CADET: 物理に基づく因果監査とエンドツーエンド運転プランナーの訓練不要な交絡除去
CADET: Physics-Grounded Causal Auditing and Training-Free Deconfounding of End-to-End Driving Planners
エンドツーエンドの自動運転プランナーが統計的な近道(因果関係のない手がかりへの依存)を学習する問題を検出・修正する、訓練不要のフレームワークCADETを提案した。
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: Zikun Guo, Yuanyuan Li, Rongjin Zou
分類: cs.RO, cs.AI
原文アブストラクト
End-to-end (E2E) autonomous-driving planners trained by imitation are prone to statistical shortcuts: they associate scene elements that merely co-occur with expert actions (a roadside object, a building facade) with driving decisions, rather than the variables that causally determine them. Such causal confusion silently compromises reliability in long-tail scenarios, and it is difficult to detect, because prevailing open-loop metrics (L2 displacement and collision rate) are dominated by ego status and do not indicate whether a planner depends on spurious cues. Existing remedies based on causal-intervention training require retraining large models and cannot audit a planner that is already deployed. We present CADET, a training-free framework that audits, benchmarks, and repairs spurious reliance in pretrained E2E planners without any parameter update.
