GroG's blog

Emoji Service Preview

GroG's picture

 

One step closer to work-e == gert-e

This is a preview of the Emoji service ...  cuz what is better to express the nuances of emotion than emojis ?
Things to fix : (oh god .. the list goes on ...)


Sparse Feature Optical Flow

GroG's picture

I've added "OpticalFlow" filter to OpenCV (worke branch), and here seeing throuhg work-e's kinect eye - you can see worke-e turning left ... or was it right ? :) 

So to make this useful for collision avoidance, some work will need to be put into it.  Like describing the direction vector.  Also some semi-intelligent pruning of data. 

It starts by getting good features to track. Which itself has a few parameters to tweak.


freenect-glview vs mrl

GroG's picture
freenect-glview image
 

BoofCV - reloaded ...

GroG's picture

Thanks wvantoorn for the link.
It looks like BoofCV is active again ... Woot !

Since there were no updates for a long time I think kwatters and myself lost interest in this project and MRL's corresponding service - http://myrobotlab.org/service/BoofCv


Kinect Navigation Filter in OpenCV Service .. (wip)

GroG's picture

High Road - Kinect mounted high, pointed down (glview)

Low Road - Kinected mounted low - pointed straight (glview)


Work-E has grown antenna

GroG's picture

Thanks again to Ray's suggestion, I purchased a $9.00 DC-DC buck converter from Amazon - which will be powering all the 12v devices on Work-E such as the wifi router and the kinect ... Progress !


Virtual Joysticks are Un-Breakable ! .. (mostly)

GroG's picture

It took "too" long, but I got virtual Joysticks working ! ...  
To be precise, any device (joysticks, gamepads, keyboards, touchpads, .. etc) which the Joystick service can see can now be "virtualized".

Ok, so what the hell does that mean ? :)


MotorControl and MotorController - Range Mapping, Min Max, Input Output

GroG's picture

One of challenges with the old mapper was what to do when setting new values of min & max.
In the above diagram we see a range established by a min & max. 

e.g.  mapper = new Mapper(-1, 1, -1, 1)  

min & max input will be -1 & 1  .. min & max output will be -1 & 1


Learning Dexterity

GroG's picture

 

Thanks Jeff Schneider !!!

Original Link :

https://blog.openai.com/learning-dexterity/

Very Lovely Doc :


Speech and Security Updates

GroG's picture

AbstractSpeechSynthesis

Inspired from moz4rs initial work here.