This paper is concerned with the path following control for an unmanned surface vessel subject to unknown dynamics and external disturbance. Firstly, an integral Line-of-Sight navigation strategy based on a fuzzy strategy to optimize lookahead distance to achieve faster convergence speed is proposed. Then a novel adaptive course control law based on trajectory linearization control technology is proposed, which is combined with the integral Line-of-Sight navigation strategy to form a complete unmanned surface vessel path following strategy. From the author's point of view, this is the first time that trajectory linearization control technology has been applied to the path following scheme by controlling the course. At the same time, in order to improve the robustness of the path following system, the unknown dynamics, external disturbance, and error in the system are compensated by neural network minimum learning parameter method with less computational complexity and a robust term, respectively. Furthermore, hyperbolic tangent function, Nussbaum function, and neural shunting model are introduced into the design of control law to solve the potential input saturation problem. Finally, the numerical simulation experiments of straight line and curve path following are given to prove the feasibility and universality of the whole set of path following scheme.

中文翻译：

---

无人水面车辆ILOS路径跟随的时变前瞻距离

本文关注的是受未知动力学和外部干扰影响的无人水面舰艇的路径跟随控制。首先，提出了一种基于模糊策略的积分视线导航策略，以优化前视距离以实现更快的收敛速度。然后提出了一种新的基于轨迹线性化控制技术的自适应航向控制律，结合积分视线导航策略，形成完整的无人水面舰船路径跟随策略。在笔者看来，这是首次将轨迹线性化控制技术应用到轨迹控制方案中。同时，为了提高路径跟随系统的鲁棒性，未知动力学、外部扰动、系统中的误差和误差分别通过神经网络最小学习参数方法进行补偿，计算复杂度较低，项具有鲁棒性。此外，将双曲正切函数、Nussbaum 函数和神经分流模型引入控制律的设计中，以解决潜在的输入饱和问题。最后，通过直线和曲线路径跟随的数值模拟实验，证明了整套路径跟随方案的可行性和通用性。将神经分流模型引入控制律设计，解决潜在的输入饱和问题。最后，通过直线和曲线路径跟随的数值模拟实验，证明了整套路径跟随方案的可行性和通用性。将神经分流模型引入控制律设计，解决潜在的输入饱和问题。最后，通过直线和曲线路径跟随的数值模拟实验，证明了整套路径跟随方案的可行性和通用性。