Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving

TL;DR

Drive My Way introduces a personalized vision-language-action framework for autonomous driving that adapts to individual driver habits and natural language instructions, enhancing human-centered driving experiences.

Contribution

It presents a novel personalized driving model that learns user embeddings and incorporates natural language guidance, enabling adaptive and individualized autonomous driving behaviors.

Findings

Improves style instruction adaptation on Bench2Drive

Generated behaviors are recognizable as individual drivers' styles

Enhances personalization in autonomous driving systems

Abstract

Human driving behavior is inherently personal, which is shaped by long-term habits and influenced by short-term intentions. Individuals differ in how they accelerate, brake, merge, yield, and overtake across diverse situations. However, existing end-to-end autonomous driving systems either optimize for generic objectives or rely on fixed driving modes, lacking the ability to adapt to individual preferences or interpret natural language intent. To address this gap, we propose Drive My Way (DMW), a personalized Vision-Language-Action (VLA) driving framework that aligns with users' long-term driving habits and adapts to real-time user instructions. DMW learns a user embedding from our personalized driving dataset collected across multiple real drivers and conditions the policy on this embedding during planning, while natural language instructions provide additional short-term guidance. Closed-loop evaluation on the Bench2Drive benchmark demonstrates that DMW improves style instruction adaptation, and user studies show that its generated behaviors are recognizable as each driver's own style, highlighting personalization as a key capability for human-centered autonomous driving. Our data and code are available at https://dmw-cvpr.github.io/.