News

The team used this machine-learning method to produce two real-world underwater gliders: a two-winged machine resembling an airplane, and a unique, four-winged object (Credit: Courtesy of the researchers).

AI shapes new autonomous underwater “gliders”

MIT CSAIL researchers combined generative AI and a physics simulation engine to create a machine that outjumped a robot designed by a human (Credit: Researchers photographed by Dan McDonald and image collaged by Alex Shipps/MIT CSAIL using assets from the researchers).

Using generative AI to help robots jump higher and land better

A robotic arm learns to understand its own body (Credit: Courtesy of the researchers).

Robots that know themselves: MIT’s vision-based system teaches machines to understand their bodies

Spotlighted News

AI shapes new autonomous underwater “gliders”

Using generative AI to help robots jump higher and land better

Robots that know themselves: MIT’s vision-based system teaches machines to understand their bodies