安全なストリーミングフロー計画：サンプリング動力学と実行動力学の整合
Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics
拡散・フローマッチングに基づく生成プランナーにおいて、サンプリング動力学を実行動力学に整合させ、高次制御バリア関数で実行ステップのみ安全制約を課すことで、計画遅延を削減し安全性を向上させる手法を提案。
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: Seunghwan Jang, Jeongyong Yang, Siddharth Ancha, SooJean Han
分類: cs.RO, cs.LG
原文アブストラクト
Generative planners based on diffusion/flow matching can learn to synthesize long-horizon trajectories from demonstrations. However, real-world deployment requires (i) enforcing safety constraints during execution and (ii) tight online replanning at fast execution rates. Prior safe diffusion/flow planners generate the agent's full trajectory at once, while repeatedly perturbing intermediate states to satisfy safety constraints. This approach is not only computationally intensive, but also introduces distribution shift since the learned sampling dynamics is distinct from the system's execution dynamics. We propose SafeStreamingFlow, a goal-conditioned planner that aligns flow sampling dynamics with execution dynamics by sequentially integrating a learned state vector field with hierarchical state prediction. Importantly, we need to enforce safety constraints only for the executed step via high order control barrier functions. Across navigation, racing, and locomotion benchmarks, SafeStreamingFlow reduces planning latency and improves safety compared to existing methods, while maintaining competitive goal-reaching success.