Identification and decentralized adaptive control of robotic manipulators using dynamical neural networks

Abstract

Summary form only given, as follows. A multilayer dynamical neural network together with a supervised training scheme that employs an LMS updating rule was used for the online identification and decentralized adaptive control of multijointed robotic manipulators. Some characteristic features of the control scheme were obtained, and a quantitative evaluation of its performance in terms of tracking desired motions was carried out.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>