% This code is copyrighted by Stanford University.
% Author: Ashutosh Saxena, Justin Drieymeyer
% Code cannot be used for commercial purposes.
% Use of the code, if used with permission from authors, must acknowledge:
% Learning to Grasp Novel Objects using Vision,
% Ashutosh Saxena, Justin Driemeyer, Justin Kearns, Chioma Osondu, Andrew Y. Ng. In 10th International Symposium on Experimental Robotics (ISER), 2006.
% Robotic Grasping of Novel Obects,
% Ashutosh Saxena, Justing Driemeyer, Justin Kearns, Andrew Y. Ng, In Neural Information Processing Systems (NIPS), 2006.
% More details / new papers at: http://ai.stanford.edu/~asaxena/learninggrasp/


The Matlab code is provided as is.  It contains bugs, and would require
the person to provide missing things. (See the papers for algorithmic details.)

If some part is in particular missing, Ashutosh could provide some clarifications,
or provide code on what is missing.


-   The depth feature vector is not necessary for it to work.  You can train and test it
    on images only, with reasonably high accuracy.

-   For dataset and relevant code, see: http://ai.stanford.edu/~asaxena/learninggrasp/data.html

-   Some code might be missing, please let me know --- I could have forgotten to upload it.