A throttle and brake controller was designed using fuzzy neural networks (FNN) and artificial neural networks (ANN). ANN and FNN regression models for the throttle control block were compared and an ANN classification model for the brake controller block was developed. All were trained and evaluated using a locally generated dataset from 6 drivers in the University of the Philippines. Both single hidden layer and two hidden layer FNN models for the throttle controllers exhibited lower errors against their ANN counterparts with FNN 2L incurring the lowest RMSE and MAE for both position and velocity simulations. FNN 1L was the safest model with the most stable space headway. The brake controller ANN 1L Br achieved 74.88% precision for throttle and 65.11% recall for brake cases.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Throttle and Brake Control Using Fuzzy-Neural Algorithm in Car Following


    Contributors:


    Publication date :

    2022-11-18


    Size :

    1440280 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    THROTTLE AND BRAKE CONTROL SYSTEMS FOR AUTOMATIC VEHICLE FOLLOWING

    Ioannou, P. / Xu, Z. | Taylor & Francis Verlag | 1994



    ACC+Stop&go maneuvers with throttle and brake fuzzy control

    Naranjo, J.E. / Gonzalez, C. / Garcia, R. et al. | IEEE | 2006