Re: AW: FAT robotic controller?

Jamey (jlivings@top.eng.utoledo.edu)
Mon, 22 Dec 1997 19:13:45 +0100 (MET)

You may want to check out the work by J. Albus with CMAC (cerebellar model
articulation controller). He specifically used it for robot control. I
realize it is not strictly fuzzy but may lead you to some interesting and
applicable solutions. One specific reference:

Albus, J. [1975]. "A new approach to manipulator control: The cerebellar
model articulation controller (CMAC)." Trans. ASME J. Dyn. Syst. Meas.
Control 97:220-227.

Also mentioned in:

Neural Fuzzy Systems, A Neuro-Fuzzy Synergism to Intelligent Systems
by Chin-Teng Lin and C.S. George Lee
1996 Prentice Hall
ISBN: 0-13-235169-2

>> ----------
>> Von: Thor Alexander[SMTP:harbinger@nospam.sprintmail.com]
>> Antwort an: harbinger@nospam.sprintmail.com
>> Gesendet: Montag, 8. Dezember 1997 00:38
>> An: Multiple recipients of list
>> Betreff: FAT robotic controller?
>>
>> 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.
>>
>> Need to control simple robotic systems (2dof arm joint, and 6dof ball
>> joint) for starters.
>> Will then need to build more complex systems from these primitive
>> joints. Would like
>> to train control system with expert (ie-human controller) and then
>> remove expert from
>> system and have it run from the learned data.
>>
>> Any help would be greatly appreciated,
>> T.Alexander
>>
>> ******* 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
>>
>
>
>
**********************************************
@ Jamey T. Livingston @
@ Graduate Student in Electrical Engineering @
@ University of Toledo @
**********************************************