Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Automotive Perception Software Development: An Empirical Investigation into Data, Annotation, and Ecosystem Challenges
University of Gothenburg, Sweden.
University of Gothenburg, Sweden.
University of Gothenburg, Sweden.
University of Gothenburg, Sweden.
Show others and affiliations
2023 (English)In: Proceedings - 2023 IEEE/ACM 2nd International Conference on AI Engineering - Software Engineering for AI, CAIN 2023, Institute of Electrical and Electronics Engineers Inc. , 2023, p. 13-24Conference paper, Published paper (Refereed)
Abstract [en]

Software that contains machine learning algorithms is an integral part of automotive perception, for example, in driving automation systems. The development of such software, specifically the training and validation of the machine learning components, requires large annotated datasets. An industry of data and annotation services has emerged to serve the development of such data-intensive automotive software components. Wide-spread difficulties to specify data and annotation needs challenge collaborations between OEMs (Original Equipment Manufacturers) and their suppliers of software components, data, and annotations.This paper investigates the reasons for these difficulties for practitioners in the Swedish automotive industry to arrive at clear specifications for data and annotations. The results from an interview study show that a lack of effective metrics for data quality aspects, ambiguities in the way of working, unclear definitions of annotation quality, and deficits in the business ecosystems are causes for the difficulty in deriving the specifications. We provide a list of recommendations that can mitigate challenges when deriving specifications and we propose future research opportunities to overcome these challenges. Our work contributes towards the on-going research on accountability of machine learning as applied to complex software systems, especially for high-stake applications such as automated driving. 

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2023. p. 13-24
Keywords [en]
accountability, annotations, data, ecosystems, machine learning, requirements specification, Application programs, Automation, Automotive industry, Large dataset, Learning algorithms, Machine components, Software design, Annotation, Automotives, Data annotation, Empirical investigation, Machine learning algorithms, Machine-learning, Requirements specifications, Software-component, Specifications
National Category
Software Engineering
Identifiers
URN: urn:nbn:se:ri:diva-65685DOI: 10.1109/CAIN58948.2023.00011Scopus ID: 2-s2.0-85165140236ISBN: 9798350301137 (electronic)OAI: oai:DiVA.org:ri-65685DiVA, id: diva2:1787112
Conference
2nd IEEE/ACM International Conference on AI Engineering - Software Engineering for AI, CAIN 2023. Melbourne, Australia. 15 May 2023 through 16 May 2023
Note

This project has received funding from Vinnova Swedenunder the FFI program with grant agreement No 2021-02572(precog), from the EU’s Horizon 2020 research and innovationprogram under grant agreement No 957197 (vedliot), and froma Swedish Research Council (VR) Project: Non-FunctionalRequirements for Machine Learning: Facilitating ContinuousQuality Awareness (iNFoRM).

Available from: 2023-08-11 Created: 2023-08-11 Last updated: 2023-08-11Bibliographically approved

Open Access in DiVA

fulltext(585 kB)85 downloads
File information
File name FULLTEXT01.pdfFile size 585 kBChecksum SHA-512
6e83c1a74196a2a07d989c1d945296e2b965184992cb72a8563316b4f44bd02113623be64b072a40f49dd57cfebc004308cef16cbbc927694cf44a138d38e147
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Borg, Markus

Search in DiVA

By author/editor
Borg, Markus
By organisation
RISE Research Institutes of Sweden
Software Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 89 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 136 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf