_gaq.push(['_trackPageview']); _gaq.push(['_trackPageLoadTime']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })();

Hacked Kinect on a mobile robot does 3D mapping

By On November 17, 2010 · 2 Comments · In KinectHacks.net News
Philipp Robbel of Personal Robots Group of MIT has installed a hacked kinect on a robot and used it to create 3D reconstruction of the environment by making the robot move around.
Also the robot uses gestures for taking directions.Its uses kinect for 3D mapping.Kinect streams the depth and color images to a remote host for SLAM and 3D map processing.
0 Hacked Kinect on a mobile robot does 3D mapping

Related posts:

  1. 3D Image Software Available for Download
 
If you enjoyed this article, please consider sharing it!
Facebook Twitter Delicious Digg
  • Paul Bouchier

    This is fantastic! Can you share some details of the slam system design and how depth is used? Which slam app do you use? Is this a scheme suitable for making a roomba vaccum a room with knowledge of where it is? Are you running Linux on the onboard PC and shipping the point cloud off to something on an external PC that turns it into something you can feed to a slam algorithm? Exactly how do you do that?

    I’ve been hacking on the roombacomm library from hackingroomba.com – see http://hackingroomba.com/code/roombacomm/ and this is a direction I’d like to go in.

  • Pingback: Contextualization « the eXplore blog