Library
local_library Home Repository

DRVN at the ICST 2025 Tool Competition – Self-Driving Car Testing Track

Conference Paper (2025)
Author(s)

A.J. Bartlett (TU Delft - Multimedia Computing)

C. Liem (TU Delft - Multimedia Computing)

Annibale Panichella (TU Delft - Software Engineering)

Multimedia Computing
DOI related publication
https://doi.org/10.1109/ICST62969.2025.10988997
More Info
expand_more
Publication Year
2025
Language
English
Multimedia Computing
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository as part of the Taverne amendment. More information about this copyright law amendment can be found at https://www.openaccess.nl. Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.@en
Pages (from-to)
807-808
ISBN (print)
979-8-3315-0815-9
ISBN (electronic)
979-8-3315-0814-2
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

DRVN is a regression testing tool that aims to diversify the test scenarios (road maps) to execute for testing and validating self-driving cars. DRVN harnesses the power of convolutional neural networks to identify possible failing roads in a set of generated examples before applying a greedy algorithm that selects and prioritizes the most diverse roads during regression testing. Initial testing discovered that DRVN performed well against random-based test selection.

Files

DRVN_at_the_ICST_2025_Tool_Com... (pdf)
(pdf | 0.357 Mb)
License info not available
warning

File under embargo until 20-11-2025