Neural network optimal feedback control with enhanced closed loop stability

Neural network optimal feedback control with enhanced closed loop stability
复制标题

具有增强闭环稳定性的神经网络最优反馈控制

DOI:
10.23919/acc53348.2022.9867619
复制
发表时间:
2021
期刊:
2022 American Control Conference (ACC)
影响因子:
--
通讯作者:
W. Kang
W. Kang
中科院分区:
--
文献类型:
--
作者:
Tenavi Nakamura;Q. Gong;W. Kang

文献摘要

参考文献

被引文献

相似文献

最近的研究表明,监督学习可以成为设计高维非线性动态系统最优反馈控制器的有效工具。但这些神经网络(NN)控制器的行为仍然没有得到很好的理解。在本文中,我们使用数值模拟来证明,典型的测试精度指标不能有效地捕捉一个神经网络控制器稳定系统的能力。特别是,一些具有高测试精度的NN可能无法稳定动态。为了解决这个问题,我们提出了两个NN架构,局部近似线性二次调节器(LQR)。数值模拟证实了我们的直觉,所提出的架构可靠地产生稳定的反馈控制器,而不牺牲最优性。
Recent research has shown that supervised learning can be an effective tool for designing optimal feedback controllers for high-dimensional nonlinear dynamic systems. But the behavior of these neural network (NN) controllers is still not well understood. In this paper we use numerical simulations to demonstrate that typical test accuracy metrics do not effectively capture the ability of an NN controller to stabilize a system. In particular, some NNs with high test accuracy can fail to stabilize the dynamics. To address this we propose two NN architectures which locally approximate a linear quadratic regulator (LQR). Numerical simulations confirm our intuition that the proposed architectures reliably produce stabilizing feedback controllers without sacrificing optimality.
使用状态相关 Riccati 方程的最优反馈定律的梯度增强监督学习
DOI: 10.1109/lcsys.2021.3086697
发表时间: 2022
影响因子: 3
作者:
Albi G
通讯作者: Albi G