Newsgroups: comp.robotics
Path: brunix!uunet!charon.amdahl.com!pacbell.com!decwrl!sdd.hp.com!saimiri.primate.wisc.edu!zaphod.mps.ohio-state.edu!howland.reston.ans.net!bogus.sura.net!udel!sbcs.sunysb.edu!shane
From: shane@cs.sunysb.edu (Shane Bouslough)
Subject: Re: Tracked mobile robot dead-reckoning
Message-ID: <1993Jan27.041520.7120@sbcs.sunysb.edu>
Sender: usenet@sbcs.sunysb.edu (Usenet poster)
Nntp-Posting-Host: sbgrad7
Organization: Dept of Computer Science, State U of NY at Stony Brook
X-Newsreader: Tin 1.1 PL5
References: <1993Jan26.183938.5241@memstvx1.memst.edu>
Date: Wed, 27 Jan 1993 04:15:20 GMT
Lines: 27

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
