Sign In

Communications of the ACM

ACM TechNews

UC Berkeley Researchers Model Robot AI Algorithm on Human Babies

View as: Print Mobile App Share:
A robot learning from its environment.

The robots were equipped with Rapid Motor Adaptation, which allows them to perceive surrounding terrain through sensory joints located in their legs.

Credit: RMA Research Team

An artificial intelligence algorithm developed by researchers at the University of California, Berkeley and Carnegie Mellon University helps four-legged robots make quick adaptations to their environment.

The model uses rapid motor adaptation (RMA), which enables robots to use sensory joints in their legs to perceive the surrounding terrain and adapt in a fraction of a second.

The researchers were inspired by the way children learn.

Berkeley's Jitendra Malik said, "The secret is that they are observing the world, they are interacting with the world, they are experimenting with the world."

The researchers plan to add vision sensors and expand RMA to robots' fingers, to enable them to grasp objects and open bottles.

From The Daily Californian
View Full Article


Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account