CORTEXA
← Browse
arxiveess.SY2026-07-03

Direct Data Driven Natural Gradient Descent for Control

Ramin Esmzad, Farnaz Adib Yaghmaie, Bahare Kiumarsi, Hamidreza Modares

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.

View free PDFSource page

Related papers

arxiveess.SY2026-07-10

Data-driven predictive control of nonlinear systems using weighted regularization

Fritz A. Engeln, Sebastian Zieglmeier, Marta Zagórowska, Jan-Willem van Wingerden

Data-driven control methods, like Data-enabled Predictive Control (DeePC), are often formulated for linear systems, where the principle of superposition allows global system behavior to be inferred from locally collected data through Willems' fundamental lemma. This principle doe…

View free PDFSource page
arxiveess.SY2026-07-23

When Persistency is not Exciting in Data-Driven Predictive Control

Gianluca Giacomelli, Chuyu Lu, Siep Weiland, Valentina Breschi

Understanding how to collect data that is meaningful for control purposes is of paramount importance in data-driven control. While existing approaches have primarily relied on the satisfaction of a rank condition to assess the quality of an experiment, we show that satisfying it…

View free PDFSource page
arxiveess.SYmath.OC2026-07-17

Gaussian behaviors and stochastic data-driven control

András Sasfi, Alberto Padoan, Ivan Markovsky, Florian Dörfler

We propose a stochastic behavioral modeling framework, termed Gaussian behaviors, which augments a deterministic linear time-invariant (LTI) behavior with a Gaussian noise component. We show that this notion is a tractable subclass of stochastic behaviors and encompasses classica…

View free PDFSource page
arxivmath.OCeess.SY2026-07-08

On the Robustness in Data-Driven Nonlinear Optimal Control: From Stability to Optimality

Yicheng Lin, Zhisheng Duan, Tianzhi Li, Bingxian Wu, Zhiyong Sun

In data-driven nonlinear control, optimal controllers designed from learned models are inevitably subject to model mismatch when deployed on actual systems, potentially compromising both closed-loop stability and optimality. This paper investigates how the model mismatch propagat…

View free PDFSource page
arxiveess.SY2026-07-03

Data-driven Kernel-based Predictive Control with Stability and Robustness Guarantees

Wenjie Liu, Yifei Li, Gang Wang, Lihua Xie

In this paper, we provide a theoretical analysis of the closed-loop properties of a data-driven kernel-based predictive control (DDKPC) scheme developed solely from input-output data. The proposed formulation integrates a robust data-driven predictive control framework with a mul…

View free PDFSource page