Title :
A novel neural controller for robot manipulator
Author :
Yu, Jiang ; Xu, Li ; Jiang, Jingpig ; Zhu, Tong
Author_Institution :
Dept. of Electr. Eng., Zhejiang Univ., Hangzhou, China
Abstract :
The success of CMAC (cerebellar model articulation control) for real-time dynamic manipulator control has been exploited by Miller etc. Fundamentally, this kind of neural network deals with discretized state variables and needs relatively large memory to store data. Impressed with the backpropagation´s potential in learning complicated nonlinear mappings, Xu, proposed LBP (localized backpropagation network), which organizes many localized BP subnets into a whole network. In this paper, we discuss its principal further and the practicability of this kind of network in real-time robot manipulator control is also investigated. Simulation results prove this neural network´s architecture has good prospects for applications
Keywords :
backpropagation; cerebellar model arithmetic computers; industrial manipulators; manipulator dynamics; neurocontrollers; real-time systems; cerebellar model articulation control; complicated nonlinear mappings learning; discretized state variables; localized backpropagation network; neural controller; real-time dynamic manipulator control; robot manipulator; Backpropagation; Computational modeling; Computer architecture; Control systems; Convergence; Electric variables control; Manipulator dynamics; Neural networks; Real time systems; Robot control;
Conference_Titel :
Industrial Electronics, Control, and Instrumentation, 1996., Proceedings of the 1996 IEEE IECON 22nd International Conference on
Conference_Location :
Taipei
Print_ISBN :
0-7803-2775-6
DOI :
10.1109/IECON.1996.570755
