DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Towards behaviour based testing to understand the black box of autonomous cars

Utesch, Fabian and Brandies, Alexander and Pekezou Fouopi, Paulin and Schießl, Caroline (2020) Towards behaviour based testing to understand the black box of autonomous cars. European Transport Research Review, 12 (48). Springer. doi: 10.1186/s12544-020-00438-2. ISSN 1867-0717.

[img] PDF - Published version

Official URL: https://etrr.springeropen.com/articles/10.1186/s12544-020-00438-2


Background Autonomous cars could make traffic safer, more convenient, efficient and sustainable. They promise the convenience of a personal taxi, without the need for a human driver. Artificial intelligence would operate the vehicle instead. Especially deep neural networks (DNNs) offer a way towards this vision due to their exceptional performance particularly in perception. DNNs excel in identifying objects in sensor data which is essential for autonomous driving. These networks build their decision logic through training instead of explicit programming. A drawback of this technology is that the source code cannot be reviewed to assess the safety of a system. This leads to a situation where currently used methods for regulatory approval do not work to validate a promising new piece of technology. Objective In this paper four approaches are highlighted that might help understanding black box technical systems for autonomous cars by focusing on its behaviour instead. The method of experimental psychology is proposed to model the inner workings of DNNs by observing its behaviour in specific situations. It is argued that penetration testing can be applied to identify weaknesses of the system. Both can be applied to improve autonomous driving systems. The shadowing method reveals behaviour in a naturalistic setting while ensuring safety. It can be seen as a theoretical driving exam. The supervised driving method can be utilised to decide if the technology is safe enough. It has potential to be developed into a practical driving exam.

Item URL in elib:https://elib.dlr.de/129843/
Document Type:Article
Title:Towards behaviour based testing to understand the black box of autonomous cars
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Utesch, FabianFabian.Utesch (at) dlr.dehttps://orcid.org/0000-0003-3830-5777
Brandies, AlexanderAlexander.Brandies (at) dlr.dehttps://orcid.org/0000-0003-1604-4748
Pekezou Fouopi, PaulinPaulin.PekezouFouopi (at) dlr.dehttps://orcid.org/0000-0003-3583-8279
Schießl, CarolineCaroline.Schiessl (at) dlr.deUNSPECIFIED
Date:29 July 2020
Journal or Publication Title:European Transport Research Review
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In ISI Web of Science:Yes
DOI :10.1186/s12544-020-00438-2
Keywords:Autonomous Cars, Deep Neural Networks, Artificial Intelligence
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Transport System
DLR - Research area:Transport
DLR - Program:V VS - Verkehrssystem
DLR - Research theme (Project):V - Energie und Verkehr
Location: Braunschweig
Institutes and Institutions:Institute of Transportation Systems > Human Factors
Deposited By: Utesch, Fabian
Deposited On:04 Sep 2020 14:06
Last Modified:04 Sep 2020 14:06

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.