ICAT: 身体化世界モデルにおける物理的リスク予測のためのインシデント事例に基づく適応的テスト
ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
ビデオ生成型世界モデルが危険な行動のリスクを過小評価する問題を指摘し、実際の事故報告や安全マニュアルからリスク記憶を構築してテストケースを生成するICAT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: Zhenglin Lai, Sirui Huang, Yuteng Li, Changxin Huang, Jianqiang Li, Bingzhe Wu
分類: cs.RO, cs.AI, cs.CV, cs.LG
原文アブストラクト
Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions, which can induce unsafe preferences during planning and training on imagined rollouts. We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories and retrieving/composing them to constrain the generation of risk cases with causal chains and severity labels. Experiments on an ICAT-based benchmark show that mainstream world models frequently miss mechanisms and triggering conditions and miscalibrate severity, falling short of the reliability required for safety-critical embodied deployment.
