Saved in:
Bibliographic Details
Main Authors: Jang, Yeongjun, Chang, Hamin, Park, Heein, Jang, Hyeonyeong, Tanaka, Takashi, Shim, Hyungbo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.10292
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910048626671616
author Jang, Yeongjun
Chang, Hamin
Park, Heein
Jang, Hyeonyeong
Tanaka, Takashi
Shim, Hyungbo
author_facet Jang, Yeongjun
Chang, Hamin
Park, Heein
Jang, Hyeonyeong
Tanaka, Takashi
Shim, Hyungbo
contents In this paper, we present a data-driven output feedback controller for nonlinear systems that achieves practical output regulation, using noise-free input/output measurement data. The proposed controller is based on (i) an inverse model of the system identified via kernel interpolation, which maps a desired output and the current state to the corresponding desired control input; and (ii) a data-driven reference selection framework that actively chooses a suitable desired output from the dataset which has been used for the identification. We establish a verifiable sufficient condition on the dataset under which the proposed controller guarantees practical output regulation. Numerical simulations demonstrate the effectiveness of the proposed controller, with additional evaluations in the presence of output measurement noise to assess its robustness empirically.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10292
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Inverse Learning-Based Output Feedback Control of Nonlinear Systems with Verifiable Guarantees
Jang, Yeongjun
Chang, Hamin
Park, Heein
Jang, Hyeonyeong
Tanaka, Takashi
Shim, Hyungbo
Systems and Control
In this paper, we present a data-driven output feedback controller for nonlinear systems that achieves practical output regulation, using noise-free input/output measurement data. The proposed controller is based on (i) an inverse model of the system identified via kernel interpolation, which maps a desired output and the current state to the corresponding desired control input; and (ii) a data-driven reference selection framework that actively chooses a suitable desired output from the dataset which has been used for the identification. We establish a verifiable sufficient condition on the dataset under which the proposed controller guarantees practical output regulation. Numerical simulations demonstrate the effectiveness of the proposed controller, with additional evaluations in the presence of output measurement noise to assess its robustness empirically.
title Inverse Learning-Based Output Feedback Control of Nonlinear Systems with Verifiable Guarantees
topic Systems and Control
url https://arxiv.org/abs/2603.10292