Unmanned surface vessels (USVs) are supposed to be able to adapt unstructured environments by means of multi-sensor active perception without any human interference, and high-accuracy path following is achieved for USVs by effective control strategies and intelligent devices of e-navigation. This paper proposes a finite-time predictor line-of-sight (LOS)-based integral sliding-mode adaptive neural (FPISAN) scheme for the path following of USVs in the presence of unknown dynamics and external disturbances, which copies with the problem of merging with the kinematic level and the kinetic level of USVs. From the point of view of USVs' practical engineering, the inertia matrix of USVs maintains nonzero off-diagonal. In order to ensure that USVs can converge to and follow a defined path, a novel LOS-based guidance law that can acquire sideslip angles by error predictors within a finite time is presented, called finite-time predictor-based LOS (FPLOS). Then, the path-following control laws are designed by combining the neural network (NN) technique with the integral sliding-mode method, where radial basis function NN (RBFNN) is applied to approximate lumped unknown dynamics induced by nonparametric uncertainties and external disturbances. The theoretical analysis verifies that the path-following guidance-control system of USVs is semiglobally uniformly ultimately bounded (SGUUB) with the aid of Lyapunov stability theory. The effectiveness and performance of this presented scheme are illustrated by simulation experiments with the comparison.

An optimal tracking control problem is critical for marine surface vessels (MSVs) with full state constraints, input constraints, external disturbances, and model uncertainty terms. For solving an MSV’s position and velocity constraints, a barrier Lyapunov function (BLF) and control barrier function (CBF) are introduced and combined with prescribed performance functions, and then, an adaptive dynamic programming (ADP) optimized tracking control strategy is presented based on the two functions. A dynamic event-triggered mechanism is employed, which reduces the number of triggers by tracking the intermittent transmission of error signals, thus avoiding actuator wear and excessive consumption of communication resources. The experience replay method is brought in the gradient descent method for improvement of the weight learning efficiency. The Lyapunov-based stability analysis shows that the designed tracking control strategy ensures that all signals and weights in the closed-loop system are semi-globally bounded with Zeno-free behavior. Numerical comparison simulation verifies the effectiveness and superiority of the strategy.