arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.02899eess.SYcs.SY
收藏

利用有限信道样本学习未知丢包率下 LQR 的控制

Learning Control for LQR with Unknown Packet Loss Rate Using Finite Channel Samples

Zhenning Zhang, Liang Xu, Yilin Mo, Xiaofan Wang

AI总结:

针对未知 Bernoulli 丢包信道下的 LQR,本文基于有限样本估计丢包率并设计 CE 控制器,分析其稳定阈值、次优性与样本复杂度。

摘要:

本文研究了通过未知 Bernoulli 丢包信道进行控制的线性二次调节器(LQR)问题。未知丢包率通过有限信道样本进行估计,随后将该估计值视为真实丢包率,设计确定性等价(CE)最优控制器。CE 控制器的稳定能力和次优性关键取决于丢包率的估计误差。针对离散时间线性系统,我们给出了确保闭环稳定的估计误差稳定性阈值,并根据估计误差以及修正 Riccati 方程之间的差异,对次优性进行了解析量化。接着,我们推导了使 CE 控制器实现稳定所需样本复杂度的上界。对于标量系统和输入矩阵可逆的 n 维系统,给出了保守性更低的定制化结果。此外,我们建立了一个独立于未知丢包率的充分条件,用于验证 CE 控制器在概率意义下是否具有稳定性。最后,通过数值算例验证了所得结果。

英文摘要:

This paper studies the linear quadratic regulator (LQR) problem over an unknown Bernoulli packet loss channel. The unknown loss rate is estimated using finite channel samples and a certainty-equivalence (CE) optimal controller is then designed by treating the estimate as the true rate. The stabilizing capability and sub-optimality of the CE controller critically depend on the estimation error of loss rate. For discrete-time linear systems, we provide a stability threshold for the estimation error to ensure closed-loop stability, and analytically quantify the sub-optimality in terms of the estimation error and the difference in modified Riccati equations. Next, we derive the upper bound on sample complexity for the CE controller to be stabilizing. Tailored results with less conservatism are delivered for scalar systems and n-dimensional systems with invertible input matrix. Moreover, we establish a sufficient condition, independent of the unknown loss rate, to verify whether the CE controller is stabilizing in a probabilistic sense. Finally, numerical examples are used to validate our results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑