Alt-BEAM Archive
Message #02332
To: Steven Bolt sbolt@xs4all.nl
From: Bob Shannon bshannon@tiac.net
Date: Wed, 14 Apr 1999 21:37:08 -0700
Subject: [alt-beam] Re: CPU again? (was Beam genome)
Steven Bolt wrote:
>
> On Tue, 13 Apr 1999, Bob Shannon wrote:
>
> > > >Of course we would also have to have competitions, to test which sets of
> > > >behaviors were superior to other sets. Identical platforms with
> > > >different behavior sets could be placed into an arena (not a park) and
> > > >observed. Simple timed trials common in animal behavior experiments
> > > >could be used similar to the firefighting contests.
> >
> > True, but if each hard-wired controller is in a unique body, we
> > cannot easily know how much of a given robots behavior is due to
> > the controller, and how much is due to the body.
> >
> > I feel that the ability to 'transplant' sets of behaviors and directly
> > compare them in a common body.
>
> But the main weak points of the current robot generation are
>
> - Inadequate mechanics
> - Inadequate sensors
I strongly disagree. The controller is, and has been the major design
problem.
Sensors today far exceed our abilities (even as humans) to process their
data.
BEAM research explicitly states that the goal is to increase the
'survival space'
and behavioral efficiency.
How are the mechanics or sensors available today inadequate?
> So imho one might define the arena for competition, but progress
> would be very constrained if only standard hardware is allowed to
> compete.
Agreed.
Non standard hardware can compete against other designs, standard or
otherwise.
This would be important in providing an ability to directly test
mechanical design
improvements as well as new behavioral sets.
------------------------------------------------------------------------
eGroup home: http://www.eGroups.com/list/alt-beam
Free Web-based e-mail groups by eGroups.com
Home