ネガティブデータの活用：衝突報告から反事実推論へ、安全な自動運転のための判断支援
The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving
衝突報告を自車視点の言語に正規化し、ログと衝突を統一シーン行動表現に変換して検索可能にすることで、提案行動の妥当性を過去事例から判断する自動運転システムを構築した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Jay Patrikar, Apoorva Sharma, Sushant Veer, Boyi Li, Sebastian Scherer, Marco Pavone
分類: cs.RO, cs.AI
原文アブストラクト
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.
