Driving Style Alignment for LLM-powered Driver Agent

TL;DR

This paper introduces a multi-alignment framework for aligning LLM-powered driver agents with human driving styles, utilizing a new high-quality natural language dataset from real driving data, validated through simulations and human evaluations.

Contribution

The paper presents a novel multi-alignment framework and a high-quality natural language dataset for aligning autonomous driving agents with human driving styles.

Findings

Effective alignment demonstrated in CARLA simulations

Human evaluations confirm improved driving style matching

New dataset enhances LLM training for driving behaviors

Abstract

Recently, LLM-powered driver agents have demonstrated considerable potential in the field of autonomous driving, showcasing human-like reasoning and decision-making abilities.However, current research on aligning driver agent behaviors with human driving styles remains limited, partly due to the scarcity of high-quality natural language data from human driving behaviors.To address this research gap, we propose a multi-alignment framework designed to align driver agents with human driving styles through demonstrations and feedback. Notably, we construct a natural language dataset of human driver behaviors through naturalistic driving experiments and post-driving interviews, offering high-quality human demonstrations for LLM alignment. The framework's effectiveness is validated through simulation experiments in the CARLA urban traffic simulator and further corroborated by human evaluations. Our research offers valuable insights into designing driving agents with diverse driving styles.The implementation of the framework and details of the dataset can be found at the link.