The Halting problem: Video analysis of self-driving cars in traffic

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Dokumenter

  • Fulltext

    Forlagets udgivne version, 2,58 MB, PDF-dokument

Using publicly uploaded videos of the Waymo and Tesla FSD self-driving cars, this paper documents how self-driving vehicles still struggle with some basics of road interaction. To drive safely self-driving cars need to interact in traffic with other road users. Yet traffic is a complex, long established social domain. We focus on one core element of road interaction: when road users yield for each other. Yielding - such as by slowing down for others in traffic - involves communication between different road users to decide who will 'go' and who will 'yield'. Videos of the Waymo and Tesla FSD self-driving cars show how these systems fail to both yield for others, as well as failing to go when yielded to. In discussion, we explore how these 'problems' illustrate both the complexity of designing for road interaction, but also how the space of physical machine/human social interactions more broadly can be designed for.

OriginalsprogEngelsk
TitelCHI 2023 - Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
ForlagAssociation for Computing Machinery, Inc.
Publikationsdato2023
Sider1-14
Artikelnummer12
ISBN (Elektronisk)9781450394215
DOI
StatusUdgivet - 2023
Begivenhed2023 CHI Conference on Human Factors in Computing Systems, CHI 2023 - Hamburg, Tyskland
Varighed: 23 apr. 202328 apr. 2023

Konference

Konference2023 CHI Conference on Human Factors in Computing Systems, CHI 2023
LandTyskland
ByHamburg
Periode23/04/202328/04/2023
SponsorACM SIGCHI, Apple, Bloomberg, Google, NSF, Siemens

Bibliografisk note

Funding Information:
Eric Stayton of Alliance Innovation Lab Silicon Valley provided invaluable insights during the videos analysis and with the connections to self-driving car design. We also thank Eric Laurier for helpful comments on the drafts and insights into ways to take the paper forward. We would also like to acknowledge the Swedish science foundation (grant RIT15-0046 "Implicit Interaction") and WASP-HS ("AI in Motion: Studying the Social World of Autonomous Vehicles", MMW 2020.0086) for financial support for this project.

Publisher Copyright:
© 2023 ACM.

Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk


Ingen data tilgængelig

ID: 384065981