检索结果-内蒙古大学图书馆

Reinforcement-Learning-Based Robust controller Design for Continuous-Time Uncertain Nonlinear systems Subject to Input Constraints

引用

IEEE TRANSACTIONS ON CYBERNETICS 2015年第7期45卷 1372-1385页

作者： Liu, Derong Yang, Xiong Wang, Ding Wei, Qinglai Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

The design of stabilizing controller for uncertain nonlinear systems with control constraints is a challenging problem. The constrained-input coupled with the inability to identify accurately the uncertainties motivates the design of stabilizing controller based on reinforcement-learning (RL) methods. In this paper, a novel RL-based robust adaptive control algorithm is developed for a class of continuous-time uncertain nonlinear systems subject to input constraints. The robust control problem is converted to the constrained optimal control problem with appropriately selecting value functions for the nominal system. Distinct from typical action-critic dual networks employed in RL, only one critic neural network (NN) is constructed to derive the approximate optimal control. Meanwhile, unlike initial stabilizing control often indispensable in RL, there is no special requirement imposed on the initial control. By utilizing Lyapunov's direct method, the closed-loop optimal control system and the estimated weights of the critic NN are proved to be uniformly ultimately bounded. In addition, the derived approximate optimal control is verified to guarantee the uncertain nonlinear system to be stable in the sense of uniform ultimate boundedness. Two simulation examples are provided to illustrate the effectiveness and applicability of the present approach.

关键词： Approximate dynamic programming (ADP) neural networks (NNs) neuro-dynamic programming nonlinear systems optimal control reinforcement learning (RL) robust control

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Dynamic Modeling for a Swimming Robotic Fish

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2016年第9期63卷 5632-5640页

作者： Yu, Junzhi Yuan, Jun Wu, Zhengxing Tan, Min Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This paper proposes a data-driven dynamic modeling method for multijoint robotic fish with irregular geometric profiles and numerous heterogeneous hydrodynamic parameters. The method is composed of two main components: dynamic modeling and hydrodynamic parameter identification. In dynamic modeling, fluid forces exerted on the robotic fish are analyzed by the Morrison equation and the strip method. A dynamic model with an explicit formulation is derived, in which all terms involved in the dynamic analysis are converted to the coordinate system attached to the head. Further, the parameter identification technique is integrated into dynamic modeling, which reshapes it with data-driven feature and thereby makes it be competent to model swimming robots with complex geometric profiles and numerous heterogeneous hydrodynamic parameters. Experimental data of the swimming robotic fish are collected to identify the parameters directly. The obtained dynamic model is validated by data captured under extensive motion modes like forward swimming, varying velocity, and turning. Comparisons of simulated and experimental results demonstrate the effectiveness of the method.

关键词： Hydrodynamic analysis modeling and control parameter identification robotic fish

来源：评论

学校读者我要写书评

暂无评论

Online approximate solution of HJI equation for unknown constrained-input nonlinear continuous-time systems

引用

INFORMATION SCIENCES 2016年 328卷 435-454页

作者： Yang, Xiong Liu, Derong Ma, Hongwen Xu, Yancai Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This paper is concerned with the approximate solution of Hamilton-Jacobi-Isaacs (HJI) equation for constrained-input nonlinear continuous-time systems with unknown dynamics. We develop a novel online adaptive dynamic programming-based algorithm to learn the solution of the HJI equation. The present algorithm is implemented via an identifier-critic architecture, which consists of two neural networks (NNs): an identifier NN is applied to estimate the unknown system dynamics and a critic NN is constructed to obtain the approximate solution of the HJI equation. An advantage of the proposed architecture is that the identifier NN and the critic NN are tuned simultaneously. With introducing two additional terms, namely, the stabilizing term and the robustifying term to update the critic NN, the initial stabilizing control is no longer required. Meanwhile, the developed critic tuning rule not only ensures convergence of the critic to the optimal saddle point but also guarantees stability of the closed-loop system. Moreover, the uniform ultimate boundedness of the weights of the identifier NN and the critic NN are proved by using Lyapunov's direct method. Finally, to illustrate the effectiveness and applicability of the developed approach, two simulation examples are provided. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Adaptive dynamic programming Hamilton-Jacobi-Isaacs equation Input constraint Neural network Optimal control Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Distributed exponential finite-time coordination of multi-agent systems: containment control and consensus

引用

INTERNATIONAL JOURNAL OF control 2015年第2期88卷 237-247页

作者： Liu, Huiyang Cheng, Long Tan, Min Hou, Zengguang Wang, Yunpeng Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China

In this paper, exponential finite-time coordination problems of multi-agent systems are investigated, including containment control and consensus. The theoretical basis is that a class of nonlinear systems has favourable finite-time convergence characteristic. For the objective of containment control, the proposed protocol ensures that the boundary agents in the same strong component exponentially reach a consensus and the internal agents exponentially converge to the convex hull spanned by the boundary agents in a finite time. For the objective of consensus, a pinning control strategy is designed for a fraction of agents such that all the agents exponentially reach a consensus with the leader in a finite time. The distinguished features of this paper lie in the following two points: (1) a smaller settling time of the Lyapunov function is obtained, which manifests in a faster convergence rate than the traditional one and (2) the weakly connected topology considered in this paper is more general than the ones (a spanning tree, a spanning forest, and so on) in other coordination problems. All the results are illustrated by some simulations.

关键词： consensus containment control exponential finite-time pinning control multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Deep sparse representation-based mid-level visual elements discovery in fine-grained classification

引用

SOFT COMPUTING 2019年第18期23卷 8711-8722页

作者： Lv, Le Zhao, Dongbin Shao, Kun Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this paper, we propose a new mid-level visual elements discovery method and apply it to the fine-grained classification. We present the duality between image patches and features extracted by the convolutional winner-take-all autoencoder (CONV-WTA-AE). The sparsity constraints used by CONV-WTA-AE make a group of objects sharing the same feature components. Hence, the image patches could be clustered by their sharing feature components and the feature components can be clustered by their co-occurrence in the image patches. We propose formulating the mid-level visual elements mining as a bipartite graph partitioning problem. The spectral partitioning algorithm is employed to co-cluster image patches and feature components. The CONV-WTA-AE is an unsupervised feature learning method. Hence, it avoids using expensive annotations. Our experiments demonstrate that the spectral partitioning method is very efficient but only the confident instances in a cluster are well discriminated. The similarity metric used by this algorithm is not accurate enough. Hence, we propose training a group of linear support vector machine (SVM) to refine the clustering results. These SVMs will be trained on the initial confident instances and provide a better discriminative similarity. Then we can re-assign instances to each clusters. To avoid overfitting, this process is iterated on many data subsets. We conduct a series of experiments on the MNIST dataset to verify our algorithm. The experimental results show that our method can discover meaningful image patch clusters. In the fine-grained classification task, visual elements are input into an ensemble of convolutional neural networks. The experiments on the CompCars dataset illustrate that our method can achieve the state-of-the-art performance.

关键词： Mid-level visual elements discovery Fine-grained classification Winner-take-all autoencoder Bipartite graph spectral partitioning

来源：评论

学校读者我要写书评

暂无评论

Neural-network-observer-based optimal control for unknown nonlinear systems using adaptive dynamic programming

引用

INTERNATIONAL JOURNAL OF control 2013年第9期86卷 1554-1566页

作者： Liu, Derong Huang, Yuzhu Wang, Ding Wei, Qinglai Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this paper, an observer-based optimal control scheme is developed for unknown nonlinear systems using adaptive dynamic programming (ADP) algorithm. First, a neural-network (NN) observer is designed to estimate system states. Then, based on the observed states, a neuro-controller is constructed via ADP method to obtain the optimal control. In this design, two NN structures are used: a three-layer NN is used to construct the observer which can be applied to systems with higher degrees of nonlinearity and without a priori knowledge of system dynamics, and a critic NN is employed to approximate the value function. The optimal control law is computed using the critic NN and the observer NN. Uniform ultimate boundedness of the closed-loop system is guaranteed. The actor, critic, and observer structures are all implemented in real-time, continuously and simultaneously. Finally, simulation results are presented to demonstrate the effectiveness of the proposed control scheme.

关键词： nonlinear observer adaptive dynamic programming neural network uniformly ultimately bounded nonlinear system

来源：评论

学校读者我要写书评

暂无评论

An automated weld seam tracking system for thick plate using cross mark structured light

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2016年第9-12期87卷 3589-3603页

作者： Kiddee, Prasarn Fang, Zaojun Tan, Min Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This paper presents a weld seam tracking system using cross mark structured light. The hardware of the proposed system consists of a two degrees of freedom (DOF) welding robot, a camera with cross mark structured light, and two computers. The system has two parts namely visual sensing and motion control. In the visual sensing part, the cross mark of the structured light is utilized to set a region of interest (ROI). In the ROI, an adapted line fitting algorithm is employed to estimate the lines. Then, intersections of the lines are computed and used as the pin points for templates creating. During the matching process, a modified template matching is used to detect the edges of V-groove weld seam. By using this technique, a huge computational cost in image processing can be reduced, and therefore the tracking can be made in real time. The position based visual servoing with proportional-derivative(PD) and velocity feedback controller is designed for seam tracking. The experimental results show that the proposed method performs the real-time tracking efficiently with sufficient accuracy.

关键词： Structured light Self-creating template Modified template matching Seam tracking control

来源：评论

学校读者我要写书评

暂无评论

Neuro-optimal tracking control for a class of discrete-time nonlinear systems via generalized value iteration adaptive dynamic programming approach

引用

SOFT COMPUTING 2016年第2期20卷 697-706页

作者： Wei, Qinglai Liu, Derong Xu, Yancai Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this paper, a novel value iteration adaptive dynamic programming (ADP) algorithm, called "generalized value iteration ADP" algorithm, is developed to solve infinite horizon optimal tracking control problems for a class of discrete-time nonlinear systems. The developed generalized value iteration ADP algorithm permits an arbitrary positive semi-definite function to initialize it, which overcomes the disadvantage of traditional value iteration algorithms. Convergence property is developed to guarantee that the iterative performance index function will converge to the optimum. Neural networks are used to approximate the iterative performance index function and compute the iterative control policy, respectively, to implement the iterative ADP algorithm. Finally, a simulation example is given to illustrate the performance of the developed algorithm.

关键词： Adaptive dynamic programming Approximate dynamic programming Adaptive critic designs Optimal control Neural networks Nonlinear systems Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Survey of single-target visual tracking methods based on online learning

引用

IET COMPUTER VISION 2014年第5期8卷 419-428页

作者： Liu, Qi Zhao, Xiaoguang Hou, Zengguang Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100080 Peoples R China

Visual tracking is a popular and challenging topic in computer vision and robotics. Owing to changes in the appearance of the target and complicated variations that may occur in various scenes, online learning scheme is necessary for advanced visual tracking framework to adopt. This paper briefly introduces the challenges and applications of visual tracking and focuses on discussing the state-of-the-art online-learning-based tracking methods by category. We provide detail descriptions of representative methods in each category, and examine their pros and cons. Moreover, several most representative algorithms are implemented to provide quantitative reference. At last, we outline several trends for future visual tracking research.

关键词： learning (artificial intelligence) robot vision object tracking single-target visual tracking method computer vision robotics target appearance online learning scheme advanced visual tracking framework online-learning-based tracking method

来源：评论

学校读者我要写书评

暂无评论

Decentralized Stabilization for a Class of Continuous-Time Nonlinear Interconnected systems Using Online Learning Optimal control Approach

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2014年第2期25卷 418-428页

作者： Liu, Derong Wang, Ding Li, Hongliang Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this paper, using a neural-network-based online learning optimal control approach, a novel decentralized control strategy is developed to stabilize a class of continuous-time nonlinear interconnected large-scale systems. First, optimal controllers of the isolated subsystems are designed with cost functions reflecting the bounds of interconnections. Then, it is proven that the decentralized control strategy of the overall system can be established by adding appropriate feedback gains to the optimal control policies of the isolated subsystems. Next, an online policy iteration algorithm is presented to solve the Hamilton-Jacobi-Bellman equations related to the optimal control problem. Through constructing a set of critic neural networks, the cost functions can be obtained approximately, followed by the control policies. Furthermore, the dynamics of the estimation errors of the critic networks are verified to be uniformly and ultimately bounded. Finally, a simulation example is provided to illustrate the effectiveness of the present decentralized control scheme.

关键词： Adaptive dynamic programming decentralized control large-scale systems neural networks nonlinear interconnected systems optimal control policy iteration reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：