UC Berkeley researchers have developed algorithms that enable robots to learn motor tasks through trial and error using a process that more closely approximates the way humans learn, marking a major milestone in the field of artificial intelligence.
In their experiments, the PR2 robot, nicknamed BRETT (Berkeley Robot for the Elimination of Tedious Tasks), used 'deep learning' techniques to complete various tasks without pre-programmed details about its surroundings.
YouTube link
0 comment(s):
Post a Comment