A child-like robot!

New York: Heard of a robot that can learn things on its own, through trial and error? Well, here is one. Researchers at the University of California-Berkeley have developed algorithms that enable robots to learn motor tasks through trial and error much like humans learn things.

They demonstrated their technique, a type of reinforcement learning, by having a robot complete various tasks, putting a clothes hanger on a rack, assembling a toy plane, screwing a cap on a water bottle, and more without pre-programmed details about its surroundings.

"The challenge of putting robots into real-life settings, like homes or offices, is that those environments are constantly changing. The robot must be able to perceive and adapt to its surroundings," said co-researcher Trevor Darrell. The researchers turned to a new branch of artificial intelligence known as deep learning.

In the world of artificial intelligence, deep learning programmes create "neural nets" in which layers of artificial neurons process overlapping raw sensory data, be it sound waves or image pixels. This helps the robot recognise patterns and categories among the data it is receiving.