This paper introduces a method to represent Takagi-Sugeno Fuzzy Control Systems (FCSs) as computational graphs, so they can be adjusted through a supervised training process based on gradient descent. It has been tested both with artificial (i.e. a known fuzzy controller) and naturalistic (i.e. driver's data extracted from the vehicle and the environment) data. The results achieved show high conformance to synthetic data, and seem to describe a car-following behavior with quite good precision, which suggests that it is possible to model the driver's behavior in a longitudinal model based on if-then type rules.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fuzzy Controller Inference via Gradient Descent to Model the Longitudinal Behavior on Real Drivers




    Erscheinungsdatum :

    2019-06-01


    Format / Umfang :

    2635702 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    A Recognition Method of Drivers Characteristics Using Fuzzy Inference

    Hiroshima, Y. / Ito, T. / Nishioka, K. | British Library Online Contents | 1995


    An Adaptive Network Fuzzy Inference System Controller for Car Following Behavior

    Long, Zhi Jun ;Li, Jing Fu | Trans Tech Publications | 2011


    ROUTE CHOICE BEHAVIOR MODEL USING FUZZY INFERENCE

    Lee, B. / Fujiwara, A. / Namgung, M. et al. | British Library Conference Proceedings | 2003


    Longitudinal Collision Avoidance Based on Model Predictive Controllers and Fuzzy Inference Systems

    Gonzalez, Leonardo / Matute-Peaspan, Jose Angel / Rastelli, Joshue Perez et al. | IEEE | 2020


    A Projected Gradient Descent Method for CRF Inference Allowing End-to-End Training of Arbitrary Pairwise Potentials

    Larsson, Måns / Arnab, Anurag / Kahl, Fredrik et al. | British Library Conference Proceedings | 2018