Standard-size autonomous navigation vehicles have rapidly improved thanks to the breakthroughs of deep learning. However, scaling autonomous driving to low-power systems deployed on dynamic environments poses several challenges that prevent their adoption. To address them, we propose a closed-loop learning flow for autonomous driving mini-vehicles that includes the target environment in-the-loop. We leverage a family of compact and high-throughput tinyCNNs to control the mini-vehicle, which learn in the target environment by imitating a computer vision algorithm, i.e., the expert. Thus, the tinyCNNs, having only access to an on-board fast-rate linear camera, gain robustness to lighting conditions and improve over time. Further, we leverage GAP8, a parallel ultra-low-power RISC-V SoC, to meet the inference requirements. When running the family of CNNs, our GAP8's solution outperforms any other implementation on the STM32L4 and NXP k64f (Cortex-M4), reducing the latency by over 13x and the energy consummation by 92%.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Robustifying the deployment of tinyML models for autonomous mini-vehicles


    Beteiligte:
    de Prado M. (Autor:in) / Rusci M. (Autor:in) / Donze R. (Autor:in) / Capotondi A. (Autor:in) / Monnerat S. (Autor:in) / Benini L. (Autor:in) / Pazos N. (Autor:in) / de Prado, M. / Rusci, M. / Donze, R.

    Erscheinungsdatum :

    2021-01-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Robustifying the deployment of tinyml models for autonomous mini-vehicles

    de Prado M. / Rusci M. / Capotondi A. et al. | BASE | 2021

    Freier Zugriff

    Robustifying Car-Following Models with Explicit Reaction Times

    Kreutz, Karsten / Eggert, Julian | IEEE | 2022


    Adaptive Traffic Control With TinyML

    Roshan, A. Navaas / Gokulapriyan, B. / Siddarth, C. et al. | IEEE | 2021


    DEPLOYMENT OF AUTONOMOUS VEHICLES

    GEISSLER FLORIAN / ROSALES RAFAEL / CIHANGIR NESLIHAN KOSE et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Adaptive traffic control method based on TinyML

    SONG CHEN / GE JUNZHENG / LI RUI | Europäisches Patentamt | 2022

    Freier Zugriff