2023

最新文章

• Designing Distributed Impulsive Controller for Networked Singularly Perturbed Systems AI翻译
  作者：He, Wangli; Liang, Kun; Qian, Feng; Chen, Guanrong
  作者单位：East China University of Science & Technology; City University of Hong Kong
  摘要：This article develops a novel synthesis approach for the synchronization of a network of singularly perturbed systems (SPSs) with a small singular perturbation parameter e via distributed impulsive control. First, a decoupling method in the setting of directed networks is employed to decompose networked SPSs related to complex eigenvalues of the Laplacian matrix. Then, based on an improved piecewise continuous Lyapunov function, an e-dependent synchronization criterion is established. The rela...
• Deep Filtering With Adaptive Learning Rates AI翻译
  作者：Qian, Hongjiang; Yin, George; Zhang, Qing
  作者单位：University of Connecticut; University System of Georgia; University of Georgia
  摘要：This article develops a new deep learning framework for general nonlinear filtering. Our main contribution is to present a computationally feasible procedure. The proposed algorithms have the capability of dealing with challenging (infinitely dimensional) filtering problems involving diffusions with randomly-varying switching. First, we convert it to a problem in a finite-dimensional setting by approximating the optimal weights of a neural network. Then, we construct a stochastic gradient-type...
• Hamiltonian Deep Neural Networks Guaranteeing Nonvanishing Gradients by Design AI翻译
  作者：Galimberti, Clara Lucia; Furieri, Luca; Xu, Liang; Ferrari-Trecate, Giancarlo
  作者单位：Swiss Federal Institutes of Technology Domain; Ecole Polytechnique Federale de Lausanne; Shanghai University
  摘要：Deep neural networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretization of continuous-time Hamiltonian systems and include several existing DNN architectures based on ordinary differential equations. Our main result is that a broad set of H-DNNs ensures nonvanishing gradients by design for an arbitrary netw...
• PAC Reinforcement Learning Algorithm for General-Sum Markov Games AI翻译
  作者：Zehfroosh, Ashkan; Tanner, Herbert G.
  作者单位：University of Delaware
  摘要：This article presents a theoretical framework for probably approximately correct (PAC) multi-agent reinforcement learning (MARL) algorithms for Markov games. Using the idea of delayed Q-learning, this article extends the well-known Nash Q-learning algorithm to build a new PAC MARL algorithm for general-sum Markov games. In addition to guiding the design of a provably PAC MARL algorithm, the framework enables checking whether an arbitrary MARL algorithm is PAC. Comparative numerical results dem...
• Robust Output Regulation and Reinforcement Learning-Based Output Tracking Design for Unknown Linear Discrete-Time Systems AI翻译
  作者：Chen, Ci; Xie, Lihua; Jiang, Yi; Xie, Kan; Xie, Shengli
  作者单位：Guangdong University of Technology; Nanyang Technological University; City University of Hong Kong; Guangdong University of Technology
  摘要：In this article, we investigate the optimal output tracking problem for linear discrete-time systems with unknown dynamics using reinforcement learning (RL) and robust output regulation theory. This output tracking problem only allows to utilize the outputs of the reference system and the controlled system, rather than their states, and differs from most existing works that depend on the state of the system. The optimal tracking problem is formulated into a linear quadratic regulation problem ...
• Distributed and Performance Guaranteed Robust Control for Uncertain MIMO Nonlinear Systems With Controllability Relaxation AI翻译
  作者：Huang, Xiucai; Song, Yongduan
  作者单位：Chongqing University
  摘要：In this article, we investigate the distributed output tracking problem for networked uncertain nonlinear multi-inputs-multi-outputs (MIMO) strict-feedback systems with intermittent actuator faults under a directed protocol. By embedding some user-designed performance functions into a backstepping-like design procedure, a distributed robust control scheme is developed that exhibits several salient features: 1) relaxing the system controllability conditions by inserting some differentiable comp...
• Disturbance Prediction-Based Adaptive Event-Triggered Model Predictive Control for Perturbed Nonlinear Systems AI翻译
  作者：Li, Pengfei; Kang, Yu; Wang, Tao; Zhao, Yun-Bo
  作者单位：Chinese Academy of Sciences; University of Science & Technology of China, CAS
  摘要：A disturbance prediction-based adaptive event-triggered model predictive control scheme is proposed for nonlinear systems in the presence of slowly varying disturbance. The optimal control problem in the model predictive control scheme is formulated by taking advantage of a proposed central path-based disturbance prediction approach, and the event-triggered mechanism is designed to be adaptive to the triggering interval. As a result, the proposed scheme improves the state prediction precision ...
• Self-Triggered Stabilization of Discrete-Time Linear Systems With Quantized State Measurements AI翻译
  作者：Wakaiki, Masashi
  作者单位：Kobe University
  摘要：We study the self-triggered stabilization of discrete-time linear systems with quantized state measurements. In the networked control system we consider, sensors may be spatially distributed and be connected to a self-triggering mechanism through finite data-rate channels. Each sensor independently encodes its measurements and sends them to the self-triggering mechanism. The self-triggering mechanism integrates quantized measurement data and then computes sampling times. Assuming that the clos...
• Integral Sliding Mode Control for a Kind of Impulsive Uncertain Reaction-Diffusion Systems AI翻译
  作者：Kao, Yonggui; Ma, Suriguga; Xia, Hongwei; Wang, Changhong; Liu, Yunlong
  作者单位：Harbin Institute of Technology; Inner Mongolia Normal University; Qufu Normal University; Harbin Institute of Technology
  摘要：This article discusses the integral sliding mode control problem for a kind of periodically impulsive uncertain reaction-diffusion systems (IURDSs). A novel integral sliding surface containing impulsive effects and reaction-diffusion terms is constructed, such that the impulsive effects for IURDSs can be removed. A novel sliding mode controller with impulsive effects is designed to ensure the reachability of the specified sliding surface in a finite time interval. By means of linear matrix ine...
• Adaptive Optimization With Decaying Periodic Dither Signals AI翻译
  作者：Xie, Siyu; Wang, Le Yi
  作者单位：Wayne State University; University of Electronic Science & Technology of China
  摘要：Real-time optimization in cyber-physical network systems with unknown system parameters must integrate optimization and parameter estimation, leading to adaptive optimization problems. Such problems encounter fundamental conflict between optimization and system identifiability. Recently, a new method of employing a stochastic or periodic dither has been introduced to resolve this conflict and achieve convergence toward optimal solutions. However, adding a dither introduces persistent disturban...