让自动驾驶模型理解施工区因果关系，提升导航准确性。
WorkDrive: Roadwork Chain of Causation for Autonomous Driving
- 构建施工区因果链，将感知结果与驾驶决策关联。
- 在ROADWork数据集上轨迹误差降低9.0%，进一步优化3.0%。
- 适合研究自动驾驶感知-决策对齐与因果推理的学者。
自动驾驶视觉语言模型在施工区表现不佳，因车道线等固定标识被改变或消失，临时障碍物如锥桶和护栏重新定义可行驶区域。尽管模型能检测这些物体，但缺乏显式引导时，仍依赖预训练中的熟悉元素进行推理，无法正确关联施工区观察与规划决策。本文提出WorkDrive框架，构建基于感知的施工区因果链（CoC），并将其与轨迹预测对齐。通过自动化多任务感知流程提取结构化场景事实，并注入因果链标注流程，引导标注者关注领域特定要素。生成的推理标签用于监督微调，再通过单一奖励——横向元动作与预测轨迹的一致性——进行强化学习。在最大的公开施工区数据集ROADWork上，所提因果链使轨迹平均位移误差（ADE）降低9.0%，一致性驱动的GRPO进一步降低3.0%，优于仅依赖轨迹的基线模型。代码与数据将公开发布。
原文摘要 · Abstract (English)
Autonomous driving vision-language models (VLMs) struggle in roadwork zones, where familiar visual cues such as lane markings and permanent signs are altered or absent, and temporary devices such as cones and barriers redefine the drivable corridor. VLMs can detect these objects, but without explicit guidance they anchor their reasoning on familiar elements from pre-training and fail to connect work-zone observations to correct planning decisions. We propose WorkDrive, a framework that constructs perception-grounded causal reasoning for work zones and aligns it with trajectory prediction. An automated multitask perception pipeline extracts structured scene facts and injects them into a Chain-of-Causation (CoC) annotation pipeline, redirecting the annotator's attention to domain-specific elements. The resulting reasoning labels are used for supervised fine-tuning, followed by reinforcement learning with a single reward: consistency between lateral meta-actions and the predicted trajectory. On ROADWork, the largest public work-zone dataset, the proposed roadwork CoC reduces trajectory average displacement error (ADE) by 9.0\%, and consistency-based GRPO yields a further 3.0\%, achieving progressive improvement over the trajectory-only baseline. Code and data will be publicly released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。