background preloader

AI

Facebook Twitter

Elina Hiltunen sur Twitter : "Yes! I got my newest book today from post! #future #technology #singularity #ai #robotics #ICT #cyber #transhumanist. Watch?v=pi7h6nmkvAM&feature=youtu. SLAM for Dummies.doc. Hackathon-web. Kinect and MRPT | The Mobile Robot Programming Toolkit. 1. Overview MRPT implements a common C++ interface to Xbox Kinect, a new RGB+D sensor with an immense potential in mobile robotics. The implementation offers the user only one unified interface.

Behind the scenes, MRPT uses one of these libraries to actually access the sensor: OpenKinect’s libfreenect on Unix/Linux and Windows.CL NUI on Windows. Intensity (RGB) images are automatically converted to the OpenCV’s format (mrpt::utils::CImage), 10bit or 11bit raw depth is converted to meters, and methods are provided to handle the two matrices of camera parameters (one for the RGB camera and one for the “range image”).

Observations grabbed from MRPT’s Kinect C++ class can be directly saved, among other types, in rawlogs for grabbing robotics datasets, or can be used online for any real-time application. 2. Tutorials:Examples:Example application: kinect_3d_view. Example1: See the links below for source code and more infoExample2: Application: kinect-3d-slam 3. 3.1. Notes on libusb for Windows: How I built a self-driving (RC) car and you can too. Updated January 11th 2013: Watch my BACON talk on this project on vimeo. Updated January 2nd 2012: the source code is now open source and available on github.

Recently, I have been refreshing my knowledge of Machine Learning by taking Andrew Ng's excellent Stanford Machine Learning course online. The lecture module on Neural Networks ends with an intriging motivating video of the ALVINN autonomous car driving itself along normal roads at CMU in the mid 90s. I was inspired by this video to see what I could build myself over the course of a weekend. From a previous project I already had a cheap radio controlled car which I set about trying to control. The ALVINN system captures video frames every couple of seconds and passes them to a (series of) neural networks which have been trained by watching a human drive in similar environments.

Record — The system captures video frames and the control input from a human driver (me!) Design Anatomy of a self-driving RC car Driver app running on Mac OS X.