🚀 go-pugleaf

In article <1993Jan27.041520.7120@sbcs.sunysb.edu>, shane@cs.sunysb.edu (Shane Bouslough) writes:
> graesserac@memstvx1.memst.edu wrote:
> 
> : This would imply the robot has an internal representation of its environment
> 
> and also
> 
> : Of course, I haven't done this, but it strikes me as similar to Rodney 
> : Brook's method in a few of his subsumption architecture robots...
> 
> Perhaps I'm mistaken, but from what I've read of Brooks, that's exactly the
> *opposite* of what subsumption achitecture does. I thought his idea was let
> the environment tell you where you are, and don't use an internal
> representation at all. The net, as usual, will correct me if I'm wrong :-).
> 
> I believe one paper was titled "Planning is just a way of avoiding figuring
> out what to do next."
> 
> : Mark C. Langston
> : langston@memstvx1.memst.edu (still inop)
> : graesserac@memstvx1.memst.edu (my prof's, I'm reachable via it)
> : fugue@mindvox.phantom.com (but I don't check this every day)
> 
> -Shane
> 
> --
> Shane Bouslough       | #include <stddisc.h>
> shane@sbcs.sunysb.edu | "Follow your bliss" - Joseph Campbell


I think you misunderstood.  I was using internal representation as a 
_CONTRAST_ to using vectors derived from sensory input to navigate,
a 'la Brooks.  I didn't realize I was being vague.

-mark langsotn