Verification Approaches for Learning-Enabled Autonomous Cyber-Physical Systems

Hoang Dung Tran; Weiming Xiang; Taylor T. Johnson

doi:10.1109/MDAT.2020.3015712

Verification Approaches for Learning-Enabled Autonomous Cyber-Physical Systems

Hoang Dung Tran, Weiming Xiang, Taylor T. Johnson

Computer Science

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

Editor's notes: Neural network control systems are often at the heart of autonomous systems. The authors classify existing verification methods for these systems and advocate the necessity of integrating verification techniques in the training process to enhance robustness.-Selma Saidi, TU Dortmund.

Original language	English (US)
Pages (from-to)	24-34
Number of pages	11
Journal	IEEE Design and Test
Volume	39
Issue number	1
DOIs	https://doi.org/10.1109/MDAT.2020.3015712
State	Published - Feb 1 2022

Keywords

Autonomy
Cyber-physical systems
Machine learning
Verification

ASJC Scopus subject areas

Software
Hardware and Architecture
Electrical and Electronic Engineering

Access to Document

10.1109/MDAT.2020.3015712

Cite this

@article{de3763e75d6a418584368ef5decc6654,

title = "Verification Approaches for Learning-Enabled Autonomous Cyber-Physical Systems",

abstract = "Editor's notes: Neural network control systems are often at the heart of autonomous systems. The authors classify existing verification methods for these systems and advocate the necessity of integrating verification techniques in the training process to enhance robustness.-Selma Saidi, TU Dortmund.",

keywords = "Autonomy, Cyber-physical systems, Machine learning, Verification",

author = "Tran, {Hoang Dung} and Weiming Xiang and Johnson, {Taylor T.}",

note = "Funding Information: This work was supported in part by the Air Force Office of Scientific Research (AFOSR) under Contract FA9550-18-1-0122 and in part by the Defense Advanced Research Projects Agency (DARPA) under Contract FA8750-18-C-0089. Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2022",

month = feb,

day = "1",

doi = "10.1109/MDAT.2020.3015712",

language = "English (US)",

volume = "39",

pages = "24--34",

journal = "IEEE Design and Test",

issn = "2168-2356",

publisher = "IEEE Computer Society",

number = "1",

}

TY - JOUR

T1 - Verification Approaches for Learning-Enabled Autonomous Cyber-Physical Systems

AU - Tran, Hoang Dung

AU - Xiang, Weiming

AU - Johnson, Taylor T.

N1 - Funding Information: This work was supported in part by the Air Force Office of Scientific Research (AFOSR) under Contract FA9550-18-1-0122 and in part by the Defense Advanced Research Projects Agency (DARPA) under Contract FA8750-18-C-0089. Publisher Copyright: © 2013 IEEE.

PY - 2022/2/1

Y1 - 2022/2/1

N2 - Editor's notes: Neural network control systems are often at the heart of autonomous systems. The authors classify existing verification methods for these systems and advocate the necessity of integrating verification techniques in the training process to enhance robustness.-Selma Saidi, TU Dortmund.

AB - Editor's notes: Neural network control systems are often at the heart of autonomous systems. The authors classify existing verification methods for these systems and advocate the necessity of integrating verification techniques in the training process to enhance robustness.-Selma Saidi, TU Dortmund.

KW - Autonomy

KW - Cyber-physical systems

KW - Machine learning

KW - Verification

UR - http://www.scopus.com/inward/record.url?scp=85125361015&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85125361015&partnerID=8YFLogxK

U2 - 10.1109/MDAT.2020.3015712

DO - 10.1109/MDAT.2020.3015712

M3 - Article

AN - SCOPUS:85125361015

SN - 2168-2356

VL - 39

SP - 24

EP - 34

JO - IEEE Design and Test

JF - IEEE Design and Test

IS - 1

ER -

Verification Approaches for Learning-Enabled Autonomous Cyber-Physical Systems

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this