X-Driver: Explainable Autonomous Driving with Vision-Language Models

TL;DR

X-Driver introduces a multi-modal large language model framework for autonomous driving that improves closed-loop performance and interpretability, validated through simulation benchmarks and surpassing current state-of-the-art methods.

Contribution

The paper presents X-Driver, a novel multi-modal large language model framework utilizing Chain-of-Thought and autoregressive modeling for enhanced autonomous driving.

Findings

X-Driver outperforms existing methods in closed-loop driving tasks.

X-Driver improves interpretability of driving decisions.

Validated on CARLA benchmarks with superior results.

Abstract

End-to-end autonomous driving has advanced significantly, offering benefits such as system simplicity and stronger driving performance in both open-loop and closed-loop settings than conventional pipelines. However, existing frameworks still suffer from low success rates in closed-loop evaluations, highlighting their limitations in real-world deployment. In this paper, we introduce X-Driver, a unified multi-modal large language models(MLLMs) framework designed for closed-loop autonomous driving, leveraging Chain-of-Thought(CoT) and autoregressive modeling to enhance perception and decision-making. We validate X-Driver across multiple autonomous driving tasks using public benchmarks in CARLA simulation environment, including Bench2Drive[6]. Our experimental results demonstrate superior closed-loop performance, surpassing the current state-of-the-art(SOTA) while improving the interpretability of driving decisions. These findings underscore the importance of structured reasoning in end-to-end driving and establish X-Driver as a strong baseline for future research in closed-loop autonomous driving.