変化するポテンシャルを操る：多目的行動におけるリアクティブ制御の十分性
Riding the Shifting Potential: When Reactive Control Suffices for Multi-Goal Behavior
静的ポテンシャル場の限界を指摘し、グラフベースの世界モデルにヌル空間投影を組み込むことで、多目的タスクの競合を状態に応じて動的に解決するリアクティブ制御手法を提案。非凸障害物回避や平面押し操作で高い成功率を示し、実ロボットにも適用可能。
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: Vito Mengers, Oliver Brock
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
Reactive control is often considered insufficient for multi-objective tasks because conflicting objectives give rise to local minima. We argue this limitation is not inherent but arises from static encodings that fail to reflect how objectives currently interact. We exploit the interaction structure encoded in a graph-based world model by extending it with nullspace projections: conflicts are resolved where they arise by projecting lower-priority gradients into the nullspace of higher-priority ones, with priorities determined continuously from the current state. We demonstrate this in two domains where conflicts between objectives are central: navigation around non-convex obstacles, where static potential fields fundamentally fail, and planar pushing of non-convex objects, where our method achieves $100\%$ success across one-hundred configurations versus $0\%$ for the steepest-descent baseline and ${\sim}55\%$ for diffusion policy, without demonstrations or retraining. The same formulation transfers directly to a real robot with additional perceptual and kinematic constraints, accommodating them through the same mechanism.
