Skip to main content

Baseball-Playing Robot in a League of its Own

New York Yankees slugger Alex Rodriguez can relax — Japan's new baseball-playing robot isn't very good.

But A-Rod had better keep an eye on this bot: It has the ability to learn, and can improve its swing over time.

The robot was developed at Japan's University of Electro-Communications in Tokyo and the Okinawa Institute of Science and Technology, Wired reports.

It wasn't created to play baseball, but to show how an artificial brain with a processing speed roughly equivalent to 100,000 neurons can mimic the capabilities of the human cerebellum, the part of the brain that controls motor skills and coordination.

The artificial brain, dubbed a "Realtime Cerebellum," or RC, takes data from an accelerometer to analyze the speed and angle of an approaching baseball, and adjusts the robot's swing accordingly.

"These results suggest that RC provides a means to apply the computational power of the cerebellum as a versatile supervised learning machine towards engineering applications," the researchers write in their study, published in the Feb. 7 issue of Neural Networks.

Like a Little Leaguer at a season opener, the robot's first few swings connect with nothing but air. But then something unusual happens: The baseball bot (basebot?) eventually learns to hit the ball with its flyswatter-like bat.

And no, it doesn't need steroids to improve its performance (yes, A-Roid, we're looking at you).

Follow Marc Lallanilla on Twitter and Google+. Follow us @livescience, Facebook & Google+. Original article on

Marc Lallanilla
Marc Lallanilla has been a science writer and health editor at and a producer with His freelance writing has appeared in the Los Angeles Times and Marc has a Master's degree in environmental planning from the University of California, Berkeley, and an undergraduate degree from the University of Texas at Austin.