Deep QP安全フィルタ:到達可能性に基づく安全フィルタのためのモデルフリー学習
Deep QP Safety Filter: Model-free Learning for Reachability-based Safety Filter
ハミルトン・ヤコビ到達可能性とモデルフリー学習を組み合わせ、モデル未知のブラックボックス力学系に対してQP安全フィルタを学習する手法を提案。
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: Byeongjun Kim, H. Jin Kim
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
We introduce Deep QP Safety Filter, a fully data-driven safety layer for black-box dynamical systems. Our method learns a Quadratic-Program (QP) safety filter without model knowledge by combining Hamilton-Jacobi (HJ) reachability with model-free learning. We construct contraction-based losses for both the safety value and its derivatives, and train two neural networks accordingly. In the exact setting, the learned critic converges to the viscosity solution (and its derivative), even for non-smooth values. Across diverse dynamical systems -- even including a hybrid system -- and multiple RL tasks, Deep QP Safety Filter substantially reduces pre-convergence failures while accelerating learning toward higher returns than strong baselines, offering a principled and practical route to safe, model-free control.
