Maybe somebody should suggest using a Mycroft unit to this guy?
Especially regarding the part where he says:
For my Echo based implementation, I had the
constraint of using Echo’s “Alexa, turn on X” and “Alexa, turn off X”
commands. Having this relatively long phrase makes control more
cumbersome than simple moment to moment LEFT’s and RIGHT’s or just naming a destination. That combined with Echo not responding instantly (voice is processed on Amazon’s servers) and sometimes not recognizing speech correctly makes a real-time micromanaged system not practical.
With the correct intent models, could we not design a similar system to be significantly less verbose? i.e. “Wheelchair - forward!” (especially if Adept cuts down on the time it takes between finishing speaking and processing)