This paper deals with the diagnosis of driving styles and traffic conditions. Two analyses, the multiple correspondence analysis (M.C.A.) and the discriminant analysis (D.A), have been used to classify each driving behaviour among three driving styles and two traffic densities. This has been realised during experimentations carried out on SHERPA driving simulator. 11 subjects had to drive on a combination of A-roads and B-roads, with various traffic densities. During these experimentations, drivers were filmed and variables, characteristic of vehicle position in relation to the road and of the driver's actions on the vehicle, were recorded. M.C.A was applied on theses variables, before hand cut into space modalities, to put forward steady phases in driving style and traffic conditions, and to identify the best set of recorded variables that allows to discriminate those phases. From the M.C.A. results, the D.A. allowed to perform an automatic classification of the new observations in the first factor plane resulting from the M.C.A.. This analysis combination gives satisfying results (87.5% of the samples were in the right set); that can still be improved through a better management of inter-individual differences in the analysis.
Driving styles and traffic density diagnosis in simulated driving conditions
Intelligent Vehicle Symposium, 2002. IEEE ; 2 ; 298-303 vol.2
01.01.2002
384772 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Driving Styles and Traffic Density Diagnosis in Simulated Driving Conditions
British Library Conference Proceedings | 2003
|Measuring driving styles and calibrating driving models
Europäisches Patentamt | 2024
|MEASURING DRIVING STYLES AND CALIBRATING DRIVING MODELS
Europäisches Patentamt | 2023
|DISC: Dataset for Analyzing Driving Styles In Simulated Crashes for Mixed Autonomy
ArXiv | 2025
|