Robust backstepping control of robotic systems using neural networks

Neural network (NN) controllers for the robust back stepping control of rob otic systems in both continuous and discrete-time are presented. Control ac tion is employed to achieve tracking performance for unknown nonlinear syst em. Tuning methods are derived for the NN based on delta rule. Novel weight tuning algorithms for the NN are obtained that are similar to epsilon-modi fication in the case of continuous-time adaptive control. Uniform ultimate boundedness of the tracking error and the weight estimates are presented wi thout using the persistency of excitation (PE) condition. Certainty equival ence is not used and regression matrix is not computed. No learning phase i s needed for the NN and initialization of the network weights is straightfo rward. Simulation results justify the theoretical conclusions.