Finite time control scheme for robot manipulators using fast terminal sliding mode control and RBFNN

Abstract

Based on terminal sliding mode control, a finite time tracking control scheme, which utilize the advantage of fast terminal sliding mode control and neural network, is presented for robot manipulators. A modified form of sliding surface is considered by introducing two nonlinear terms in the sliding surface. Then a novel robust control scheme is proposed, which shows the strong robustness towards uncertainties and disturbance and as a result the finite time convergence of the tracking error is achieved. The radial basis function neural network is utilized to estimate the nonlinearity of the robot dynamics using update laws. Furthermore the adaptive compensator eliminates the need of knowledge about the upper bound of external disturbances and neural network reconstruction error. The numerical simulation result shows the effectiveness of proposed controller for the case of microbot type robot manipulator in a comparative manner.