We love robots here at Table Tennis Nation, especially the ping pong playing robots. Luckily, it seems we’re living in the gold age for table tennis playing robots (and no, we’re not talking about ball feeders). We’re talking about robots that hit with other robots, play against other other robots, robots that play humans, robots that beat humans, robots that intimidate humans, robots that pick up balls, and robots that are balls. ROBOT PING PONG, what’s not to love?
Given our enthusiasm, we were excited to hear that MIT is getting in on the ping pong action too by developing an algorithm to help robots track a ping pong ball in the air, especially in “cluttered” settings where the MIT system is 15% better than others. Ummmm, are ping pong playing robots coming to play us in our basements soon?
A Massachusetts Institute of technology (MIT) student improves robots’ abilities to recognise (sic) objects and their orientation in a project designed to teach them to play table tennis.
The algorithm, designed by Jared Glover, a graduate student in MIT’s Department of Electrical Engineering and Computer Science, exploits a statistical construct known as the Bingham distribution. Glover has created an open-source software tool designed to speed up the Bingham distribution calculation while analysing (sic) orientation of ping-pong balls in flight, as a part of a broader project to teach robots to play table tennis.
The algorithm offers a particular improvement in robots’ visual recognition performance in settings where visual information is particularly poor, performing 50 per cent better than its competitors.
Compared with its rivals, the system is 15 per cent more effective at identifying familiar objects in cluttered scenes. However, the creators believe the nature of the Bingham distribution will enable making it even more effective in settings where information is patchy or unreliable.
You can read more about the research here, but if there’s one takeaway quote from the inventor, Jared Glover, it’s this one, “You can spend your whole PhD programming a robot to find tables and chairs and cups and things like that, but there aren’t really a lot of general-purpose tools. With bigger problems, like estimating relationships between objects and their attributes and dealing with things that are somewhat ambiguous, we’re really not anywhere near where we need to be. And until we can do that, I really think that robots are going to be very limited.”
Ping pong playing robots are a big deal. We need to end this government shutdown and just commit all our resources to creating the world’s greatest table tennis playing robots.