生成モーションプランナーの形式的安全検証と認定ローカル安定化による改良
Formal Safety Verification and Refinement for Generative Motion Planners via Certified Local Stabilization
生成モーションプランナーを小さな追従制御器で模倣し、ニューラルネットワーク検証を適用することで、安全性を形式的に保証しつつオンラインで安全に展開する手法を提案。
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: Devesh Nath, Haoran Yin, Glen Chou
分類: cs.RO, cs.LG, cs.SY, eess.SY, math.OC
原文アブストラクト
We present a method for formal safety verification of learning-based generative motion planners. Generative motion planners (GMPs) offer advantages over traditional planners, but verifying the safety and dynamic feasibility of their outputs is difficult since neural network verification (NNV) tools scale only to a few hundred neurons, while GMPs often contain millions. To preserve GMP expressiveness while enabling verification, our key insight is to imitate the GMP by stabilizing references sampled from the GMP with a small neural tracking controller and then applying NNV to the closed-loop dynamics. This yields reachable sets that rigorously certify closed-loop safety, while the controller enforces dynamic feasibility. Building on this, we construct a library of verified GMP references and deploy them online in a way that imitates the original GMP distribution whenever it is safe to do so, improving safety without retraining. We evaluate across diverse planners, including diffusion, flow matching, and vision-language models, improving safety in simulation (on ground robots and quadcopters) and on hardware (differential-drive robot).
