見えざるものを夢見る:ワールドモデル正則化拡散ポリシーによる分布外ロバスト性の実現
Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustness
拡散ポリシーにワールドモデルを統合し、分布外の外乱時に視覚入力を捨てて内部の想像(予測ダイナミクス)で制御を継続する手法を提案。MetaWorldや実世界で高い成功率を達成。
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: Ziou Hu, Xiangtong Yao, Yuan Meng, Zhenshan Bing, Alois Knoll
分類: cs.RO
原文アブストラクト
Diffusion policies excel at visuomotor control but often fail catastrophically under severe out-of-distribution (OOD) disturbances, such as unexpected object displacements or visual corruptions. To address this vulnerability, we introduce the Dream Diffusion Policy (DDP), a framework that deeply integrates a diffusion world model into the policy's training objective via a shared 3D visual encoder. This co-optimization endows the policy with robust state-prediction capabilities. When encountering sudden OOD anomalies during inference, DDP detects the real-imagination discrepancy and actively abandons the corrupted visual stream. Instead, it relies on its internal "imagination" (autoregressively forecasted latent dynamics) to safely bypass the disruption, generating imagined trajectories before smoothly realigning with physical reality. Extensive evaluations demonstrate DDP's exceptional resilience. Notably, DDP achieves a 73.8% OOD success rate on MetaWorld (vs. 23.9% without predictive imagination) and an 83.3% success rate under severe real-world spatial shifts (vs. 3.3% without predictive imagination). Furthermore, as a stress test, DDP maintains a 76.7% real-world success rate even when relying entirely on open-loop imagination post-initialization.
