Neural Network Observer Based Adaptive Trajectory Tracking Control Strategy of Unmanned Surface Vehicle With Event-Triggered Mechanisms and Signal Quantization

This paper concerned with the network observer based adaptive trajectory tracking control strategy of Unmanned Surface Vehicle with event-triggered mechanisms and signal quantization. In expound upon input quantization, this paper introduces a linear analytical model enabling controller design without necessitating prior knowledge of the input quantization parameters. Meanwhile, the quantized state variables are estimated through the neural network-based observer. As a result, the quantized feedback controller is designed to use the observer's estimation results, through a combination of backstepping, dynamic surface techniques, and event-triggered mechanisms. The stability of the formulated closed-loop system is demonstrated through the application of Lyapunov stability theory principles. Ultimately, the effectiveness of the proposed control strategy is substantiated through simulation experiments.