用于控制的直接数据驱动自然梯度下降
Direct Data Driven Natural Gradient Descent for Control
AI总结：
介绍基于自然梯度下降的直接数据驱动控制框架，提出含闭环协方差矩阵的两种数据驱动NGD formulation，直接从数据合成稳定策略，获收敛性理论保证并验证。
摘要：
本文引入一种基于自然梯度下降（NGD）的新型直接数据驱动控制框架，用于设计可解释且鲁棒的闭环策略，无需显式模型识别。我们提出两种数据驱动的NGD公式，通过Fisher信息矩阵（FIM）纳入闭环协方差矩阵，使梯度更新能根据系统固有不确定性进行预处理。利用闭环系统的两种基于数据的参数化，我们的方法能够直接从数据中合成有稳定性保证的策略。我们使用半定规划（SDP）为收缩和收敛提供理论保证，并在ROSbot XL平台的仿真和硬件上验证了我们的框架。结果表明，与线性二次调节器（LQR）和标准数据驱动基线相比，该方法具有直观的特性，特别是在收敛速度、鲁棒性和控制可解释性方面。这项工作弥合了面向轨迹的自然梯度方法与实际数据驱动控制设计之间的差距。
英文摘要：
This paper introduces a novel direct data-driven control framework based on Natural Gradient Descent (NGD) to design interpretable and robust closed-loop policies without requiring explicit model identification. We propose two data-driven NGD formulations that incorporate the closed-loop covariance matrix through the Fisher Information Matrix (FIM), allowing gradient updates to be preconditioned according to the system's intrinsic uncertainty. Leveraging two distinct data-based parameterizations of the closed-loop system, our method enables stability-guaranteed policy synthesis directly from data. We provide theoretical guarantees for contraction and convergence using semidefinite programs (SDPs) and validate our framework in both simulations and on hardware on a ROSbot XL platform. The results demonstrate intuitive features compared to linear-quadratic regulator (LQR) and standard data-driven baselines, particularly in terms of convergence speed, robustness, and control interpretability. This work bridges the gap between trajectory-oriented natural gradient methods and practical data-driven control design.
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。
