The automobile industry has been finding ways to make driving safer and more convenient. We have reached a point where we need to automate the process of driving and make it more affordable. The present implementations are very robotic and cannot run among human-driven vehicles, and this made us realize the need of having a more naturalistic driving style for the autonomous vehicles. This research paper focuses on making a level 3 autonomous vehicle with the help of computer vision and deep learning. The main objective is to achieve the most ideal results in lane detection and object detection which can be worked upon to improve results. The reason that this project is of such great value is the fact that 80%of road accidents happen due to human error and negligence and we believe that providing a driver aid of some sorts could be really helpful in such scenarios. With the help of this paper we will be able to obtain high values with great accuracy with the help of which this can be implemented in real-time vehicles by just making a few alterations and by simple calibrations. We believe this will be a step toward a complete autonomous future.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Naturalistic Driving Simulation Using Automation


    Additional title:

    Advs in Intelligent Syst., Computing




    Publication date :

    2021-07-24


    Size :

    12 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Naturalistic Driving Study

    Raphael Grzebieta | DOAJ | 2015

    Free access

    Driving Style Clustering using Naturalistic Driving Data

    Chen, Kuan-Ting / Chen, Huei-Yen Winnie | Transportation Research Record | 2019


    Driving Maneuvers Analysis Using Naturalistic Highway Driving Data

    Li, Guofa / Li, Shengbo Eben / Jia, Lijuan et al. | IEEE | 2015


    Lane Change Detection Using Naturalistic Driving Data

    Guo, Hongyu / Xie, Kun / Keyvan-Ekbatani, Mehdi | IEEE | 2021


    Software simulation of headlighting performance and naturalistic driving data

    Flannagan, Michael J. / Sullivan, John M. / Sivak, Michael | Tema Archive | 2009