AI models let robots carry out tasks in unfamiliar environments

The five AI models, called robot utility models (RUMs), allow machines to complete five separate tasks in unfamiliar environments with a 90% success rate.

Researchers hope their findings will make it quicker and easier to teach robots new skills, helping them function within previously unseen domains.

Mahi Shafiullah notes, 'In the past, people have focused a lot on the problem of 'How do we get robots to do everything?' but not really asking...how do we get robots to do the things they do know how to do-everywhere?'

Teaching robots new skills generally requires a lot of data, which is hard to come by, making it much harder than training large language models.

Read at MIT Technology Review