Learning driving behavior is fundamental for autonomous vehicles to “understand” traffic situations. This paper proposes a novel method for learning a behavioral model of car-following using automata learning algorithms. The model is interpretable for car-following behavior analysis. Frequent common state sequences are extracted from the model and clustered as driving patterns. The Next Generation SIMulation dataset on the I-80 highway is used for learning and evaluating. The experimental results demonstrate high accuracy of car-following model fitting.
Original languageEnglish
Title of host publication20th World Congress of the International Federation of Automatic Control (IFAC 2017)
EditorsD. Dochain, D. Henrion, D. Peaucelle
PublisherElsevier
Pages2353-2358
Volume50
DOIs
StatePublished - Jul 2017
Event20th World Congress of the International Federation of Automatic Control (IFAC), 2017 - Toulouse, France

Publication series

NameIFAC-PapersOnLine
PublisherElsevier
Number1
Volume50
ISSN (Electronic)2405-8963

Conference

Conference20th World Congress of the International Federation of Automatic Control (IFAC), 2017
Abbreviated titleIFAC 2017
CountryFrance
CityToulouse
Period9/07/1714/07/17
Internet address

ID: 28357265