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.
Drive as Veteran: Fine-tuning of an Onboard Large Language Model for Highway Autonomous Driving
2024-06-02
1905009 byte
Conference paper
Electronic Resource
English
ONBOARD INFORMATION PROCESSING DEVICE, AUTONOMOUS DRIVING SYSTEM, AND ONBOARD SYSTEM
European Patent Office | 2023
|ONBOARD INFORMATION PROCESSING DEVICE, AUTONOMOUS DRIVING SYSTEM, AND ONBOARD SYSTEM
European Patent Office | 2024
|Autonomous onboard optical processor for driving aid
SPIE | 1995
|An Onboard Aeroengine Model-Tuning System
Online Contents | 2017
|