信頼性の高い長期計画のための構成拡散の改良
Refining Compositional Diffusion for Reliable Long-Horizon Planning
構成拡散計画におけるモード平均化問題を解決するため、事前学習済み拡散モデルの自己再構成誤差と重なり一貫性項を用いた訓練不要のガイダンス手法RCDを提案し、長期タスクで既存手法を上回る性能を示した。
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: Kyowoon Lee, Yunhao Luo, Anh Tong, Jaesik Choi
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Compositional diffusion planning generates long-horizon trajectories by stitching together overlapping short-horizon segments through score composition. However, when local plan distributions are multimodal, existing compositional methods suffer from mode-averaging, where averaging incompatible local modes leads to plans that are neither locally feasible nor globally coherent. We propose Refining Compositional Diffusion (RCD), a training-free guidance method that steers compositional sampling toward high-density, globally coherent plans. RCD leverages the self-reconstruction error of a pretrained diffusion model as a proxy for the log-density of composed plans, combined with an overlap consistency term that enforces consistency at segment boundaries. We show that the combined guidance concentrates sampling on high-density plans that mitigate mode-averaging. Experiments on challenging long-horizon tasks from OGBench, including locomotion, object manipulation, and pixel-based observations, demonstrate that RCD consistently outperforms existing methods.
関連論文
- モデルベースとモデルフリー拡散の統合による制約付き計画計画/拡散モデル
- SafeDiffuser: 拡散確率モデルによる安全な計画計画/拡散モデル
