In this work, we present a lightweight pipeline for robust behavioral cloning of a human driver using end-to-end imitation learning. The proposed pipeline was employed to train and deploy three distinct driving behavior models onto a simulated vehicle. The training phase comprised of data collection, balancing, augmentation, preprocessing, and training a neural network, following which the trained model was deployed onto the ego vehicle to predict steering commands based on the feed from an onboard camera. A novel coupled control law was formulated to generate longitudinal control commands on the go based on the predicted steering angle and other parameters such as the actual speed of the ego vehicle and the prescribed constraints for speed and steering. We analyzed the computational efficiency of the pipeline and evaluated the robustness of the trained models through exhaustive experimentation during the deployment phase. We also compared our approach against state-of-the-art implementation in order to comment on its validity.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Robust Behavioral Cloning for Autonomous Vehicles Using End-to-End Imitation Learning


    Additional title:

    Sae Intl. J Cav




    Publication date :

    2021-08-19


    Size :

    17 pages




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Vision-Based Trajectory Planning via Imitation Learning for Autonomous Vehicles

    Cai, Peide / Sun, Yuxiang / Chen, Yuying et al. | IEEE | 2019



    A Survey on Imitation Learning Techniques for End-to-End Autonomous Vehicles

    Le Mero, Luc / Yi, Dewei / Dianati, Mehrdad et al. | IEEE | 2022


    Dynamic Conditional Imitation Learning for Autonomous Driving

    Eraqi, Hesham M. / Moustafa, Mohamed N. / Honer, Jens | IEEE | 2022


    Robust end-to-end learning for autonomous vehicles

    Amini, Alexander Andre | BASE | 2018

    Free access