@Tsinghua_Uni: Revolutionizing wearable hand sensing! Innovative Tsinghua team introduces WRISTPP: a wristband sensor reconstructing p…
Summary
Tsinghua University introduces WRISTPP, a wristband sensor that reconstructs precise hand postures and contact pressures in real time, outperforming headset cameras and reducing arm fatigue, with applications in embodied AI and robot teleoperation.
View Cached Full Text
Cached at: 07/29/26, 06:00 PM
Revolutionizing wearable hand sensing! Innovative Tsinghua team introduces WRISTPP: a wristband sensor reconstructing precise hand postures & contact pressures in real time. It outperforms headset cameras with less arm fatigue, perfect for embodied AI and robot teleoperation. https://t.co/PXfHbspnSV
Similar Articles
Wristband enables wearers to control a robotic hand with their own movements
MIT researchers have developed an ultrasound wristband that tracks hand movements in real-time using AI to control robotic hands or virtual environments. The technology, published in Nature Electronics, aims to improve dexterous robot training and VR interaction without the limitations of cameras or sensor gloves.
Ultrasound imaging turns a robot hand into a skillful mimic
MIT researchers developed a wristband with ultrasound stickers that images muscles and tendons, using AI to translate those images into hand movements to wirelessly control a robotic hand with high dexterity.
@rohanpaul_ai: Another beautiful robotic hand. WUJI trained its 20-joint robot hand, WUJI Hand 2, to spin a pen inside a physics simul…
WUJI demonstrated its 20-joint WUJI Hand 2 performing pen spinning, trained in the MuJoCo-based mjlab simulator with PPO and then deployed on the real hand, alongside a sensor glove for teleoperation and data collection. The code, motion clips, trained models, and printable pen files are released under the Apache 2.0 license.
@Knesix: Whoa. This looks amazing!
WUJI demonstrated its 20-joint WUJI Hand 2 robotic hand spinning a pen, trained in a physics simulator and deployed sim-to-real, showcased around IROS 2026.
@LinusEkenstam: Humanoids are moving beyond basic grasping into dexterous manipulation. These WUJI demos are seriously impressive. Move…
WUJI showcases its Hand 2 humanoid dexterous hand, which mirrors human hand movements via camera tracking or a glove and learns skills like pen spinning through reinforcement learning in mjlab simulation before transferring them to the real world. The wuji-mjlab code is released as open source for developers and researchers.