Hybrid Zonotope-Based Backward Reachability Analysis for Neural Feedback Systems With Nonlinear Plant Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hang, Zhang, Yuhao, Xu, Xiangru
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913271048568832
author Zhang, Hang
Zhang, Yuhao
Xu, Xiangru
author_facet Zhang, Hang
Zhang, Yuhao
Xu, Xiangru
contents The increasing prevalence of neural networks in safety-critical control systems underscores the imperative need for rigorous methods to ensure the reliability and safety of these systems. This work introduces a novel approach employing hybrid zonotopes to compute the over-approximation of backward reachable sets for neural feedback systems with nonlinear plant models and general activation functions. Closed-form expressions as hybrid zonotopes are provided for the over-approximated backward reachable sets, and a refinement procedure is proposed to alleviate the potential conservatism of the approximation. Two numerical examples are provided to illustrate the effectiveness of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2310_06921
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Hybrid Zonotope-Based Backward Reachability Analysis for Neural Feedback Systems With Nonlinear Plant Models
Zhang, Hang
Zhang, Yuhao
Xu, Xiangru
Optimization and Control
Systems and Control
The increasing prevalence of neural networks in safety-critical control systems underscores the imperative need for rigorous methods to ensure the reliability and safety of these systems. This work introduces a novel approach employing hybrid zonotopes to compute the over-approximation of backward reachable sets for neural feedback systems with nonlinear plant models and general activation functions. Closed-form expressions as hybrid zonotopes are provided for the over-approximated backward reachable sets, and a refinement procedure is proposed to alleviate the potential conservatism of the approximation. Two numerical examples are provided to illustrate the effectiveness of the proposed approach.
title Hybrid Zonotope-Based Backward Reachability Analysis for Neural Feedback Systems With Nonlinear Plant Models
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2310.06921