Print Email Facebook Twitter MOHA Title MOHA: A Multi-Mode Hybrid Automaton Model for Learning Car-Following Behaviors Author Lin, Q. (TU Delft Cyber Security) Zhang, Yihuan (Tongji University) Verwer, S.E. (TU Delft Cyber Security) Wang, Jun (Tongji University) Date 2019 Abstract This paper proposes a novel hybrid model for learning discrete and continuous dynamics of car-following behaviors. Multiple modes representing driving patterns are identified by partitioning the model into groups of states. The model is visualizable and interpretable for car-following behavior recognition, traffic simulation, and human-like cruise control. The experimental results using the next generation simulation datasets demonstrate its superior fitting accuracy over conventional models. Subject car-following behaviorComputational modelingData miningData modelsHybrid automatonLearning automataNumerical modelssimulation and control.Time series analysisVehicles To reference this document use: http://resolver.tudelft.nl/uuid:dc18fedd-0b16-4d10-ab79-06f977756d02 DOI https://doi.org/10.1109/TITS.2018.2823418 ISSN 1524-9050 Source IEEE Transactions on Intelligent Transportation Systems, 20 (2), 790-796 Bibliographical note Accepted author manuscript Part of collection Institutional Repository Document type journal article Rights © 2019 Q. Lin, Yihuan Zhang, S.E. Verwer, Jun Wang Files PDF 45517217_08384014.pdf 2.72 MB Close viewer /islandora/object/uuid%3Adc18fedd-0b16-4d10-ab79-06f977756d02/datastream/OBJ/view