Re: NAO Robot : is Ada there too ?

["Dmitry A. Kazakov" <mailbox@dmitry-kazakov.de>]

On Mon, 13 Jun 2011 09:55:04 +0200, Yannick Duch�ne (Hibou57) wrote:

> Le Mon, 13 Jun 2011 09:19:53 +0200, Dmitry A. Kazakov  
> <mailbox@dmitry-kazakov.de> a �crit:
> 
>> On Sun, 12 Jun 2011 00:03:19 +0200, Yannick Duch�ne (Hibou57) wrote:
>>
>>> We often heard about Lego Mindstorms Robot here, with Ada in the place.  
>>> I
>>> just saw an advertising on a web site leading to this:
>>> http://developer.aldebaran-robotics.com/join/?gclid=CNjagrbsrqkCFYINfAodq1-lJw
>>
>> 500 MHz / 256 MB look pretty barren for any sort of AI + control + image
>> processing [+ voice recognition].
> Add to this, 2 GB of flash memory.

Yes, for a incremental machine learning you would like to have more to
store the learnt stuff, provided the robot would operate more or less
autonomous. (I have an impression that robots like this are rather mobile
sensors/actuators connected over WiFi the host (brain) than true robots.)

> Yes, that's not the must, but already more than what's available to the  
> Lego Mindstorm.

It also lacks standard industrial I/O interfaces for the sensors and
actuators (e.g. EtherCAT or CAN etc), which would allow you to customize
the motherboard and the processor (processors).

> And there was old experiment with AI and Prolog, oin the 80's, on machines  
> with less than that.

I doubt that Prolog can be useful for the AI deployed in a robot. There is
not much inference it would do, more problems like path finding, which are
not logical. Further, even considering logical problems you rather need
fuzzy inference than Prolog's stuff. And certainly Prolog is absolutely
useless for image processing and control.

Ada is the only language you need, really!

-- 
Regards,
Dmitry A. Kazakov
http://www.dmitry-kazakov.de