arXiv cs.AI· Roland Stolz, Vitus L\"untzel, Romain Pascual, Eric Sax, Matthias Althoff·· 2 小时前AI 评分31
通过模型一致性保障系统演化下屏蔽式数据驱动控制器的安全
Keeping Shielded Data-Driven Controllers Safe Under System Evolution via Model Consistency
AI 导读
数据驱动控制器的黑盒特性带来安全风险,常见做法是用 shield 屏蔽器基于物理系统假设限制输入,但系统演化会使固定假设失效。该 arXiv 论文提出模型驱动方法 V-SUM,将控制器与安全屏蔽器统一为虚拟单一底层模型,通过一致性检查持续评估安全保证,并借助一致性保持规则自动更新模型、恢复有效屏蔽。在单轮车系统 reach-avoid 任务上的评估显示,该方法能在系统变化下有效维持安全保证。
正文 · 原文
Abstract:Cyber-physical systems (CPS) increasingly contain data-driven controllers, which raise safety concerns given their black-box nature. A common mitigation is to enforce system safety via a shield around the controller, which restricts the inputs based on assumptions about the physical system. However, these assumptions are usually fixed and may become invalid as the system evolves (during development or due to component degradation), possibly leading to unsafe behavior. We address this limitation in a model-driven approach that treats both the data-driven controller and safety shield as first-class models that are integrated into a virtual single underlying model (V-SUM) alongside system models. We describe system evolution as changes in the associated models, such that consistency checking yields a continuous assessment of safety guarantees. In case of inconsistencies, consistency-preservation rules automatically update the models and restore a valid safety shield. We evaluate our approach on a reach-avoid task for a unicycle system. The results show that consistency-driven evolution effectively maintains safety guarantees under system changes and provides a principled basis for evaluating and restoring performance.
| Subjects: | Systems and Control (eess.SY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.24428 [eess.SY] |
| (or arXiv:2611.24428v1 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24428 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Roland Stolz [view email]
[v1]
Wed, 18 Nov 2026 13:45:39 UTC (121 KB)
来源:arXiv cs.AI · arxiv.org