DriveJudge: 用视觉-语言模型重新思考自动驾驶评估
DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models
AI总结：
提出DriveJudge，结合规则评估与VLM推理，通过选择性调用物理规则函数实现可解释且上下文感知的驾驶评估，在驾驶质量分类和轨迹偏好选择任务上超越现有方法。
摘要：
自动驾驶已转向端到端策略学习，其中可靠、可解释的策略评估是一个基本挑战，因为驾驶质量高度依赖于上下文。常用的基于规则的驾驶指标（如EPDMS）可解释但缺乏上下文感知，而近期基于VLM的评估虽具有上下文感知能力，但受限于模糊的VLM输出和较弱的物理基础。为了以既可解释又上下文感知的方式评估驾驶，我们引入了DriveJudge。DriveJudge是一个驾驶评估代理，它将规则基础评估与视觉-语言模型（VLM）推理相结合，并在解释环境上下文后有选择地调用基于物理的确定性规则函数。为了训练和评估DriveJudge，我们整理了一个包含33,577个具有挑战性的驾驶样本的大规模数据集，并附有人类标注，指示给定场景中的驾驶行为是否合理。利用该数据集，我们解决了驾驶指标评估中未被充分探索的问题，并引入了两个与人类对齐的基准任务：驾驶质量分类和轨迹偏好选择。DriveJudge在驾驶质量分类上比EPDMS高出21.23 AUC，在轨迹偏好选择上比近期基于VLM的DriveCritic高出6.5%，为可解释且精确的驾驶评估设立了新标准。
英文摘要：
Autonomous driving has shifted towards end-to-end policy learning, where reliable, interpretable policy evaluation is a fundamental challenge as driving quality is highly context-dependent. Commonly used rule-based driving metrics like EPDMS are interpretable but lack context-awareness, while recent VLMbased evaluations are context-aware but limited by ambiguous VLM outputs and weak physical grounding. To evaluate driving in a manner that is both interpretable and context-aware, we introduce DriveJudge. DriveJudge is a driving evaluation agent that combines rule-grounded evaluation with Vision-Language Model (VLM) reasoning and selectively invokes physically-grounded deterministic rule functions after interpreting the environmental context. To train and evaluate DriveJudge, we curate a large-scale dataset of 33,577 challenging driving samples with human annotations on whether the driving behavior is reasonable in the given scenario. With this dataset, we address the underexplored problem of driving metric evaluation, and introduce two human-aligned benchmark tasks: Driving Quality Classification and Trajectory Preference Selection. DriveJudge outperforms EPDMS for driving quality classification by 21.23 AUC, and the recent VLM-based DriveCritic for trajectory preference selection by 6.5%, setting a new standard for interpretable and precise driving evaluation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
