Command filtered robust adaptive NN trajectory tracking control for marine surface vessels under input saturation

Abstract

In this paper, we propose a robust adaptive neural network (NN) trajectory tracking control scheme for marine surface vessels (MSVs) in the presence of dynamic uncertainties and unknown environmental disturbances under input saturation in the command filtered vector-backstepping design framework. The adaptive NNs are applied to reconstruct the uncertainties of MSV dynamics. Two designed adaptive laws online provide the estimation of the norm of NNs weight matrix and the sum of the bounds of NN approximation errors and external disturbances, respectively. An auxiliary dynamic system (ADS) is utilized to handle the input saturation effect. The command filter is used to avoid the derivation operation of virtual control, and a compensating signal is designed to remove the effect of the error arising from the command filter for improving the tracking control performance. It is theoretically shown that all the signals in the closed-loop trajectory tracking control system of MVSs are bounded. Finally, simulation results verify the effectiveness of our proposed control scheme for MSVs.