论文标题
通过最佳控制，实时的基于神经网络的模型近似可及的集合
Approximating Reachable Sets for Neural Network based Models in Real-Time via Optimal Control
论文作者
论文摘要
在本文中，我们提出了一个数据驱动的框架，以实时估计使用神经网络（NNS）对植物进行建模的控制系统的可及集合。我们利用了使用NNS轨迹数据学到的四摩托模型的运行示例。 NN学习的离线，可以在线兴奋，以获得线性近似值以进行可及性分析。我们使用基于动态模式分解的方法来获得NN模型的线性升降器。因此，因此获得的线性模型可以利用最佳控制理论实时获得与可触及集合的多元近似值。可以将多重近似值调整为任意程度的准确性。所提出的框架可以扩展到使用NNS估算植物动力学的其他非线性模型。我们使用四型动力学的说明性模拟来证明所提出的框架的有效性。
In this paper, we present a data-driven framework for real-time estimation of reachable sets for control systems where the plant is modeled using neural networks (NNs). We utilize a running example of a quadrotor model that is learned using trajectory data via NNs. The NN learned offline, can be excited online to obtain linear approximations for reachability analysis. We use a dynamic mode decomposition based approach to obtain linear liftings of the NN model. The linear models thus obtained can utilize optimal control theory to obtain polytopic approximations to the reachable sets in real-time. The polytopic approximations can be tuned to arbitrary degrees of accuracy. The proposed framework can be extended to other nonlinear models that utilize NNs to estimate plant dynamics. We demonstrate the effectiveness of the proposed framework using an illustrative simulation of quadrotor dynamics.
