Due to the limitations of network communication conditions for online calling GPT, the onboard deployment of Large Language Models for autonomous driving is in need. In this paper, we propose Drive as Veteran, a fine-tuned LLaMA-7B model with driving tasks. A training set consisting of instructions, scenario descriptions and human-annotated driving tasks is established. Through LoRA fine-tuning, the capability of generating correct driving tasks of our model is demonstrated through a numerical experiment and the comparison to GPT-3.5 is presented. We show that smaller-sized Large Language Models could be deployed onboard with fast generation speed and high accuracy, which could serve as a core component for decision-making in autonomous driving.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Drive as Veteran: Fine-tuning of an Onboard Large Language Model for Highway Autonomous Driving


    Beteiligte:
    Wang, Yujin (Autor:in) / Huang, Zhaoyan (Autor:in) / Liu, Quanfeng (Autor:in) / Zheng, Yutong (Autor:in) / Hong, Jinlong (Autor:in) / Chen, Junyi (Autor:in) / Xiong, Lu (Autor:in) / Gao, Bingzhao (Autor:in) / Chen, Hong (Autor:in)


    Erscheinungsdatum :

    02.06.2024


    Format / Umfang :

    1905009 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    ONBOARD INFORMATION PROCESSING DEVICE, AUTONOMOUS DRIVING SYSTEM, AND ONBOARD SYSTEM

    ANDO KOICHI / AMPO KEISUKE | Europäisches Patentamt | 2023

    Freier Zugriff

    ONBOARD INFORMATION PROCESSING DEVICE, AUTONOMOUS DRIVING SYSTEM, AND ONBOARD SYSTEM

    ANDO KOICHI / AMPO KEISUKE | Europäisches Patentamt | 2024

    Freier Zugriff

    Autonomous onboard optical processor for driving aid

    Attia, Mondher / Servel, Alain / Guibert, Laurent | SPIE | 1995


    Fusing Onboard Modalities with V2V Information for Autonomous Driving

    Wan, Haodong / Xu, Wenchao / Cheng, Nan et al. | IEEE | 2022


    An Onboard Aeroengine Model-Tuning System

    Yuan, Ye | Online Contents | 2017