用车祸报告训练自动驾驶系统，让决策更安全可靠。
The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving
- 将事故描述转为以车辆为中心的视角，统一建模为可检索的场景动作表示。
- 在nuScenes数据集上，关键动作召回率从24%提升至53%。
- 引入反事实推理，帮助系统在高风险场景中做出更优决策，适合安全敏感应用。
基于学习的自动驾驶系统通常仅在无事故数据上训练，难以应对接近安全边界的场景。真实车祸报告恰好提供了所需的对比证据，但其叙述结构松散、视角为第三人称，且与传感器视图关联弱。本文通过将事故叙述转化为以车辆为中心的语言，并将日志与事故统一映射到场景-动作表示空间，实现高效检索。决策时，系统通过检索相似先例来评估当前动作；进一步引入代理式反事实扩展，为每个可能动作生成合理替代方案，检索并比较其后果后作出判断。在nuScenes基准测试中，先例检索显著提升了模型校准性，上下文偏好动作的召回率从24%提升至53%。反事实变体在保持该优势的同时，进一步增强了高风险场景下的决策精度。
原文摘要 · Abstract (English)
Learning-based autonomous driving systems are trained mostly on incident-free data, offering little guidance near safety-performance boundaries. Real crash reports contain precisely the contrastive evidence needed, but they are hard to use: narratives are unstructured, third-person, and poorly grounded to sensor views. We address these challenges by normalizing crash narratives to ego-centric language and converting both logs and crashes into a unified scene-action representation suitable for retrieval. At decision time, our system adjudicates proposed actions by retrieving relevant precedents from this unified index; an agentic counterfactual extension proposes plausible alternatives, retrieves for each, and reasons across outcomes before deciding. On a nuScenes benchmark, precedent retrieval substantially improves calibration, with recall on contextually preferred actions rising from 24% to 53%. The counterfactual variant preserves these gains while sharpening decisions near risk.
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。