Command filtered backstepping control of constrained flexible joint robotic manipulator

Here, an adaptive radial basis function (RBF) neural network (NN) backstepping controller is proposed for a class of input-constrained flexible joint robotic manipulators represented by strict-feedback form with unknown terms, external stochastic disturbance, and output disturbance. The approach robust against both deterministic uncertainties disturbances copes the control input amplitude saturation. Moreover, deploying minimal learning parameter method command filter technique, computational burden derivative terms greatly decreases. Considering mean-value theorem assists us to avoid need having saturation bounds in prior. suggested tracking scheme mandates closed-loop system states be semi-globally bounded-in-probability. Also, quartic Barrier Lyapunov utilized force error confined within pre-chosen small region around origin. Eventually, numerical simulation robot manipulator single link performed show effectiveness performance developed method.