Title :
A neural network-based robot controller
Author :
Derbal, Y. ; Bayoumi, M.M.
Author_Institution :
Queen´´s Univ., Kingston, Ont., Canada
Abstract :
A neural network robot controller and a learning rule that is appropriate to closed-loop control of robot manipulators in particular and to dynamic systems in general are proposed. The stability of the closed-loop system is addressed using the input-output stability theory. Extensive simulations have been carried out to study the performance of the proposed neural network controller when applied to a two-degree-of-freedom robot arm
Keywords :
closed loop systems; control system analysis; learning (artificial intelligence); neural nets; robots; stability; closed-loop control; dynamic systems; input-output stability theory; learning rule; neural network robot controller; robot manipulators; simulations; stability; two-degree-of-freedom robot arm; Acceleration; Equations; Feedforward neural networks; Neural networks; Neurons; Optical propagation; Robot control; Sampling methods; Vectors; Velocity control;
Conference_Titel :
Systems, Man and Cybernetics, 1992., IEEE International Conference on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-0720-8
DOI :
10.1109/ICSMC.1992.271661
