在未知系统内部机制下，用历史状态预测未来状态并提前预警安全风险。
Predictive Monitoring of Black-Box Dynamical Systems
- 基于泰勒展开与后向差分法，从有限观测状态推断未来状态。
- 理论证明预测误差有上界，且实际测试中精度显著优于现有方法。
- 适合对复杂黑箱系统进行轻量级实时安全监控的场景。
我们研究了在定量安全属性下对黑箱动态系统进行预测性运行时监控的问题。黑箱设定意味着系统及控制器的确切语义未知，仅能有限时间点观测闭环系统的状态。本文提出一种新框架，根据过去观测状态预测未来状态，预测数量由用户指定。方法结合泰勒展开与后向差分算子进行数值微分，并在系统动力学与控制器平滑的假设下，推导出预测误差的上界。预测状态用于提前识别潜在的安全违规。实验表明，该方法对复杂黑箱系统具有实际应用价值，计算开销小，且显著优于当前最先进的预测安全监控技术。
原文摘要 · Abstract (English)
We study the problem of predictive runtime monitoring of black-box dynamical systems with quantitative safety properties. The black-box setting stipulates that the exact semantics of the dynamical system and the controller are unknown, and that we are only able to observe the state of the controlled (aka, closed-loop) system at finitely many time points. We present a novel framework for predicting future states of the system based on the states observed in the past. The numbers of past states and of predicted future states are parameters provided by the user. Our method is based on a combination of Taylor's expansion and the backward difference operator for numerical differentiation. We also derive an upper bound on the prediction error under the assumption that the system dynamics and the controller are smooth. The predicted states are then used to predict safety violations ahead in time. Our experiments demonstrate practical applicability of our method for complex black-box systems, showing that it is computationally lightweight and yet significantly more accurate than the state-of-the-art predictive safety monitoring techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。