Event-Triggered Adaptive Neural Trajectory Tracking Control of Uncrewed Surface Vehicle With Output Constraints and Quantization

This paper develops an event-triggered adaptive neural control scheme for uncrewed surface vehicle (USV) trajectory tracking control, considering input delay, time-varying output constraints, and saturated input quantization. An asymmetric Barrier Lyapunov Function (BLF) is employed within a backstepping framework to guarantee constraint satisfaction throughout the control process. To mitigate the adverse effects of input delay, the Pade approximation method and an auxiliary state variable are employed to handle the input delay effectively. The auxiliary dynamic filter is designed to compensate for the effects of input saturation. To address model uncertainties, radial basis function neural networks (RBFNNs) are utilized for accurate function approximation. In addition, an event-triggered mechanism is designed to reduce communication burden by suppressing redundant control updates. To further save communication resources, control input signals are quantized. The proposed approach is theoretically validated through Lyapunov-based stability analysis and numerically verified via simulation cases.