Print Email Facebook Twitter Car-following Behavior Model Learning Using Timed Automata Title Car-following Behavior Model Learning Using Timed Automata Author Zhang, Yihuan (Tongji University) Lin, Q. (TU Delft Cyber Security) Wang, Jun (Tongji University) Verwer, S.E. (TU Delft Cyber Security) Contributor Dochain, D. (editor) Henrion, D. (editor) Peaucelle, D. (editor) Date 2017-07 Abstract 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. Subject real-time automata learningstate sequence clusteringcar-following behaviorpiece-wise fitting To reference this document use: http://resolver.tudelft.nl/uuid:886516fe-764c-4d15-8968-406ad9ee2eb1 DOI https://doi.org/10.1016/j.ifacol.2017.08.423 Publisher Elsevier Source IFAC-PapersOnLine Event 20th World Congress of the International Federation of Automatic Control (IFAC), 2017, 2017-07-09 → 2017-07-14, Toulouse, France Series IFAC-PapersOnLine, 2405-8963, 50 (1) Part of collection Institutional Repository Document type conference paper Rights © 2017 Yihuan Zhang, Q. Lin, Jun Wang, S.E. Verwer Files PDF 1_s2.0_S2405896317307735_main.pdf 517.13 KB Close viewer /islandora/object/uuid:886516fe-764c-4d15-8968-406ad9ee2eb1/datastream/OBJ/view