We investigate a deep learning methodology that can produce more accurate behaviors for autonomous vehicles with a much smaller amount of training data than by using supervised learning alone. In this paper, we develop a Correction-Based Incremental Learning (CBIL) algorithm that adds additional training examples strategically selected from cases where the autonomous vehicle has made mistakes, and is repeated over multiple iterations to dramatically improve mean time to failure. CBIL can be thought of as an online mistake bound learning model that reduces the number of training examples needed to define robust decision boundaries, and is trained offline to solve the problem of catastrophic forgetting. We quantitatively benchmark the performance of CBIL using several experiments related to autonomous platooning performed in truck driving simulations and in the laboratory with mobile robots.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Incremental Lifelong Deep Learning for Autonomous Vehicles


    Beteiligte:


    Erscheinungsdatum :

    01.11.2018


    Format / Umfang :

    1862367 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Learning & Autonomous Vehicles

    Seidl, R. | TIBKAT | 2018


    Learning Self-Awareness for Autonomous Vehicles: Exploring Multisensory Incremental Models

    Ravanbakhsh, Mahdyar / Baydoun, Mohamad / Campo, Damian et al. | IEEE | 2021


    Deep Learning-based Localisation for Autonomous Vehicles

    Carrillo Mendoza, Ricardo | TIBKAT | 2021

    Freier Zugriff

    Deep learning based beam control for autonomous vehicles

    ZHOU LUBING / MENG XIAOLI / SHETTI KARAN RAJENDRA | Europäisches Patentamt | 2023

    Freier Zugriff

    Deep learning based beam control for autonomous vehicles

    LUBING ZHOU / XIAOLI MENG / KARAN RAJENDRA SHETTI | Europäisches Patentamt | 2024

    Freier Zugriff