hairygael's blog

Three complete robots built in 25 days

hairygael's picture

Designing, 3D printing, assembling and painting of these respectively 1.60m, 160m and 1.20m robots was done in 25 days.

I barely had nights to sleep, working alone in my work shop, I thought I wouldn't be able to accomplish the task in time.

The surface finishing with car filler on all the 3D printed parts took me a long time to get a perfect smooth finish for the paint job.


AcapellaSpeech is out of usage

hairygael's picture

AcapellaSpeech is out of usage since yesterday, due to restrictions on the demo mode.

Because we need a speaking robot, I will try to use MarySpeech service instead of AcapellaSpeech service.

So I run a simple script like this:

inmoovTest = Runtime.createAndStart("inmoovTest", "ProgramAB")
inmoovTest.startSession("ProgramAB", "gael", "inmoovTest")
mouth = Runtime.createAndStart("i01.mouth", "MarySpeech")
mouth.setVoice("cmu-bd1-hsmm")


Using "if" function with faceTracking

hairygael's picture

This should be very simple for many of you guys, but since I didn't create the faceTracking service, I am swimming far from offshore to reach the coast.

So, here is what I'm trying to do:


converter for AIML encoded "ISO-8859-1" to "UTF-8"

hairygael's picture

So to make it short.

I found a free French Open Source chat bot which contains a lot of possibilities based on ALICE2.0.

The problem is that all the AIML files are encoded in "ISO-8859-1"

Therefore when I use French with WebKitRecognition it doesn't work correctly and takes only the default answers.

#############################

Here is how the AIML are looking like:


AIML to fetch Google search

hairygael's picture

So I have created or modified various AIML to ty things into InMoov, but this one is giving me trouble.

I made all kinds of tests, but everytime I get something that doesn't work.

#####################################


Extract Blender python gestures to be used with virtual InMoov

hairygael's picture

I’m wondering how Gareth, or anyone else, would proceed to use the below Blender file along with virtual InMoov to create simili human gestures.

The c3d addon for Blender is in the preferences to be added.

http://inmoov.fr/wp-content/uploads/2015/10/walking_slow03.c3d


Meeting MaVo at the Eindhoven MakerFaire Netherland

hairygael's picture

We had a great time meeting more Makers with very interesting projects.

Leon and Marten were also there for fun and great time discussing over what could be done in the near future on InMoov.

As a surprise, MaVo (the person who worked the service Gesture Creator but not least) came to see us, all the way from Germany!

Bright time and good energy!


At Makercon I talked about oject recognition

hairygael's picture

Here is what they have been working on. I just received the link of the github release:

https://github.com/teradeep/demo-apps

 

And of course MyRobotLab:


Adding InMoov sound scheme to your Audiofile directory

hairygael's picture

Thanks to Leon for creating the sound scheme that I have been using since MFParis2014.

Thanks to Sebastien of QuaiLab (France) for creating this script to let all InMoov builders benefit of the sound scheme.

Of course you can do this manually by retrieving the mp3 on my website and replacing the "starting mouth.mp3" in your Audiofile directory. But this is intended to be added as default on my full inmoov script.