Comments on "A neural network compensator for uncertainties of robotics manipulators"

摘要

It is shown in this letter that the function of the neural network compensator proposed in the original paper is redundant. Perfect rejection of both structured and unstructured uncertainties in the robot dynamic model can be achieved directly without the compensator.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>