This article presents a prescribed-time tracking control method for underactuated unmanned surface vessels (USVs) using a neural reinforcement learning (RL) approach. First, the hand position approach, addressing the underactuated characteristic, is employed to convert the model of USV into the integral cascade form. Second, inheriting the advantages of prescribed performance control (PPC), the proposed controller not only stabilizes the tracking error within an asymmetric prescribed-time range, but also removes the limitation of initial conditions. Subsequently, the identifier—actor-critic architecture is introduced in the optimized backstepping design, which gives the solution of the Hamilton–Jacobi–Bellman (HJB) equation. Meanwhile, the relative threshold event-triggered mechanism is also considered to reduce the communication burden and executive frequency of actuators. Finally, employing the Lyapunov stability theory, it is proven that all signals in the closed-loop system are bounded, and the developed control scheme is demonstrated to be effective through simulation and experimental results.

In this paper, we investigate a neural adaptive formation control problem for underactuated unmanned surface vehicles (USVs). Considering the limitation of communication distance and the security of formation systems, collision-free and connectivity maintenance are guaranteed by defining a prescribed-time tuning function and proper error transformation. Furthermore, a new nonlinear first-order filter, solving the complexity problem, is designed to promote the system performance. Subsequently, neural networks (NNs) are used to approximate USVs’ dynamics and their transient performance is improved by prediction error. By blending prediction errors and neural approximation, it is guaranteed the general external disturbances and approximation errors are compensated via constructed disturbance observers (DOs), simultaneously. Meanwhile, utilizing the minimal number of learning parameters (MNLPs) methodology, the number of NNs’ learning parameters can be significantly reduced. It is rigorously proved that all signals in the closed-loop system are bounded via Lyapunov stability theorem. Finally, simulation and experimental studies are presented to verify the effectiveness and advantages of theoretical results.