Online ResNet-Based Adaptive Control for Nonlinear Target Tracking
Systems and Control
2025-06-02 v2 Systems and Control
Abstract
A generalized ResNet architecture for adaptive control of nonlinear systems with black box uncertainties is developed. The approach overcomes limitations in existing methods by incorporating pre-activation shortcut connections and a zeroth layer block that accommodates different input-output dimensions. The developed Lyapunov-based adaptation law establishes exponential convergence to a neighborhood of the target state despite unknown dynamics and disturbances. Furthermore, the theoretical results are validated through a comparative experiment.
Keywords
Cite
@article{arxiv.2503.14372,
title = {Online ResNet-Based Adaptive Control for Nonlinear Target Tracking},
author = {Cristian F. Nino and Omkar Sudhir Patil and Jordan C. Insinger and Marla R. Eisman and Warren E. Dixon},
journal= {arXiv preprint arXiv:2503.14372},
year = {2025}
}
Comments
6 pages, 3 figures