulation, then ran the trained policy on the physical hand around IROS 2026. A camera tracked markers on the pen and wrist while the policy sent joint targets 50 times a second. The post also describes a sensor glove for live control and says WUJI released code, motion clips, trained models and printable pen files under Apache 2.0.

Combined views

—

2 Sources, first seen 1h ago

— likes— comments— saves— reposts

Combined views

—

2 Sources, first seen 1h ago

— likes— comments— saves— reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

2 Sources

Rohan Paul@rohanpaul_aiAnother beautiful robotic hand. WUJI trained its 20-joint robot hand, WUJI Hand 2, to spin a pen inside a physics simulator, then ran that same trained policy on the real hand. It showed this around IROS 2026 (the International Conference on Intelligent Robots and Systems), together with a sensor glove that lets a person control the hand live. Pen spinning is a hard test for a robot hand, because the pen keeps rolling, sliding and passing between fingers, and one finger moving a bit late drops it. @wuji_global’s Hand 2 has 20 joints, four per finger, each independently driven by its own motor, and supports a 1,000 Hz control rate. Training used mjlab, a robot-learning toolkit built on the MuJoCo physics simulator, running 4,096 virtual copies of the hand at the same time with PPO (Proximal Policy Optimization), a reinforcement learning method where the AI improves by trial and error and gets rewarded for good moves. The AI learns to follow 40 recorded pen motions in 5 groups, from a simple turn around 1 axis up to continuous spins across several axes, and it keeps correcting its fingers whenever the pen drifts from the plan. On the real hand, the policy sends targets to all 20 joints 50 times a second, while an industrial camera tracks printed markers on both ends of a 250mm 3D-printed pen plus a tag on the wrist, so the AI always knows where the pen is. The glove covers the other way of teaching a robot: 5 electromagnetic sensors at the fingertips track each finger's position and angle 120 times a second with about 10ms delay or less, and software turns that into joint angles the robot hand copies. A 526-point pressure grid on the glove's palm also records how hard the person grips, which makes it useful for collecting training data for robots that learn by copying humans. WUJI released the code, motion clips, trained models and printable pen files under the open Apache 2.0 license, so a lab with a WUJI Hand 2, a camera and an NVIDIA GPU can repeat the whole setup.1h
Jesús Enrique Rosas - The Body Language Guy@KnesixWhoa. This looks amazing!1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    2 Sources

    Rohan Paul@rohanpaul_aiAnother beautiful robotic hand. WUJI trained its 20-joint robot hand, WUJI Hand 2, to spin a pen inside a physics simulator, then ran that same trained policy on the real hand. It showed this around IROS 2026 (the International Conference on Intelligent Robots and Systems), together with a sensor glove that lets a person control the hand live. Pen spinning is a hard test for a robot hand, because the pen keeps rolling, sliding and passing between fingers, and one finger moving a bit late drops it. @wuji_global’s Hand 2 has 20 joints, four per finger, each independently driven by its own motor, and supports a 1,000 Hz control rate. Training used mjlab, a robot-learning toolkit built on the MuJoCo physics simulator, running 4,096 virtual copies of the hand at the same time with PPO (Proximal Policy Optimization), a reinforcement learning method where the AI improves by trial and error and gets rewarded for good moves. The AI learns to follow 40 recorded pen motions in 5 groups, from a simple turn around 1 axis up to continuous spins across several axes, and it keeps correcting its fingers whenever the pen drifts from the plan. On the real hand, the policy sends targets to all 20 joints 50 times a second, while an industrial camera tracks printed markers on both ends of a 250mm 3D-printed pen plus a tag on the wrist, so the AI always knows where the pen is. The glove covers the other way of teaching a robot: 5 electromagnetic sensors at the fingertips track each finger's position and angle 120 times a second with about 10ms delay or less, and software turns that into joint angles the robot hand copies. A 526-point pressure grid on the glove's palm also records how hard the person grips, which makes it useful for collecting training data for robots that learn by copying humans. WUJI released the code, motion clips, trained models and printable pen files under the open Apache 2.0 license, so a lab with a WUJI Hand 2, a camera and an NVIDIA GPU can repeat the whole setup.1h
    Jesús Enrique Rosas - The Body Language Guy@KnesixWhoa. This looks amazing!1h
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet