Meet the Guessing Robot

Loraine Lawson

It's always exciting for me when researchers create robots, flying cars, Death Stars -- anything that looks like it actually walked out of a sci-fi movie, no matter how Ed Wood-esque it might be.


So, of course, I was thrilled to read in the New Sciencist Tech that Purdue University researchers have a self-navigating robot, which moves through buildings using a little mapping and some mathematical guesswork.


This solves a major problem with robots, in that these robots can navigate successfully by mapping as little as 33 percent of a building -- at least in simulations. They use an algorithym to guess the rest. Normally, robots have to map the whole area before they can move around -- a painstakingly slow and resource-intensive process.


But what really impressed me is that the little guy, pictured in the BBC's article, looked a lot like the little mouse droids scooting around the Death Star.


OK. So I'm easily impressed.


The point is, if this technology works, you could have robots that can navigate a building much quicker than existing robots. And that's bound to have all kinds of real-world ramifications. For instance, the Roomba will be much more adept at sweeping once it can figure out the rug is square.


In part, the robot maps with what scientists call SLAM (simultaneous localization and mapping) technology. This lets the robot build a map of the area while tracking its position.


Scientists are research how to use SLAM for endoscopic surgical instruments, while the DOD has its heart set on self-driving vehicles.

Add Comment      Leave a comment on this blog post

Post a comment





(Maximum characters: 1200). You have 1200 characters left.




Subscribe to our Newsletters

Sign up now and get the best business technology insights direct to your inbox.