Title :
Neural network servo control of a robot manipulator joint in real-time
Author :
Charney, Douglas M. ; Josin, Gary M.
Author_Institution :
Neural Systems Inc., Vancouver, BC, Canada
Abstract :
Empirical results are presented for a real-time experiment where a feedforward neural network is used to replace an existing proportional-derivative (P-D) servo controller and trained online in real-time using a performance measure to control positioning of a robot manipulator joint. The optimized neural network controller was tested online as both a fixed and adaptive controller, with step and ramp input commands, under different joint loading conditions. The results are compared to the existing P-D controller
Keywords :
adaptive control; microcomputer applications; neural nets; position control; robots; servomechanisms; P-D controller; adaptive controller; feedforward neural network; fixed controller; joint loading conditions; neural network servo control; position control; robot manipulator joint; servomechanisms; Feedforward neural networks; Manipulators; Neural networks; PD control; Position measurement; Proportional control; Robots; Servomechanisms; Servosystems; Testing;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170673
