Robots master skills with ‘deep learning’ technique

“What we’re reporting on here is a new approach to empowering a robot to learn,” said Professor Pieter Abbeel of UC Berkeley. “The key is that when a robot is faced with something new, we won’t have to reprogram it. 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.”
 
The work is part of a new People and Robots Initiative at UC’s Center for Information Technology Research in the Interest of Society (CITRIS). The new multi-campus, multidisciplinary research initiative seeks to keep the advances in artificial intelligence, robotics and automation aligned to human needs.
 
“Most robotic applications are in controlled environments where objects are in predictable positions,” said UC Berkeley faculty member Trevor Darrell, director of the Berkeley Vision and Learning Center. “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.”
 
Conventional, but impractical, approaches to helping a robot make its way through a 3D world include pre-programming it to handle the vast range of possible scenarios or creating simulated environments within which the robot operates.
 
Instead, the UC Berkeley researchers turned to a new branch of artificial intelligence known as deep learning, which is loosely inspired by the neural circuitry of the human brain when it perceives and interacts with the world.
 
“For all our versatility, humans are not born with a repertoire of behaviors that can be deployed like a Swiss army knife, and we do not need to be programmed,” said postdoctoral researcher Sergey Levine. “Instead, we learn new skills over the course of our life from experience and from other humans.
 
This learning process is so deeply rooted in our nervous system, that we cannot even communicate to another person precisely how the resulting skill should be executed. We can at best hope to offer pointers and guidance as they learn it on their own.”