Robust adaptive neural network-based control of robot manipulators subject to external disturbances

The dynamics of the robot manipulator, in general are highly nonlinear and subject to varying payload, potential external disturbance, and model uncertainties. To solve the strong nonlinearity and unmodeled dynamics problems with unknown upper bound of the external disturbances in robot manipulator control, a new robust adaptive neural network-based controller is proposed in this paper. As compared with the existing controllers, the designed control law can overcome the tolerable external disturbances, where a priori knowledge of upper bound for the system uncertainties and external disturbances is not required. The stability and convergence properties of the closed-loop system are analytically proved using Lyapunov stability theory. Simulations are performed for a three-link manipulator to illustrate the viability and the advantages of the proposed controller.