MIT Innovators Utilize AI to Transform Hand Gestures Into Robot Training Data

WHO:

ABC News - Researchers at the Massachusetts Institute of Technology (MIT) developed a tool for collecting data on human hand motion.

ABC News - Xuanhe Zhao is an MIT professor of mechanical engineering involved in the project.

WHAT:

ABC News - The tool captures the movement of muscles, tendons, and ligaments beneath the skin using an ultrasound wristband.

ABC News - The wristband can mirror hand gestures, including all 26 letters in American Sign Language, within 120 milliseconds.

ABC News - The technology aims to help robots achieve dexterity for tasks like housework and surgery.

ABC News - The human hand has 22 degrees of freedom, which the AI algorithm decodes from images generated by the wristband.

WHERE:

ABC News - The research is conducted at the Massachusetts Institute of Technology in Cambridge, Massachusetts.

HOW:

ABC News - The wristband uses high-frequency sound waves to capture images of muscle and tendon movements.

ABC News - The system relays the captured data to a computer that uses AI to enable a robotic hand to mimic the gestures.

ABC News - The wristband operates wirelessly, allowing the controlling person and the receiving robot to be in different locations.

(UPDATED June 9, 2026 15:58 UTC)

Researchers at the Massachusetts Institute of Technology have developed an innovative tool that captures human hand motion using a specialized ultrasound wristband. This wristband can mirror hand gestures, including all 26 letters in American Sign Language, within just 120 milliseconds, and it operates wirelessly, allowing for remote control of robotic hands. The technology aims to enhance robotic dexterity for various tasks, utilizing high-frequency sound waves to decode the intricate movements of muscles, tendons, and ligaments beneath the skin.