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

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.