Towards a cognitive warning system for safer hybrid traffic

Ágoston Török, Krisztián Varga, Jean Marie Pergandi, Pierre Mallet, Ferenc Honbolygó, V. Csépe, Daniel Mestre

Research output: Contribution to journalArticle

Abstract

Technological development brings increasingly closer the era of widely available self-driving cars. However, presumably there will be a time when human drivers and self-driving cars would share the same roads. In the current paper, we propose a cognitive warning system that utilizes information collected from the behaviour of the human driver and sends warning signals to self-driving cars in case of human related emergency. We demonstrate that such risk detection can identify danger earlier than an external sensor would, based on the behaviour of the human-driven vehicle. We used data from a simulator experiment, where 21 participants slalomed between road bumps in a virtual reality environment. Occasionally, they had to react to dangerous roadside stimuli by large steering movements. We used one-class SVM to detect emergency behaviour in both steering and vehicle trajectory data. We found earlier detection of emergency based on steering wheel data, than based on vehicle trajectory data. We conclude that tracking cognitive variables of the human driver means that we can utilize the outstanding power of the brain to evaluate external stimuli. Information about the result of this evaluation (be it steering action or saccade) could be the basis of a warning signal that is readily understood by the computer of a self-driving car.

Original languageEnglish
Pages (from-to)431-439
Number of pages9
JournalIntelligent Decision Technologies
Volume11
Issue number4
DOIs
Publication statusPublished - Jan 1 2017

Fingerprint

Alarm systems
Railroad cars
Trajectories
Roadsides
Eye movements
Virtual reality
Brain
Wheels
Simulators
Sensors
Experiments

Keywords

  • driver behaviour
  • one-class SVM
  • t-SNE
  • Warning system

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Török, Á., Varga, K., Pergandi, J. M., Mallet, P., Honbolygó, F., Csépe, V., & Mestre, D. (2017). Towards a cognitive warning system for safer hybrid traffic. Intelligent Decision Technologies, 11(4), 431-439. https://doi.org/10.3233/IDT-170305

Towards a cognitive warning system for safer hybrid traffic. / Török, Ágoston; Varga, Krisztián; Pergandi, Jean Marie; Mallet, Pierre; Honbolygó, Ferenc; Csépe, V.; Mestre, Daniel.

In: Intelligent Decision Technologies, Vol. 11, No. 4, 01.01.2017, p. 431-439.

Research output: Contribution to journalArticle

Török, Á, Varga, K, Pergandi, JM, Mallet, P, Honbolygó, F, Csépe, V & Mestre, D 2017, 'Towards a cognitive warning system for safer hybrid traffic', Intelligent Decision Technologies, vol. 11, no. 4, pp. 431-439. https://doi.org/10.3233/IDT-170305
Török Á, Varga K, Pergandi JM, Mallet P, Honbolygó F, Csépe V et al. Towards a cognitive warning system for safer hybrid traffic. Intelligent Decision Technologies. 2017 Jan 1;11(4):431-439. https://doi.org/10.3233/IDT-170305
Török, Ágoston ; Varga, Krisztián ; Pergandi, Jean Marie ; Mallet, Pierre ; Honbolygó, Ferenc ; Csépe, V. ; Mestre, Daniel. / Towards a cognitive warning system for safer hybrid traffic. In: Intelligent Decision Technologies. 2017 ; Vol. 11, No. 4. pp. 431-439.
@article{0af34bd906614cbda96faaa393322fed,
title = "Towards a cognitive warning system for safer hybrid traffic",
abstract = "Technological development brings increasingly closer the era of widely available self-driving cars. However, presumably there will be a time when human drivers and self-driving cars would share the same roads. In the current paper, we propose a cognitive warning system that utilizes information collected from the behaviour of the human driver and sends warning signals to self-driving cars in case of human related emergency. We demonstrate that such risk detection can identify danger earlier than an external sensor would, based on the behaviour of the human-driven vehicle. We used data from a simulator experiment, where 21 participants slalomed between road bumps in a virtual reality environment. Occasionally, they had to react to dangerous roadside stimuli by large steering movements. We used one-class SVM to detect emergency behaviour in both steering and vehicle trajectory data. We found earlier detection of emergency based on steering wheel data, than based on vehicle trajectory data. We conclude that tracking cognitive variables of the human driver means that we can utilize the outstanding power of the brain to evaluate external stimuli. Information about the result of this evaluation (be it steering action or saccade) could be the basis of a warning signal that is readily understood by the computer of a self-driving car.",
keywords = "driver behaviour, one-class SVM, t-SNE, Warning system",
author = "{\'A}goston T{\"o}r{\"o}k and Kriszti{\'a}n Varga and Pergandi, {Jean Marie} and Pierre Mallet and Ferenc Honbolyg{\'o} and V. Cs{\'e}pe and Daniel Mestre",
year = "2017",
month = "1",
day = "1",
doi = "10.3233/IDT-170305",
language = "English",
volume = "11",
pages = "431--439",
journal = "Intelligent Decision Technologies",
issn = "1872-4981",
publisher = "IOS Press",
number = "4",

}

TY - JOUR

T1 - Towards a cognitive warning system for safer hybrid traffic

AU - Török, Ágoston

AU - Varga, Krisztián

AU - Pergandi, Jean Marie

AU - Mallet, Pierre

AU - Honbolygó, Ferenc

AU - Csépe, V.

AU - Mestre, Daniel

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Technological development brings increasingly closer the era of widely available self-driving cars. However, presumably there will be a time when human drivers and self-driving cars would share the same roads. In the current paper, we propose a cognitive warning system that utilizes information collected from the behaviour of the human driver and sends warning signals to self-driving cars in case of human related emergency. We demonstrate that such risk detection can identify danger earlier than an external sensor would, based on the behaviour of the human-driven vehicle. We used data from a simulator experiment, where 21 participants slalomed between road bumps in a virtual reality environment. Occasionally, they had to react to dangerous roadside stimuli by large steering movements. We used one-class SVM to detect emergency behaviour in both steering and vehicle trajectory data. We found earlier detection of emergency based on steering wheel data, than based on vehicle trajectory data. We conclude that tracking cognitive variables of the human driver means that we can utilize the outstanding power of the brain to evaluate external stimuli. Information about the result of this evaluation (be it steering action or saccade) could be the basis of a warning signal that is readily understood by the computer of a self-driving car.

AB - Technological development brings increasingly closer the era of widely available self-driving cars. However, presumably there will be a time when human drivers and self-driving cars would share the same roads. In the current paper, we propose a cognitive warning system that utilizes information collected from the behaviour of the human driver and sends warning signals to self-driving cars in case of human related emergency. We demonstrate that such risk detection can identify danger earlier than an external sensor would, based on the behaviour of the human-driven vehicle. We used data from a simulator experiment, where 21 participants slalomed between road bumps in a virtual reality environment. Occasionally, they had to react to dangerous roadside stimuli by large steering movements. We used one-class SVM to detect emergency behaviour in both steering and vehicle trajectory data. We found earlier detection of emergency based on steering wheel data, than based on vehicle trajectory data. We conclude that tracking cognitive variables of the human driver means that we can utilize the outstanding power of the brain to evaluate external stimuli. Information about the result of this evaluation (be it steering action or saccade) could be the basis of a warning signal that is readily understood by the computer of a self-driving car.

KW - driver behaviour

KW - one-class SVM

KW - t-SNE

KW - Warning system

UR - http://www.scopus.com/inward/record.url?scp=85040032885&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040032885&partnerID=8YFLogxK

U2 - 10.3233/IDT-170305

DO - 10.3233/IDT-170305

M3 - Article

AN - SCOPUS:85040032885

VL - 11

SP - 431

EP - 439

JO - Intelligent Decision Technologies

JF - Intelligent Decision Technologies

SN - 1872-4981

IS - 4

ER -