Adaptive neural network control for marine surface vehicles platoon with input saturation and output constraints

This paper addresses the decentralized problem for marine surface vessels (MSVs) in the presence of unknown unmodeled nonlinear dynamics, time-varying external disturbances and input saturations. First, platoon formation is proceeded by using line-of-sight (LOS) guidance. Since each marine vehicle can only acquire information from its immediate predecessor, a symmetric barrier Lyapunov function (BLF) is employed to guarantee the formation errors constrained within a certain range such that leaders and followers can preserve the predefined information structure and ensure the correct steady-state regime. Next, due to the superior approximation capability of an adaptive neural network (NN), we propose a BLF-based controller to deal with the model uncertainties. Further, an auxiliary design system is introduced to compensate for the effect of input saturation. Finally, the uniform ultimate boundedness of all the state errors can be proved and simulation examples are presented to illustrate the effectiveness of the proposed method.