EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generating Edge Cases for Testing Autonomous Vehicles Using Real-World Data

Dhanoop Karunakaran, Julie Stephany Berrio Perez iD, Stewart Worrall

Sensors · 25.12.2023 · 24 (1) · 108

DOI: 10.3390/s24010108 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.12.2023. Verfasst von Dhanoop Karunakaran und 2 weiteren Autor:innen. Beteiligte Einrichtung: Emerging Technologies, IAG, Sydney, NSW 2000, Australia. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Centre for Robotics (ACFR), University of Sydney, Insurance Australia Group (IAG).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the past decade, automotive companies have invested significantly in autonomous vehicles (AV), but achieving widespread deployment remains a challenge in part due to the complexities of safety evaluation. Traditional distance-based testing has been shown to be expensive and time-consuming. To address this, experts have proposed scenario-based testing (SBT), which simulates detailed real-world driving scenarios to assess vehicle responses efficiently. This paper introduces a method that builds a parametric representation of a driving scenario using collected driving data. By adopting a data-driven approach, we are then able to generate realistic, concrete scenarios that correspond to high-risk situations. A reinforcement learning technique is used to identify the combination of parameter values that result in the failure of a system under test (SUT). The proposed method generates novel, simulated high-risk scenarios, thereby offering a meaningful and focused assessment of AV systems.

Schlagwörter

Stichwörter der Autor:innen

autonomous vehiclesdata-driven methodedge case generationparametric representationscenario-based testingtesting

Autor:innen und Institutionen

  • Emerging Technologies, IAG, Sydney, NSW 2000, Australia.
  • Australian Centre for Robotics, University of Sydney, Sydney, NSW 2008, Australia.

ORCID-Profile: Julie Stephany Berrio Perez

Förderung

  • Australian Centre for Robotics (ACFR)
  • University of Sydney
  • Insurance Australia Group (IAG)
  • Cooperative Research Centres program

Zitieren

APA

Karunakaran, D., Berrio Perez, J. S., & Worrall, S. (2023). Generating Edge Cases for Testing Autonomous Vehicles Using Real-World Data. Sensors, 24(1), 108. https://doi.org/10.3390/s24010108

Vancouver

Karunakaran D, Berrio Perez JS, Worrall S. Generating Edge Cases for Testing Autonomous Vehicles Using Real-World Data. Sensors. 2023;24(1):108. doi:10.3390/s24010108

BibTeX
@article{Karunakaran2023,
  author = {Karunakaran, Dhanoop and Berrio Perez, Julie Stephany and Worrall, Stewart},
  title = {Generating Edge Cases for Testing Autonomous Vehicles Using Real-World Data},
  journal = {Sensors},
  year = {2023},
  volume = {24},
  number = {1},
  pages = {108},
  doi = {10.3390/s24010108}
}
Kostenlos starten →