Dynamic Event-Triggered Optimal Control for Heterogeneous Vehicle Platoon Based on Integral Reinforcement Learning

IF 6.7 2区计算机科学 Q1 ENGINEERING, MULTIDISCIPLINARY

IEEE Transactions on Network Science and Engineering Pub Date : 2025-02-12 DOI:10.1109/TNSE.2025.3540993

Yongming Li;Ying Xu;Kewen Li

引用次数: 0

Abstract

This article investigates the issue of data-based distributed optimal control for third-order heterogeneous vehicle platoon system (HVPS) with input saturation under switching topology. In the control design, the integral reinforcement learning (IRL) algorithm is used to learn the online solution of the Hamilton-Jacobi-Bellman (HJB) equation with unknown dynamics. Combining IRL algorithm and critic neural network (CNN), a distributed adaptive optimal control approach is designed based on dynamic event-triggered (DET) mechanism. By the aid of topology-dependent Lyapunov function and the average dwell time method, the developed optimal control method demonstrates that all the signals in the considered system are uniformly ultimately bounded (UUB), the closed-loop system can achieve Nash equilibrium and string stability can be ensured. In addition, Zeno behavior can also be avoided. Finally, to illustrate the effectiveness of the developed optimal control approach, a simulation example is given.

查看原文本刊更多论文

本文研究了开关拓扑结构下具有输入饱和的三阶异构车辆排系统（HVPS）的基于数据的分布式最优控制问题。在控制设计中，使用积分强化学习（IRL）算法来学习具有未知动态的汉密尔顿-雅各比-贝尔曼（HJB）方程的在线解。结合 IRL 算法和批评神经网络（CNN），设计了一种基于动态事件触发（DET）机制的分布式自适应优化控制方法。借助拓扑依赖的 Lyapunov 函数和平均停留时间法，所开发的最优控制方法证明了所考虑系统中的所有信号都是均匀终极有界（UUB）的，闭环系统可以达到纳什均衡，并能确保串稳定性。此外，还可以避免 Zeno 行为。最后，为了说明所开发的优化控制方法的有效性，给出了一个仿真实例。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Network Science and Engineering Engineering-Control and Systems Engineering

CiteScore

12.60

自引率

9.10%

发文量

393

期刊介绍： The proposed journal, called the IEEE Transactions on Network Science and Engineering (TNSE), is committed to timely publishing of peer-reviewed technical articles that deal with the theory and applications of network science and the interconnections among the elements in a system that form a network. In particular, the IEEE Transactions on Network Science and Engineering publishes articles on understanding, prediction, and control of structures and behaviors of networks at the fundamental level. The types of networks covered include physical or engineered networks, information networks, biological networks, semantic networks, economic networks, social networks, and ecological networks. Aimed at discovering common principles that govern network structures, network functionalities and behaviors of networks, the journal seeks articles on understanding, prediction, and control of structures and behaviors of networks. Another trans-disciplinary focus of the IEEE Transactions on Network Science and Engineering is the interactions between and co-evolution of different genres of networks.