Second Order Sliding Mode Adaptive Neurocontrol for Robot
Abstract
In this paper we present a low dimensional adaptive neural networkcontroller for robot manipulators with fast convergence oftracking error. Its novelty lies in the low dimensional network,smooth control input and very fast convergence that reduce thecomputational cost that face the problem of over parameterization.The control strategy is based on a second order sliding surfacewhich drives the controller and the online computation of weightswith a chattering-free control output. Furthermore, a time basegenerator induces well-posed finite time convergence of trackingerrors for any initial condition. We validate our approach including experimental results obtained in a planar 2 dgf manipulator.
