Tag Archives: PingPong

Northeastern University’s haptic ball-racket system is one pricey game of paddle ball

Posted on by

Northeastern University's haptic ballracket system is one pricey game of paddle ball

We had the chance to check out a couple of student projects at Northeastern University's fantastically-named Action Lab during a trip to Boston this week. On our quick tour through the facilities, we were shown a haptic controller being used to simulate the act of carrying a cup full of coffee, in order to monitor how people adapt movements to deal with the fluid dynamics of a hypothetical hot beverage inside the equally theoretical cup. The team had all sorts of strange and fascinating controls bandied about the facilities for the purpose of monitoring reactions to movement, but the one that really caught our eye was the ball-racket system. The controller uses a hacked up ping pong paddle connected to an encoder that feeds its real world vertical position into a computer, so test subjects can participate in what looks like rudimentary Atari game of paddle ball. Also on the bottom is a breaking mechanism that applies force to the paddle when the "ball" makes contact, so it feels like the real thing. There's a video of the system in action after the break, and more information about the studies can be found in the source link below.

Continue reading Northeastern University's haptic ball-racket system is one pricey game of paddle ball

Northeastern University's haptic ball-racket system is one pricey game of paddle ball originally appeared on Engadget on Thu, 15 Nov 2012 13:36:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceAction Lab  | Email this | Comments

German robot arm learns ping-pong as it plays humans, might rival its masters

Posted on by

Germans robot arm learns pingpong as it plays, might rival its human masters

We like to tell ourselves that learning by doing is the best strategy for improving our skills, but we seldom apply that philosophy to our robots; with certain exceptions, they're just supposed to know what to do from the start. Researchers at the Technical University of Darmstadt disagree and have developed algorithms proving that robot arms just need practice, practice, practice to learn complex activities. After some literal hand-holding with a human to understand the basics of a ping-pong swing, a TUD robot can gradually abstract those motions and return the ball in situations beyond the initial example. The technique is effective enough that the test arm took a mere hour of practice to successfully bounce back 88 percent of shots and compete with a human. That's certainly better than most of us fared after our first game. If all goes well, the science could lead to robots of all kinds that need only a small foundation of code to accomplish a lot. Just hope that the inevitable struggle between humans and robots isn't settled with a ping-pong match... it might end badly.

Filed under: ,

German robot arm learns ping-pong as it plays humans, might rival its masters originally appeared on Engadget on Sun, 28 Oct 2012 07:57:00 EDT. Please see our terms for use of feeds.

Permalink New Scientist  |  sourceUniversity of Texas (PDF)  | Email this | Comments