A slam dunk for machine learning

Heni Ben Amor, left, an assistant professor of computer science and Kevin Sebastian Luck, a computer science doctoral student, watch as their robot tosses a ball. A simple task for a human, accurately throwing a ball can take most robots up to three days to master. But a new algorithm developed by Ben Amor has reduced that learning time to a matter of hours. Photographer: Jessica Hochreiter/ASU

It picks up the ball, carefully lines up its shot and in one fluid movement, releases its projectile. The robot’s arms remain in the air expectantly as the ball bounces off the rim and drops out of sight. You can almost sense the robot’s dejection as its lifeless, Kinect-powered eyes stare blankly at its missed target.

This, of course, is humanity’s knack for personification taking over. The robot isn’t upset when it misses, nor is it elated when it finally sinks a basket. However, it is doing something humans do.

The robot is learning.

Though machine learning — a type of artificial intelligence that enables a computer to learn without explicit programming — isn’t new, the speed at which this robot learns breaks new ground in robotics. While many robots can take anywhere from two to three days to learn how to execute a given task, one Arizona State University engineer has created an algorithm that allowed his basketball-throwing robot to learn how to sink a shot in a matter of hours.

Read more and see video on Full Circle