Paper Info
Title
Stable, online learning using CMACs for neuroadaptive tracking control of flexible-joint manipulators
Abstract
An artificial neural network is proposed for the precision control of flexible-joint robots. The training method uses backstepping in an online, direct neuroadaptive scheme in order to guarantee stability. The online weight updates include a learning term that improves performance while maintaining stability. Albus's cerebellar model arithmetic computer algorithm is modified to work for flexible robots by utilizing radial basis functions to deal with the elasticity. The resulting hybrid network is referred to as CMAC-RBF associative memory or CRAM network. Many of the properties of the CMAC for rigid robot control are kept by using CRAM for flexible-joint robots
Year
DOI
Venue
1998
10.1109/ROBOT.1998.677025
Robotics and Automation, 1998. Proceedings. 1998 IEEE International Conference
Keywords
Field
DocType
adaptive control,cerebellar model arithmetic computers,content-addressable storage,feedforward neural nets,learning (artificial intelligence),manipulators,neurocontrollers,position control,stability,cmacs,associative memory,backstepping,cerebellar model arithmetic computer algorithm,flexible-joint manipulators,neuroadaptive tracking control,online direct neuroadaptive scheme,precision control,radial basis functions,stable online learning,artificial neural networks,computer networks,learning artificial intelligence,gears,robot control,artificial neural network,radial basis function
Robot control,Backstepping,Content-addressable memory,Radial basis function,Control theory,Computer science,Control engineering,Content-addressable storage,Adaptive control,Robot,Artificial neural network
Conference
Volume
ISSN
ISBN
1
1050-4729
0-7803-4300-X
Citations 
PageRank 
References 
5
0.71
5
Authors
2
Name
Order
Citations
PageRank
C. J. Macnab14010.34
D'Eleuterio, G.M.T.28411.83