[ACT-R-users] ACT-R robot

[Bruce J Weimer MD]

Greg,

I've been reading several of the papers you referenced.  Is there any 
technical information on ACT-R/E and it's implementation?  Is any source 
code available?

Also, I was wondering as I read the papers, is information that's learned 
during a session with the robot stored or saved when the robot's turned off 
or is it lost?  I'm reading through the ACT-R tutorials and it seems that 
each time a model is run, it's reset to run again - there (so far) hasn't 
been any mention of a mechanism to save the information in declarative 
memory, weights, latencies, etc.

Bruce.




----- Original Message ----- 
From: "Greg Trafton" <greg.trafton at nrl.navy.mil>
To: "Bruce J Weimer MD" <bjweimer at charter.net>
Cc: <act-r-users at act-r.psy.cmu.edu>
Sent: Monday, June 23, 2008 11:55 AM
Subject: Re: [ACT-R-users] ACT-R robot


> We've been hooking up ACT-R to our robots for several years now.
>
> We have a new version (OK, a couple new versions) that basically take 
> information from the robot's sensors, put them into ACT-R's audicon or 
> visicon (as appropriate) and go from there.  we're calling our  modified 
> version ACT-R/E (for Embodied).
>
> we have several papers available that describe some of the  capabilities 
> we use, most available at 
> http://www.nrl.navy.mil/aic/iss/aas/CognitiveRobots.php
>
> thanks,
> greg
>