This paper presents a novel adaptive neural event-triggered formation control strategy for underactuated surface vehicles (USVs) in the presence of marine practical constraints, i.e. the waypoints-based planned path and actuator failures. The proposed strategy is composed of the guidance model and the control one. For the guidance part, the logic virtual ship (LVS) guidance principle is developed to implement the reference path programming for the formation pattern. For merit of the adaptive virtual ship, the smooth reference can be produced for followers without using the velocity information of leader. Furthermore, the proposed adaptive neural fault-tolerant control algorithm is to guarantee that the followers can maintain their pattern and converge to the corresponding reference path. In the algorithm, the neural networks (NNs)-based observer is designed to estimate the unmeasurable velocities of followers online. With the input event-triggered mechanism, two adaptive parameters are derived to compensate for the gain uncertainty and actuator failure. And that could effectively reduce the communication burden for the channel from controller to actuator. The derived closed-loop system has been proved to be with the semi-global uniform ultimate bounded (SGUUB) stability. Finally, the superiority of the proposed strategy can be verified by the simulation experiments.

本文提出了一种新的自适应神经事件触发的编队控制策略，该策略针对存在海上实际约束（即基于航路点的计划路径和执行器故障）的欠驱动地面车辆（USV）。所提出的策略由制导模型和控制模型组成。对于制导部分，开发了逻辑虚拟船（LVS）制导原理，以实现编队模式的参考路径编程。鉴于自适应虚拟船的优点，可以在不使用引导者速度信息的情况下为跟随者生成平滑参考。此外，提出的自适应神经容错控制算法是为了确保跟随者可以保持其模式并收敛到相应的参考路径。在算法中 基于神经网络（NNs）的观察者的目的是在线估计跟随者的不可测量的速度。通过输入事件触发机制，可以导出两个自适应参数来补偿增益不确定性和执行器故障。这样可以有效减少从控制器到执行器的通道的通信负担。已经证明派生的闭环系统具有半全局一致的极限极限（SGUUB）稳定性。最后，通过仿真实验可以验证所提策略的优越性。这样可以有效减少从控制器到执行器的通道的通信负担。已经证明派生的闭环系统具有半全局一致的极限极限（SGUUB）稳定性。最后，通过仿真实验可以验证所提策略的优越性。这样可以有效减少从控制器到执行器的通道的通信负担。已经证明派生的闭环系统具有半全局一致的极限极限（SGUUB）稳定性。最后，通过仿真实验可以验证所提策略的优越性。