Skip to search boxSkip to navigationSkip to main content

Safety Verification of Neural Network Control Systems Using Guaranteed Neural Network Model Reduction

*Corresponding author for this work
Scholary Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Research

Related Event

Title

61st IEEE Conference on Decision and Control, CDC 2022

Event type

Conference

Date

12/06/2022 - 12/09/2022

Location

CancunMexico

Abstract

<p>This paper aims to enhance the computational efficiency of safety verification of neural network control systems by developing a guaranteed neural network model reduction method. First, a concept of model reduction precision is proposed to describe the guaranteed distance between the outputs of a neural network and its reduced-size version. A reachability-based algorithm is proposed to accurately compute the model reduction precision. Then, by substituting a reduced-size neural network controller into the closed-loop system, an algorithm to compute the reachable set of the original system is developed, which is able to support much more computationally efficient safety verification processes. Finally, the developed methods are applied to a case study of the Adaptive Cruise Control system with a neural network controller, which is shown to significantly reduce the computational time of safety verification and thus validate the effectiveness of the method.</p>

Publication Information

Output type

Scholary Output:
Chapter in Book/Report/Conference proceeding
Conference contribution
Research

Original language

English (US)

Pages from-to (Number of pages)

Pages 1521-1526 (6 pages)

Publication milestones

  • Published - 2022

Publication status

Published - 2022

Publisher

Institute of Electrical and Electronics Engineers Inc.

Publication series

  • Publication series name: Proceedings of the IEEE Conference on Decision and Control
    ISSN (Print): 0743-1546
    ISSN (Electronic): 2576-2370
    Volume: 2022-December

ISBN (Electronic)

9781665467612

Publication IDs

  • Scopus: 85146979053

Host publication title

2022 IEEE 61st Conference on Decision and Control, CDC 2022

Publication metrics

Metrics

Fractional count
1
Fractional count
0.50
Fractional count
1
Fractional count
0.50
Fractional count
1
Fractional count
1
Scopus
citations

PlumX, opens in new tab

Citation count
4
Captures
4

Funding Details

This research was supported by the National Science Foundation, under NSF CAREER Award 2143351 and NSF CNS Award 2223035. Weiming Xiang is with School of Computer and Cyber Sciences, Augusta University, Augusta GA 30912, USA. [email protected] Zhongzhu Shao is with School of Electrical Engineering, Southwest Jiaotong University, China.
FunderFunding numbers
NSF
2223035, 2143351