Modified Line-of-Sight Guidance Law With Adaptive Neural Network Control of Underactuated Marine Vehicles With State and Input Constraints

Abstract

This article presents a modified line-of-sight (LOS) guidance law and an adaptive neural network (NN) controller for underactuated marine vehicles in the presence of uncertainties and constraints. Unlike conventional LOS guidance, the proposed guidance law counteracts the drift caused by external disturbances to maintain zero cross-track error. Furthermore, an adaptive NN controller is designed using the barrier Lyapunov function (BLF) to deal with the system constraints and disturbances affecting unknown vehicle dynamics. The stability analysis of the adaptive controller guarantees the uniform ultimate boundedness of the closed-loop system. The proposed control strategy is verified in the simulation and experimental environment in the presence of external disturbances. Both simulation and experimental results confirm that the proposed modified LOS guidance law and adaptive NN controller guarantees asymptotic convergence to the desired path and maintains zero cross-track error despite environmental disturbances.