paper-with-me

홈 › Papers

Lyapunov-Based Deep Residual Neural Network (ResNet) Adaptive Control

2024-04-10 · Omkar Sudhir Patil, Duc M. Le, Emily J. Griffis, Warren E. Dixon

Deep Neural Network (DNN)-based controllers have emerged as a tool to compensate for unstructured uncertainties in nonlinear dynamical systems. A recent breakthrough in the adaptive control literature provides a Lyapunov-based approach to derive weight adaptation laws for each layer of a fully-connected feedforward DNN-based adaptive controller. However, deriving weight adaptation laws from a Lyapunov-based analysis remains an open problem for deep residual neural networks (ResNets). This paper provides the first result on Lyapunov-derived weight adaptation for a ResNet-based adaptive controller. A nonsmooth Lyapunov-based analysis is provided to guarantee asymptotic tracking error convergence. Comparative Monte Carlo simulations are provided to demonstrate the performance of the developed ResNet-based adaptive controller. The ResNet-based adaptive controller shows a 64% improvement in the tracking and function approximation performance, in comparison to a fully-connected DNN-based adaptive controller.

📄 PDF Abstract BibTeX arXiv:2404.07385

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Online ResNet-Based Adaptive Control for Nonlinear Target Tracking

2025-03-18 · Cristian F. Nino, Omkar Sudhir Patil, Jordan C. Insinger, Marla R. Eisman 외

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 conne…

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families

2019-11-23 · Yibo Yang, Jianlong Wu, Hongyang Li, Xia Li 외

The correspondence between residual networks and dynamical systems motivates researchers to unravel the physics of ResNets with well-developed tools in numeral methods of ODE systems. The Runge-Kutta-Fehlberg method is a…

Interpolation between Residual and Non-Residual Networks

2020-06-10 · Zonghan Yang, Yang Liu, Chenglong Bao, Zuoqiang Shi

Although ordinary differential equations (ODEs) provide insights for designing network architectures, its relationship with the non-residual convolutional neural networks (CNNs) is still unclear. In this paper, we presen…

Adversarial Attackimage-classificationImage Classification

Verifiable Error Bounds for Physics-Informed Neural Network Solutions of Lyapunov and Hamilton-Jacobi-Bellman Equations

2026-03-20 · Jun Liu arxiv

Many core problems in nonlinear systems analysis and control can be recast as solving partial differential equations (PDEs) such as Lyapunov and Hamilton-Jacobi-Bellman (HJB) equations. Physics-informed neural networks (…

Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions

2025-05-16 · Kehan Long, Jorge Cortés, Nikolay Atanasov

We study the problem of certifying the stability of closed-loop systems under control policies derived from optimal control or reinforcement learning (RL). Classical Lyapunov methods require a strict step-wise decrease i…

Reinforcement Learning (RL)