Data-Driven Distributionally Robust Safety Verification Using Barrier Certificates and Conditional Mean Embeddings

arXiv:2403.10497v1 Announce Type: cross
Abstract: Algorithmic verification of realistic systems to satisfy safety and other temporal requirements has suffered from poor scalability of the employed formal approaches. To design systems with rigorous guarantees, many approaches still rely on exact models of the underlying systems. Since this assumption can rarely be met in practice, models have to be inferred from measurement data or are bypassed completely. Whilst former usually requires the model structure to be known a-priori and immense amounts of …

abstract arxiv cs.lg cs.sy data data-driven design design systems eess.sy embeddings mean requirements robust safety scalability systems temporal type verification