# YOUDrive：将驾驶风格作为端到端自动驾驶的可组合方向

> 原文链接：https://robotics.hellobike.com/papers/2026-10-10-2610-14802
> 频道：papers | 更新日期：2026-10-10 | 标签：arxiv, cs.RO
> 核心摘要：YOUDrive用可缩放组合的风格方向控制端到端驾驶行为，并在NAVSIM navtest上验证。

# YOUDrive：将驾驶风格作为端到端自动驾驶的可组合方向

::: v-pre
> 原文链接：[YOUDrive: Driving Style as a Composable Direction for End-to-End Autonomous Driving](https://arxiv.org/abs/2610.14802)（arXiv 2610.14802 · 发布日期：2026-10-10）

**YOUDrive: Driving Style as a Composable Direction for End-to-End Autonomous Driving**

YOUDrive用可缩放组合的风格方向控制端到端驾驶行为，并在NAVSIM navtest上验证。

## 核心要点

- 端到端驾驶策略任务性能强，但缺少推理时调节加速、制动和车距等驾驶风格的直接机制。
- YOUDrive将各教师行为蒸馏为任务向量，在规划器表征中形成可缩放、可组合的风格方向。
- 在这些方向条件下，flow-matching解码器建模多模态轨迹分布，并生成运动学可行的运动备选。
- NAVSIM navtest上，单一系数可单调控制六种教师persona的进取性，PDMS最高达0.954；代码、检查点和指标将发布。

**验证范围与局限**：验证范围为NAVSIM navtest上的个人与混合风格配置。

## 英文摘要 (Abstract)

End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a vehicle accelerates, brakes, and maintains distance. Policies trained without explicit preference conditioning lack a direct mechanism for adjusting these behaviors at inference. We propose YOUDrive, a vision--language--action planner for continuous and composable driving-style control. Each teacher's behavior is distilled into a task vector, a learned parameter update that induces a style direction in the planner's representation. These directions can be scaled and combined at inference without retraining the backbone. Conditioned on these directions, a flow-matching decoder models a multimodal trajectory distribution and generates kinematically feasible motion alternatives. We introduce the Style Alignment Score (SAS) to describe human-referenced kinematic behavior after safety and task gating. On NAVSIM navtest, a single coefficient monotonically controls assertiveness across six teacher-derived personas, while PDMS remains above 0.90 across the tested individual and blended configurations, reaching 0.954. Further analyses reveal systematic policy-specific kinematics after controlling for scene context, whereas the evaluated discrete style labels provide limited additional explanatory power. Code, checkpoints, and the metric will be released.

作者：Guantian Zheng, Lidong Yu, Tianyu Gao, Jiaxing Chen, Jiashu Li, Chen Lv
:::

## 原始参考来源 (Sources)

- [arXiv 2610.14802：YOUDrive: Driving Style as a Composable Direction for End-to-End Autonomous Driving](https://arxiv.org/abs/2610.14802)