kwatters's blog

Connector and Document Processing Pipeline Framework

So, my work work is really around building custom search engines.  I am constantly re-inventing the wheel of creating a framework that can crawl a data source (such as a website , rss feed, file system, database.. etc)

Leap Motion -> Translate / Rotate -> Inverse Kinematics -> publish joint angles -> InMoovArm -> gain + phase shift of angles -> Servo   Woo Hoo ....  End to end functionality.

Leap Motion + Inverse Kinematics + WebGUI !

Well.. I started testing the leap motion locally. I found that the leap motion, sitting on my desk can measure a lot of things about the orientation of my hand in front of my body.  It recognizes both left and right hand postion, orientation and finger direction as compared to the palm...

Initially, I am interested in tracking the position of the hand in the frame so I want to start getting a sense of the x,y,z  range reading.  

I see that the x,y,z values range between

An Agent has been detected in the matrix!

So, as it turns out the Oculus Rift latest SDK and Runtime no longer supports using "extended model" with the Oculus Rift.  Which means we need to update our support for it.  I have started working with LWJGL and some examples.  Above you can see a virtual screen rendered in front of the user in the oculus rift. 

Here is a list of the current services in MRL so we can figure out what to QA.

Links :

Update: Here's a better preview using MaryTTS

Here's a sneak peak at the new WebGUI with ProgramAB and the speech recognition using Google Chrome web speech toolkit.

So, I saw on hack-a-day that there was going to be a meetup at the Artist Asylum here in Boston.  I wasn't even aware of any maker spaces around here, so I just had to go check it out.  Awesome times, lots of cool projects, including.. yes..  a hover board... 

Ok, So I realize that I'm editing and updating this blog in reverse.. but so be it.  Anyway, here's another little update on the progress with these bevel gear / robot arm joint project.  It moves!  It knows where it moves!  

Well, as we open the gateways to blender from MRL, it seemed like a pretty obvious leap to start trying to render point cloud data from the kinect via OpenNI in blender.  I had the kinect write out to a text file all the x,y,z points.  In a small python script in blender, I loaded that text file and rendered small circles for each point.  

Just came across this robot...  It's a bit more agile than the InMoov .