Poster: Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles

Cumhur Erkan Tuncali; Georgios Fainekos; Hisahiro Ito; James Kapinski

doi:10.1145/3178126.3187004

Poster: Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles

Cumhur Erkan Tuncali, Georgios Fainekos, Hisahiro Ito, James Kapinski

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

16 Scopus citations

Abstract

One of the main challenges in testing autonomous driving systems is the presence of machine learning components, such as neural networks, for which formal properties are difficult to establish. We present a simulation-based testing framework that supports methods used to evaluate cyberphysical systems, such as test case generation and automatic falsification. We demonstrate how the framework can be used to evaluate closed-loop properties of autonomous driving system models that include machine learning components.

Original language	English (US)
Title of host publication	HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems
Subtitle of host publication	Computation and Control (part of CPS Week)
Publisher	Association for Computing Machinery, Inc
Pages	283-284
Number of pages	2
ISBN (Electronic)	9781450356428
DOIs	https://doi.org/10.1145/3178126.3187004
State	Published - Apr 11 2018
Event	21st International Conference on Hybrid Systems: Computation and Control, HSCC 2018 - Porto, Portugal Duration: Apr 11 2018 → Apr 13 2018

Publication series

Name	HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week)

Other

Other	21st International Conference on Hybrid Systems: Computation and Control, HSCC 2018
Country/Territory	Portugal
City	Porto
Period	4/11/18 → 4/13/18

ASJC Scopus subject areas

Computer Science Applications
Electrical and Electronic Engineering
Control and Systems Engineering
Computer Networks and Communications

Access to Document

10.1145/3178126.3187004

Cite this

Tuncali, C. E., Fainekos, G., Ito, H., & Kapinski, J. (2018). Poster: Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles. In HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week) (pp. 283-284). (HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week)). Association for Computing Machinery, Inc. https://doi.org/10.1145/3178126.3187004

Poster: Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles. / Tuncali, Cumhur Erkan; Fainekos, Georgios; Ito, Hisahiro et al.
HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week). Association for Computing Machinery, Inc, 2018. p. 283-284 (HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Tuncali, CE, Fainekos, G, Ito, H & Kapinski, J 2018, Poster: Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles. in HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week). HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week), Association for Computing Machinery, Inc, pp. 283-284, 21st International Conference on Hybrid Systems: Computation and Control, HSCC 2018, Porto, Portugal, 4/11/18. https://doi.org/10.1145/3178126.3187004

Tuncali CE, Fainekos G, Ito H, Kapinski J. Poster: Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles. In HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week). Association for Computing Machinery, Inc. 2018. p. 283-284. (HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week)). doi: 10.1145/3178126.3187004

Tuncali, Cumhur Erkan ; Fainekos, Georgios ; Ito, Hisahiro et al. / Poster : Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles. HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week). Association for Computing Machinery, Inc, 2018. pp. 283-284 (HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week)).

@inproceedings{7e365190bafa420b87250a79005661f8,

title = "Poster: Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles",

abstract = "One of the main challenges in testing autonomous driving systems is the presence of machine learning components, such as neural networks, for which formal properties are difficult to establish. We present a simulation-based testing framework that supports methods used to evaluate cyberphysical systems, such as test case generation and automatic falsification. We demonstrate how the framework can be used to evaluate closed-loop properties of autonomous driving system models that include machine learning components.",

author = "Tuncali, {Cumhur Erkan} and Georgios Fainekos and Hisahiro Ito and James Kapinski",

note = "Publisher Copyright: {\textcopyright} 2018 Copyright held by the owner/author(s).; 21st International Conference on Hybrid Systems: Computation and Control, HSCC 2018 ; Conference date: 11-04-2018 Through 13-04-2018",

year = "2018",

month = apr,

day = "11",

doi = "10.1145/3178126.3187004",

language = "English (US)",

series = "HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week)",

publisher = "Association for Computing Machinery, Inc",

pages = "283--284",

booktitle = "HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems",

}

TY - GEN

T1 - Poster

T2 - 21st International Conference on Hybrid Systems: Computation and Control, HSCC 2018

AU - Tuncali, Cumhur Erkan

AU - Fainekos, Georgios

AU - Ito, Hisahiro

AU - Kapinski, James

PY - 2018/4/11

Y1 - 2018/4/11

N2 - One of the main challenges in testing autonomous driving systems is the presence of machine learning components, such as neural networks, for which formal properties are difficult to establish. We present a simulation-based testing framework that supports methods used to evaluate cyberphysical systems, such as test case generation and automatic falsification. We demonstrate how the framework can be used to evaluate closed-loop properties of autonomous driving system models that include machine learning components.

AB - One of the main challenges in testing autonomous driving systems is the presence of machine learning components, such as neural networks, for which formal properties are difficult to establish. We present a simulation-based testing framework that supports methods used to evaluate cyberphysical systems, such as test case generation and automatic falsification. We demonstrate how the framework can be used to evaluate closed-loop properties of autonomous driving system models that include machine learning components.

UR - http://www.scopus.com/inward/record.url?scp=85049444876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049444876&partnerID=8YFLogxK

U2 - 10.1145/3178126.3187004

DO - 10.1145/3178126.3187004

M3 - Conference contribution

AN - SCOPUS:85049444876

T3 - HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems: Computation and Control (part of CPS Week)

SP - 283

EP - 284

BT - HSCC 2018 - Proceedings of the 21st International Conference on Hybrid Systems

PB - Association for Computing Machinery, Inc

Y2 - 11 April 2018 through 13 April 2018

ER -

Poster: Sim-ATAV: Simulation-based adversarial testing framework for autonomous vehicles

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this