走我的路：面向个性化驾驶的视觉-语言-动作模型偏好对齐
Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving
把驾驶风格编码为用户嵌入并作为规划策略的条件输入，再叠加自然语言指令做短期引导，为端到端驾驶中「个性化/风格可控」提供了一条可复用的条件化 VLA 思路；其个性化驾驶数据集与 Bench2Drive 闭环评测协议也可直接用于评估风格适配能力。
原文依据 DMW learns a user embedding from our personalized driving dataset collected across multiple real drivers and conditions the policy on this embedding during planning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人类驾驶行为本质上是个人化的，它由长期习惯塑造，并受短期意图影响。不同个体在加速、制动、汇入、让行与超车等各类情形下的方式各不相同。然而，现有的端到端自动驾驶系统要么针对通用目标进行优化，要么依赖固定的驾驶模式，缺乏适应个体偏好或理解自然语言意图的能力。为弥补这一空白，我们提出 Drive My Way（DMW），一个个性化的视觉-语言-动作（VLA）驾驶框架，它能够与用户的长期驾驶习惯对齐，并适应用户的实时指令。DMW 从我们采集的个性化驾驶数据集中学习用户嵌入，该数据集涵盖多名真实驾驶员与多种行驶条件；在规划阶段，策略以该嵌入为条件，同时自然语言指令提供额外的短期引导。在 Bench2Drive 基准上的闭环评测表明，DMW 提升了风格指令的适应能力；用户研究显示，其生成的行为可被识别为每位驾驶员自身的风格，凸显了个性化作为以人为中心的自动驾驶关键能力的重要性。
英文原文摘要 1192 字符
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.