観測条件付き残差ニューラル制御バリア関数のハイパーネットワークによる学習
ORN-CBF: Learning Observation-conditioned Residual Neural Control Barrier Functions via Hypernetworks
ハミルトン・ヤコビ到達可能性解析に基づき、観測に条件付けられたニューラル制御バリア関数をハイパーネットワークで学習し、部分観測環境でも安全集合を近似する手法を提案。地上ロボットとクアッドコプターで有効性を検証。
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: Bojan Derajić, Sebastian Bernhard, Wolfgang Hönig
分類: cs.RO, cs.LG, cs.SY, eess.SY
原文アブストラクト
Control barrier functions (CBFs) have been demonstrated as an effective method for safety-critical control of autonomous systems. Although CBFs are simple to deploy, their design remains challenging, motivating the development of learning-based approaches. Yet, issues such as suboptimal safe sets, applicability in partially observable environments, and lack of rigorous safety guarantees persist. In this work, we propose observation-conditioned neural CBFs based on Hamilton-Jacobi (HJ) reachability analysis, which approximately recover the maximal safe sets. We exploit certain mathematical properties of the HJ value function, ensuring that the predicted safe set never intersects with the observed failure set. Moreover, we leverage a hypernetwork-based architecture that is particularly suitable for the design of observation-conditioned safety filters. The proposed method is examined both in simulation and hardware experiments for a ground robot and a quadcopter. The results show improved success rates and generalization to out-of-domain environments compared to the baselines.
