Re: FAT robotic controller?

Gal Kaminka (galk@ISI.EDU)
Sun, 7 Dec 1997 22:48:53 +0100 (MET)

(The following bounced of his email, so I'm posting it here):

Hi!

Thor Alexander (harbinger@nospam.sprintmail.com) wrote:
: Can anyone point me to resources for controlling robots (or 2d/3d sims)
: with FAT (fuzzy adaptive theorem), FAM,BAM or other neural-nets?

: Have solid understanding of fuzzy but need a jumping on point for
: control applications.
[snipped]

There isn't too much work on Fuzzy control of robots that I'm aware of,
which is a shame since the field could use some fuzzy-based tools - from
my own experience. The pointers below all refer to fuzzy robot navigation,
on actual robots (not just simulations), but I hope they prove useful
I don't have URLs or exact references handy right now - the following is
strictly of the top of my head, but you're welcome to contact me directly
via email for more detailes.

* Kurt Konolige, Alessandro Saffioti et al. did some good work at SRI.
They both have some of their papers on-line.

* H. Zimmermann's group (I believe - I may be wrong) had a fuzzy
navigation system as part of their Moria robot.

* Yen and Pfluger had a number of papers describing fuzzy-based navigation
as an example of an extended Payton-Rosenblatt command-fusion scheme.
Yen is at Texas A&M university, computer science department.

* Jeremy Baxter did some nice work (especially concerning the use of
"negative rules"), on navigation.

I also did some work in this area, and am now using it and extending it in
the RoboCup domain (simulation track).

I just know I'm forgetting a few more. I remember reading a fairly recent
article in one of the robotics journals (Autonomous Robots, perhaps).
I am currently away from my office and so don't have all the details - but
you're welcome to contact me directly.

Hope this helps.

Gal

--
----------------------------------------------------------------------------
Gal A. Kaminka    galk@isi.edu/galk@usc.edu    http://www.isi.edu/soar/galk/ 
Research Assistant, Applied Philosopher   USC Information Sciences Institute 
     "Death is an engineering problem." -- Bart Kosko, "Fuzzy Thinking"
     "But life is not an engineering task." -- Gal A. Kaminka

******* Crossposted: comp.robotics.research (moderated) ******* Summary: Academic, government & industry research in robotics. Archives and information: http://www.robot.ireq.ca/CRR Charter: ftp://ftp.robot.ireq.ca/pub/crr/Charter Meta-discussions/information: crr-request@robot.ireq.ca