The Berkeley Robot for the Elimination of Tedious Tasks (BRETT) is a robot that learns how to do things just like how kids do by trial and error.
With the new deep learning algorithm s University of California, Berkeley researchers have come up with, the Berkeley robot or BRETT can complete numerous tasks such as screwing a cap on a water bottle, putting a clothes hanger on a rack and assembling a toy plane.
BRETT can accomplish all these tasks even without programming it with details on its surroundings. On the other hand, it must be noted that developing artificial intelligence is not without trouble.
One of the things that have to be considered when developing artificial intelligence is the amount of programming involved in spelling out each aspect of a task. Normally, a robot or software program cannot adapt if it does not come across that task in the real world precisely as it was programmed to, Forbes has learned.
To deal with this, researchers are working on many ways to help machines learn by trial and error. In a statement from UC Berkeley, Department of Electrical Engineering and Computer Sciences Professor Pieter Abbeel said that are reporting is "a new approach to empowering a robot to learn."
"The key is that when a robot is faced with something new, we won't have to reprogram it," Abbeel explained. "The exact same software, which encodes how the robot can learn, was used to allow the robot to learn all the different tasks we gave it."
Watch BRETT The Robot do things like a kid through trial and error here: