グラフ誘導型安全ディフューザー:トポロジカルグラフ誘導による安全な拡散プランニング
Graph-Guided Safe Diffuser: Topological Graph Guidance for Safe Diffusion Planning
拡散モデルベースのプランナーに高レベルのトポロジカルグラフプランナーを組み合わせ、構造レベルで安全性を確保する階層的フレームワークG2SDを提案。迷路ナビゲーションで衝突なしの目標到達率を40-50%から98%に向上させた。
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: Nakgyu Yang, KwangBin Lee, SooJean Han
分類: cs.RO
原文アブストラクト
Many diffusion-based planners enforce safety through inference-time guidance, but such interleaved trajectory deformations often degrade kinematic feasibility due to manifold rupture. We propose Graph-Guided Safe Diffuser (G2SD), a hierarchical framework that leverages a high-level topological graph planner to guide a low-level diffusion model. G2SD enforces safety at a structural level by abstracting the data manifold into a learned latent graph, on which high-level planning is performed. Continuous trajectories are generated by diffusion planners, which are conditioned on the graph node representations selected by the high-level planner. Theoretical analyses demonstrate conditions under which manifold rupture occurs in diffusion planners, and show that G2SD improves safety by reducing the constraint violation probability as the number of segments increases. Experiments demonstrate that G2SD substantially outperforms baselines, increasing goal-reaching rate without any collision from 40-50% to 98% in Maze2D navigation and also achieving superior task scores in locomotion.