Playing in the "Lab" with Cognitive Toys
I've been playing with toys in my spare time - and thinking about how Cognitive Computing services might make a toy interesting for kids. In particular, I'm looking at (1) How toys can LISTEN and engage in SENSEMAKING of what kids are saying and (2) How the toys can REACT - for example, move limbs, eyes, or say something back.
What Makes a "good" Cognitive toy?
I'm not sure yet. My daughter has a Teddy Bear. His name is Ted. He doesn't say much - but they are pals.
I'm wondering how much the toys need to do, to engage and delight kids. My kids have furbees - which I find quite noisy - but they are verbose and the kids also like them. So we've got two data points - silent ted and frantic furbees.
I'm assuming that a toy that REACTS is going to be a hit - listening to what kids say and how they say it and then doing something. We'll see as we continue to build and test the prototypes.
Lab Test - Basic Speech & Responses
This VIDEO is a VERY early stage test of integrating a few different components. We integrate
- IBM Watson speech to text (STT),
- R Studio (as main code base)
- Python (to call the serial pieces of the Arduino, as R made it really hard)
- Arduino driving servos with eyeballs on them
- IBM Watson Text to Speech for the Response
With Voice Controlled Helicopter
The Name - Boaty McBoatFace
In case you're not familiar with the origin of this name....
About this blog
This is an informal blog that explores tools, code and tricks that group members have developed to engage IBM Watson cognitive computing services - from the R Programming Language. Packages include RCURL to access Watson APIs - for services that include Natural Language Classifier and Speech to Text. THIS IS MY PERSONAL BLOG - it does not represent the views of my employer. Code is presented as 'use at your own risk' (it has lots of bugs)
Created: September 13, 2015English