Toward Driver State Models that Explain Interindividual Variability of Distraction for Adaptive Automation

Margit Höfler, Peter Moertl

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem Konferenzband


Although there exist many models of distracted driving, identifying a distracted driver is still challenging as distraction might appear differently for different drivers but also within an individual driver in different situations. Here we present a driver state model that focusses on safety-relevant driver-distraction by conceptualizing driving control as influenced by both environmental factors and individual preferences. Also, the model differentiates compensatory control from exploratory control movements to better diagnose driving distraction. We then test several predictions that are derived from this model in a driving-simulator study. In this study participants drove the same road with or without a secondary task while their eye movements and driving performance was recorded. Our results are consistent with previous findings that overall steering control actions increase in the distraction condition but also that exploratory steering movements are apparently more sensitive indicators for distraction than compensatory control actions.

TitelHCI in Mobility, Transport, and Automotive Systems. Driving Behavior, Urban and Smart Mobility - 2nd International Conference, MobiTAS 2020, Held as Part of the 22nd HCI International Conference, HCII 2020, Proceedings
UntertitelDriving Behavior, Urban and Smart Mobility. HCII 2020
Redakteure/-innenHeidi Krömker
PublikationsstatusVeröffentlicht - 2020
VeranstaltungHCI International 2020: 22nd International Conference on Human-Computer Interaction - Virtuell, Dänemark
Dauer: 19 Jul 202024 Jul 2020


NameLecture Notes in Computer Science


KonferenzHCI International 2020

ASJC Scopus subject areas

  • !!Theoretical Computer Science
  • !!Computer Science(all)

Fingerprint Untersuchen Sie die Forschungsthemen von „Toward Driver State Models that Explain Interindividual Variability of Distraction for Adaptive Automation“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren