On-line adaptation in robot control
David A. Fraser, F. Azhar, Kaspar A. Althoefer · 1993
Neural nets offer the chance of controlling a system effectively without knowing the relations between the required and directly controlled properties of the system. The authors report the training and performance of neural nets in the control loops of a robot arm, which are able to adapt to changes in the robot dynamics and reoptimise the control functionality without requiring intervention from an operator.