Learning only from a small set of examples remains a huge challenge in machine learning. Despite recent breakthroughs in the applications of neural networks, the applicability of these techniques has been limited by the requirement for large amounts of training data. What’s more, the standard supervised machine learning method does not provide a satisfactory solution for learning new concepts from little data. However, the ability to learn enough information from few samples has been demonstrated in humans. This suggests that humans may make use of prior knowledge of a previously learned model when learning new ones on a small amount of training examples. In the area of autonomous driving, the model learns to drive the vehicle with training data from humans, and most machine learning based control algorithms require training on very large datasets. Collecting and constructing training data set takes a huge amount of time and needs specific knowledge to gather relevant information. This paper aims to learn control parameters from only a few training images. We build a simple control system which can use prior knowledge to correct parameters when the vehicle deviates from the training route, and allows for learning on a few training examples. The system introduces a new architecture that when combined with neural networks, significantly lowers the amount of data required to make meaningful predictions and improves the ability to learn meaningful information on the surrounding environment in never before seen scenarios. We test a simple implementation of our algorithm on a 1/10-scale autonomous driving vehicle. The proposed models produce effective control commands in some untrained lane deviation scenarios, when the number of training examples is normally too small for traditional machine learning methods to work, and allows the vehicle to find the correct track in the lane.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Handling Deviation for Autonomous Vehicles after Learning from Small Dataset


    Weitere Titelangaben:

    Sae Technical Papers


    Beteiligte:
    Peng, Gaoliang (Autor:in) / Guo, Longxiang (Autor:in) / Wang, Weitian (Autor:in) / Jia, Yunyi (Autor:in) / Zhang, Zhujun (Autor:in)

    Kongress:

    WCX World Congress Experience ; 2018



    Erscheinungsdatum :

    2018-04-03




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    Handling Deviation for Autonomous Vehicles after Learning from Small Dataset

    Zhang, Zhujun / Guo, Longxiang / Wang, Weitian et al. | British Library Conference Proceedings | 2018


    Exception handling for autonomous vehicles

    LI DONG / MCNAUGHTON MATTHEW / YEHOSHUA SHIR et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    EXCEPTION HANDLING FOR AUTONOMOUS VEHICLES

    LI DONG / MCNAUGHTON MATTHEW PAUL / YEHOSHUA SHIR et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    HANDLING FAULTS IN AUTONOMOUS VEHICLES

    LORINCZ ALBERT / CIMINO MATTHEW DANIEL / LUPU MIRCEA FLORIAN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    HANDLING FAULTS IN AUTONOMOUS VEHICLES

    LORINCZ ALBERT / CIMINO MATTHEW DANIEL / LUPU MIRCEA FLORIAN et al. | Europäisches Patentamt | 2023

    Freier Zugriff