Use of Genetic Algorithms to evolve robot behavior?

Thread View: comp.robotics

3 messages

[T] Back to Threads [V] Tree View [G] Group Articles

3 total messages Started by Layne L Ainsworth Sat, 09 Jan 1993 00:21

#1753

Author: Layne L Ainsworth
Date: Sat, 09 Jan 1993 00:21

29 lines
1479 bytes

(A third attempt to post this article)
(Somebody mail me if I am posting this a million times, 'cause I sure
 don't see it in these groups)

Has anyone tried to do this: 

"Herds" of cheap (really cheap), reprogrammable robots, each loaded
with one set of the test "chromosome" population of a Genetic
Algorithm system. They could be evaluated to optimize indivdual
performance, or "hive" well-being.  Each "generation" would be the
same robots, with a new generation of "chromosomes" on board.

Pointers to papers or discussion of the feasibility of such a project
would both be welcome. I would think this could be a job for the
much-heralded and -scorned MiniBoard. Wire up all the connections to
various sensors/actuators and let the herd discover uses for them.

My dream, of course, is a bunch of robots that (who?) could
continuously clean my house. :-)

Thanks.

-Layne



-- 
  Layne Ainsworth | lains@world.std.com <or> ...!{xylogics,uunet}!world!lains
	  The truth can't hurt you; it's just like the dark.

Re: Use of Genetic Algorithms to evolve robot behavior?

#1768

Author: Joerg Heitkoetter
Date: Sun, 10 Jan 1993 15:43

36 lines
1900 bytes

In article <C0K8zq.54A@world.std.com>, lains@world.std.com (Layne L
Ainsworth) writes:
|> Pointers to papers or discussion of the feasibility of such a project
|> would both be welcome. I would think this could be a job for the
|> much-heralded and -scorned MiniBoard. Wire up all the connections to
|> various sensors/actuators and let the herd discover uses for them.
See the SAB-90 conference proceedings:

@Proceedings{SAB91,
  editor =       "Jean-Arcady Meyer and Stewart W.~Wilson",
  title =        "From Animals to Animats. Proceedings of the 1st
                 International Conference on Simulation of Adaptive
                 Behavior",
  booktitle =    "From Animals to Animats. Proceedings of the 1st
                 International Conference on Simulation of Adaptive
                 Behavior",
  publisher =    "MIT Press",
  address =      "Cambridge, MA",
  year =         "1991",
  volume =       "",
  note =         "",
  ISBN =         "0-262-63138-5",
  signature =    "joke",
  keywords =     "artificial life / adaptive behavior",
  attr =         "toRead",
}

Hope that helps.

	-joke

--
Joerg Heitkoetter
Systems Analysis Group
University of Dortmund, Europe
(joke@ls11.informatik.uni-dortmund.de).

Re: Use of Genetic Algorithms to evolve robot behavior?

#1811

Author: Ashwin Ram
Date: Tue, 12 Jan 1993 16:05

25 lines
1745 bytes

In article <C0K8zq.54A@world.std.com> lains@world.std.com (Layne L Ainsworth) writes:
>   Has anyone tried to do this: 
>   
>   "Herds" of cheap (really cheap), reprogrammable robots, each loaded
>   with one set of the test "chromosome" population of a Genetic
>   Algorithm system. They could be evaluated to optimize indivdual
>   performance, or "hive" well-being.  Each "generation" would be the
>   same robots, with a new generation of "chromosomes" on board.

See:

Mike Pearce, Ron Arkin and Ashwin Ram (1992), The Learning of Reactive
Control Parameters Through Genetic Algorithms, in Proceedings of the IEEE/RSJ
International Conference on Intelligent Robots and Systems (IROS-92),
Raleigh, NC, pp. 130-137.

A postscript version of this paper (without figures :-() is available for
anonymous FTP from ftp.cc.gatech.edu:/pub/ai (see the README file or e-mail
me for instructions).

Ashwin Ram <ashwin@cc.gatech.edu>
Assistant Professor, College of Computing
Georgia Institute of Technology, Atlanta, Georgia 30332-0280
(404) 853-9372 (phone)
(404) 853-9378 (fax)

Thread Navigation

This is a paginated view of messages in the thread with full content displayed inline.

Messages are displayed in chronological order, with the original post highlighted in green.

Use pagination controls to navigate through all messages in large threads.

Back to All Threads