WOGAN at the SBFT 2023 Tool Competition - Cyber-Physical Systems Track

Jesper Winsten; Ivan Porres

doi:10.1109/sbft59156.2023.00009

WOGAN at the SBFT 2023 Tool Competition - Cyber-Physical Systems Track

Jesper Winsten, Ivan Porres

Informationsteknologi

Forskningsoutput: Kapitel i bok/konferenshandling › Konferensbidrag › Vetenskaplig › Peer review

2 Citeringar (Scopus)

Sammanfattning

WOGAN 2023 is an online test generation tool based on Wasserstein generative adversarial networks. We show how it can be applied to the SBFT 2023 competition to generate failure-inducing roads to test the lane keeping assist system of an autonomous car. The WOGAN 2023 tool is based on a previous entry to the competition. Here, we present improvements to WOGAN in the form of a combined fitness function based on the body out of lane percentage and the distance from the center of the lane. We also use road rotations in the road generation stage for greater test diversity.

Originalspråk	Engelska
Titel på värdpublikation	2023 IEEE/ACM International Workshop on Search-Based and Fuzz Testing (SBFT)
Förlag	IEEE
Sidor	43-44
ISBN (elektroniskt)	979-8-3503-0182-3
ISBN (tryckt)	979-8-3503-0183-0
DOI	https://doi.org/10.1109/sbft59156.2023.00009
Status	Publicerad - 2023
MoE-publikationstyp	A4 Artikel i en konferenspublikation
Evenemang	IEEE/ACM International Workshop on Search-Based and Fuzz Testing - Varaktighet: 14 maj 2023 → …

Konferens

Konferens	IEEE/ACM International Workshop on Search-Based and Fuzz Testing
Förkortad titel	SBFT
Period	14/05/23 → …

Åtkomst av dokument

10.1109/sbft59156.2023.00009

Citera det här

@inproceedings{7fb39007267b498087e76ce698ae9c1f,

title = "WOGAN at the SBFT 2023 Tool Competition - Cyber-Physical Systems Track",

abstract = "WOGAN 2023 is an online test generation tool based on Wasserstein generative adversarial networks. We show how it can be applied to the SBFT 2023 competition to generate failure-inducing roads to test the lane keeping assist system of an autonomous car. The WOGAN 2023 tool is based on a previous entry to the competition. Here, we present improvements to WOGAN in the form of a combined fitness function based on the body out of lane percentage and the distance from the center of the lane. We also use road rotations in the road generation stage for greater test diversity.",

author = "Jesper Winsten and Ivan Porres",

year = "2023",

doi = "10.1109/sbft59156.2023.00009",

language = "English",

isbn = "979-8-3503-0183-0",

pages = "43--44",

booktitle = "2023 IEEE/ACM International Workshop on Search-Based and Fuzz Testing (SBFT)",

publisher = "IEEE",

address = "United States",

note = "IEEE/ACM International Workshop on Search-Based and Fuzz Testing, SBFT ; Conference date: 14-05-2023",

}

TY - GEN

T1 - WOGAN at the SBFT 2023 Tool Competition - Cyber-Physical Systems Track

AU - Winsten, Jesper

AU - Porres, Ivan

PY - 2023

Y1 - 2023

N2 - WOGAN 2023 is an online test generation tool based on Wasserstein generative adversarial networks. We show how it can be applied to the SBFT 2023 competition to generate failure-inducing roads to test the lane keeping assist system of an autonomous car. The WOGAN 2023 tool is based on a previous entry to the competition. Here, we present improvements to WOGAN in the form of a combined fitness function based on the body out of lane percentage and the distance from the center of the lane. We also use road rotations in the road generation stage for greater test diversity.

AB - WOGAN 2023 is an online test generation tool based on Wasserstein generative adversarial networks. We show how it can be applied to the SBFT 2023 competition to generate failure-inducing roads to test the lane keeping assist system of an autonomous car. The WOGAN 2023 tool is based on a previous entry to the competition. Here, we present improvements to WOGAN in the form of a combined fitness function based on the body out of lane percentage and the distance from the center of the lane. We also use road rotations in the road generation stage for greater test diversity.

U2 - 10.1109/sbft59156.2023.00009

DO - 10.1109/sbft59156.2023.00009

M3 - Conference contribution

SN - 979-8-3503-0183-0

SP - 43

EP - 44

BT - 2023 IEEE/ACM International Workshop on Search-Based and Fuzz Testing (SBFT)

PB - IEEE

T2 - IEEE/ACM International Workshop on Search-Based and Fuzz Testing

Y2 - 14 May 2023

ER -

WOGAN at the SBFT 2023 Tool Competition - Cyber-Physical Systems Track

Sammanfattning

Konferens

Åtkomst av dokument

Fingeravtryck

Citera det här