IEEE Trans Cybern. 2022 Sep;52(9):9587-9596. doi: 10.1109/TCYB.2021.3053575. Epub 2022 Aug 18.
Complex dynamical systems rely on the correct deployment and operation of numerous components, with state-of-the-art methods relying on learning-enabled components in various stages of modeling, sensing, and control at both offline and online levels. This article addresses the runtime safety monitoring problem of dynamical systems embedded with neural-network components. A runtime safety state estimator in the form of an interval observer is developed to construct the lower bound and upper bound of system state trajectories in runtime. The developed runtime safety state estimator consists of two auxiliary neural networks derived from the neural network embedded in dynamical systems, and observer gains to ensure the positivity, namely, the ability of the estimator to bound the system state in runtime, and the convergence of the corresponding error dynamics. The design procedure is formulated in terms of a family of linear programming feasibility problems. The developed method is illustrated by a numerical example and is validated with evaluations on an adaptive cruise control system.
复杂动力系统依赖于众多组件的正确部署和运行，最先进的方法依赖于在离线和在线水平的建模、传感和控制的各个阶段使用基于学习的组件。本文针对嵌入神经网络组件的动力系统的运行时安全监控问题。开发了一种以区间观测器形式的运行时安全状态估计器，以在线构建系统状态轨迹的下界和上界。所开发的运行时安全状态估计器由从嵌入动力系统的神经网络导出的两个辅助神经网络和观测器增益组成，以确保正定性，即估计器在运行时限制系统状态的能力和相应误差动力学的收敛性。设计过程以一系列线性规划可行性问题的形式给出。该方法通过数值示例进行说明，并在自适应巡航控制系统上进行评估验证。
