Koopman作用素とConformal保証によるスケーラブルなデータ駆動型到達可能性解析と制御
Scalable Data-Driven Reachability Analysis and Control via Koopman Operators with Conformal Coverage Guarantees
Koopman理論とニューラルネットワークで未知の非線形ダイナミクスを線形近似し、Conformal予測で誤差を保証することで、高次元システムの確率的な安全性検証を効率的に行うフレームワークを提案した。
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: Devesh Nath, Haoran Yin, Glen Chou
分類: eess.SY, cs.AI, cs.LG, cs.RO, cs.SY, math.OC
原文アブストラクト
We propose a scalable reachability-based framework for probabilistic, data-driven safety verification of unknown nonlinear dynamics. We use Koopman theory with a neural network (NN) lifting function to learn an approximate linear representation of the dynamics and design linear controllers in this space to enable closed-loop tracking of a reference trajectory distribution. Closed-loop reachable sets are efficiently computed in the lifted space and mapped back to the original state space via NN verification tools. To capture model mismatch between the Koopman dynamics and the true system, we apply conformal prediction to produce statistically-valid error bounds that inflate the reachable sets to ensure the true trajectories are contained with a user-specified probability. These bounds generalize across references, enabling reuse without recomputation. Results on high-dimensional MuJoCo tasks (11D Hopper, 28D Swimmer) and 12D quadcopters show improved reachable set coverage rate, computational efficiency, and conservativeness over existing methods.
