Intelligent control of vehicles for “ITS for the sea” applications

In the emerging field of ITS (intelligent transportation systems), "ITS for the sea" refers to the area of maritime traffic. Automated vehicle control systems are a key technology for ITS. This paper presents a model-based neural network adaptive controller for combined surge (longitudinal) and sway (lateral) control of fully automated surface vessels (ASVs). The control algorithm blends a self adaptive neural network module and a classical proportional plus derivative (PD)-like control to menimize the tracking error by completing each other. The adaptive neural module counteracts for inherent model discrepancies, strong nonlinearities and coupling effects. Stability issues are established using a Lyapunov-based method. \´Numerical simulation results using a three degree of freedom nonlinear dynamic model are presented under severe accelerations on curved paths to validate the controller.