Stable on-line learning neuro-control of an industrial manipulator

We apply our on-line learning neural network approach to joint level trajectory control of an industrial welding robot. This application demonstrates the ability of neuro-control to model complex nonlinear components of a plant, thereby yielding impressive improvements in accuracy compared to the original robot´s controller. In order to set this work in context we briefly review our on-line learning neuro-control method, it has a strict theoretical basis including guarantees of the whole system´s stability