Published • loading... • Updated
MIT researchers channel AI to turn hand gestures into robot training data
In tests with eight volunteers, the wristband mirrored hand gestures in 120 milliseconds and could help robots learn dexterous tasks.
- Researchers at the Massachusetts Institute of Technology developed an ultrasound wristband that captures muscle and tendon movements beneath the skin, relaying images to enable nearby robotic hands to mimic human gestures.
- Humanoid robots struggle with complex grasping tasks because the human hand possesses 22 degrees of freedom—specific ways joints bend or rotate—that remain difficult for machines to replicate.
- The wristband uses high-frequency sound waves to "see" "through its wearer's" skin, with an AI algorithm decoding images into gestures including all 26 letters of American Sign Language.
- Beyond simple remote control, the system provides data for tasks requiring precise finger and hand flexion, including surgery and complex housework.
- MIT professor Xuanhe Zhao aims to imbue artificial intelligence with sensory data from the physical world, enabling humanoid robots to eventually learn dexterous tasks without human guidance.
Insights by Ground AI
27 Articles
27 Articles
Associated Press News+26 Reposted by 26 other sources
MIT researchers channel AI to turn hand gestures into robot training data
Humanoid robots struggling with tasks like grasping a cup have a new teacher — a person wearing an ultrasound wristband that captures the movement of muscles, tendons and ligaments beneath the skin.
·New York, United States
Read Full ArticleCoverage Details
Total News Sources27
Leaning Left14Leaning Right3Center9Last UpdatedBias Distribution54% Left
Bias Distribution
- 54% of the sources lean Left
54% Left
L 54%
C 35%
11%
Factuality
To view factuality data please Upgrade to Premium
