Fixed-time multilayer neural network-based leader–follower formation control of autonomous surface vessels with limited field-of-view sensors and saturated actuators

This paper proposes a fixed-time multilayer neural network-based formation control problem for the autonomous surface vessels based on the relative distance and orientation angle constraints. The proposed approach only expends the measurements of comparative distance and orientation angle sensors with a limited field-of-view (FOV). The proposed strategy is able to obtain the perfect trajectory tracking performance when the motion ability of all the vessels is restricted into a predefined region owing to the limited FOV limitations. An asymmetric time-varying barrier Lyapunov function is efficiently utilized to cope with the limited FOV constraints. A multilayer neural network is efficiently applied to estimate the model uncertainties and unmodeled dynamics through the online updating of weight matrices. The suggested controller preserves both the comparative distance and orientation angles between consecutive vessels inside the predefined constraints, and the state errors converge to small residual sets around the zero in a fixed time. This feature accelerates the convergence speed and modifies the transient performance of the trajectory tracking control for all the vessels in the formation construction.