Rowan Cheung(@rowancheung)

MIT engineers built an AI wristband that controls robots by reading your hand muscles. It works by ...

7.5内容质量
MIT engineers built an AI wristband that controls robots by reading your hand muscles.

It works by ...

TL;DR · AI 摘要

MIT开发了一款AI腕带,通过超声波读取手腕肌肉和肌腱图像,实时还原五指22种动作,用于控制机器人。

核心要点

  • AI腕带利用超声波成像捕捉手腕肌肉活动,无需侵入式传感器。
  • 算法可精确重建22种手部动作,适用于钢琴演奏、手语等复杂任务。
  • 项目正扩展数据集以训练手术机器人,有望成为人机交互通用接口。
#AI#人机交互#机器人#超声波传感#MIT
打开原文

It works by using an ultrasound to capture images of the muscles and tendons in your wrist.

An AI algorithm then translates those images into the exact position of all 5 fingers, tracking 22 https://t.co/hnCOS0BgQQ" / X

Rowan Cheung on X: "MIT engineers built an AI wristband that controls robots by reading your hand muscles. It works by using an ultrasound to capture images of the muscles and tendons in your wrist. An AI algorithm then translates those images into the exact position of all 5 fingers, tracking 22 https://t.co/hnCOS0BgQQ" / X

Don’t miss what’s happening

Image 1
Image 1

Rowan Cheung ![Image 2](http://x.com/rowancheung)

@rowancheung

MIT engineers built an AI wristband that controls robots by reading your hand muscles. It works by using an ultrasound to capture images of the muscles and tendons in your wrist. An AI algorithm then translates those images into the exact position of all 5 fingers, tracking 22 different ways your hand can bend, twist, and extend. In demos, wearers directed a robotic hand to play piano just by moving their own fingers. To put the complexity in perspective, it takes: > 34 muscles > 27 joints > 100+ tendons ...Just to scroll your phone This device captures it all from a band the size of a smartwatch. They tested across 8 volunteers with different hand sizes, tracking everything from sign language letters to holding scissors. The team is now collecting data from hundreds more users to train robots in surgical procedures. Something like this could one day become the universal remote for robots and virtual worlds, and we're way closer than most people expect.

2:39

3:14 PM · Apr 17, 2026

·

25K Views

14

14

85

32

Read 14 replies