Title :
Adaptive robot control using a processor network
Author :
Azhar, F. ; Fraser, D.A.
Author_Institution :
Dept. of Electron. & Electr. Eng., London Univ., UK
Abstract :
Control of a revolute robot manipulator has been distributed over a transputer network. Feedforward and feedback position control filters for the three major axes have been implemented as neural nets. With one hidden layer and trained using back-propagation. The feedforward filter continues to adapt during operation and shows a steady improvement in control quality, and the ability to adapt to changes in the system dynamics
Keywords :
adaptive control; backpropagation; computerised control; feedforward neural nets; manipulators; position control; three-term control; transputer systems; adaptive robot control; back-propagation; control quality; feedforward position control filters; hidden layer; neural nets; processor network; robot manipulator; system dynamics; transputer network; Adaptive control; Control systems; Feedforward neural networks; Filters; Manipulators; Neural networks; Neurofeedback; Position control; Programmable control; Robot control;
Conference_Titel :
Parallel and Distributed Processing, 1993. Proceedings. Euromicro Workshop on
Conference_Location :
Gran Canaria
Print_ISBN :
0-8186-3610-6
DOI :
10.1109/EMPDP.1993.336384
