A model for naturalistic glance behavior around Tesla Autopilot disengagements.
Attention
Driver modelling
Naturalistic driving
Takeover
Transition of control
Journal
Accident; analysis and prevention
ISSN: 1879-2057
Titre abrégé: Accid Anal Prev
Pays: England
ID NLM: 1254476
Informations de publication
Date de publication:
Oct 2021
Oct 2021
Historique:
received:
16
12
2020
revised:
12
07
2021
accepted:
07
08
2021
pubmed:
8
9
2021
medline:
1
10
2021
entrez:
7
9
2021
Statut:
ppublish
Résumé
We present a model for visual behavior that can simulate the glance pattern observed around driver-initiated, non-critical disengagements of Tesla's Autopilot (AP) in naturalistic highway driving. Drivers may become inattentive when using partially-automated driving systems. The safety effects associated with inattention are unknown until we have a quantitative reference on how visual behavior changes with automation. The model is based on glance data from 290 human initiated AP disengagement epochs. Glance duration and transition were modelled with Bayesian Generalized Linear Mixed models. The model replicates the observed glance pattern across drivers. The model's components show that off-road glances were longer with AP active than without and that their frequency characteristics changed. Driving-related off-road glances were less frequent with AP active than in manual driving, while non-driving related glances to the down/center-stack areas were the most frequent and the longest (22% of the glances exceeded 2 s). Little difference was found in on-road glance duration. Visual behavior patterns change before and after AP disengagement. Before disengagement, drivers looked less on road and focused more on non-driving related areas compared to after the transition to manual driving. The higher proportion of off-road glances before disengagement to manual driving were not compensated by longer glances ahead. The model can be used as a reference for safety assessment or to formulate design targets for driver management systems.
Sections du résumé
OBJECTIVE
OBJECTIVE
We present a model for visual behavior that can simulate the glance pattern observed around driver-initiated, non-critical disengagements of Tesla's Autopilot (AP) in naturalistic highway driving.
BACKGROUND
BACKGROUND
Drivers may become inattentive when using partially-automated driving systems. The safety effects associated with inattention are unknown until we have a quantitative reference on how visual behavior changes with automation.
METHODS
METHODS
The model is based on glance data from 290 human initiated AP disengagement epochs. Glance duration and transition were modelled with Bayesian Generalized Linear Mixed models.
RESULTS
RESULTS
The model replicates the observed glance pattern across drivers. The model's components show that off-road glances were longer with AP active than without and that their frequency characteristics changed. Driving-related off-road glances were less frequent with AP active than in manual driving, while non-driving related glances to the down/center-stack areas were the most frequent and the longest (22% of the glances exceeded 2 s). Little difference was found in on-road glance duration.
CONCLUSION
CONCLUSIONS
Visual behavior patterns change before and after AP disengagement. Before disengagement, drivers looked less on road and focused more on non-driving related areas compared to after the transition to manual driving. The higher proportion of off-road glances before disengagement to manual driving were not compensated by longer glances ahead.
APPLICATION
CONCLUSIONS
The model can be used as a reference for safety assessment or to formulate design targets for driver management systems.
Identifiants
pubmed: 34492560
pii: S0001-4575(21)00379-1
doi: 10.1016/j.aap.2021.106348
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
106348Informations de copyright
Copyright © 2021 The Authors. Published by Elsevier Ltd.. All rights reserved.