检索结果-内蒙古大学图书馆

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Wei, Qinglai Li, Benkai Song, Ruizhuo Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing Peoples R China

ISBN: (纸本)9781538627266

This paper concerns with a novel generalized policy iteration (GPI) algorithm with approximation errors. Approximation errors are explicitly considered in the GPI algorithm. The properties of the stable GPI algorithm with approximation errors are analyzed. The convergence of the developed algorithm is established to show that the iterative value function is convergent to a finite neighborhood of the optimal performance index function. Finally, numerical examples and comparisons are presented.

关键词： Adaptive critic designs adaptive dynamic programming approximate dynamic programming neuro-dynamic programming generalized policy iteration nonlinear systems optimal control neural networks reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data-Based Self-Learning Optimal Control for Continuous-Time Unknown Nonlinear Systems With Disturbance 28

Data-Based Self-Learning Optimal Control for Continuous-Time...

引用

28th Chinese Control and Decision Conference

作者： Wei, Qinglai Liu, Derong Song, Ruizhuo Yan, Pengfei Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing 100083 Peoples R China

ISBN: (纸本)9781467397148

In this paper, a new data-based self-learning control scheme is developed to solve infinite horizon optimal control problems for continuous-time nonlinear systems. The developed optimal control scheme can be implement without knowing the mathematical model of the system. According to the input-output data of the nonlinear systems, a recurrent neural network (RNN) is employed to reconstruct the dynamics of the nonlinear system. According to the RNN model of the system, a new two-person zero-sum adaptive dynamic programming (ADP) algorithm is developed to obtain the optimal control, where the reconstruction error and the system disturbance are considered the control input of the system. Single-layer neural networks are used to construct the critic and action networks, which are presented to approximate the performance index function and the control law, respectively. Finally, simulation results will show the effectiveness of the developed data-based ADP methods.

关键词： Adaptive critic designs Adaptive dynamic programming Approximate dynamic programming neuro-dynamic programming Recurrent neural network Data-based control Optimal control

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Sensor-Based Navigation with Neural Tracking Control of the Wheeled Mobile Robot

Fuzzy Sensor-Based Navigation with Neural Tracking Control o...

引用

13th International Conference on Artificial Intelligence and Soft Computing (ICAISC)

作者： Szuster, Marcin Hendzel, Zenon Burghardt, Andrzej Rzeszow Univ Technol Dept Appl Mech & Robot PL-35959 Rzeszow Poland

ISBN: (纸本)9783319071756;9783319071763

Navigation of the wheeled mobile robot in the unknown environment with simultaneous realisation of the generated trajectory, is one of the most challenging and up to date problems in the modern mobile robotics. In the article a new approach is presented to a collision-free trajectory generating for a wheeled mobile robot, realised in a form of the hierarchical control system with two layers. The first layer is a tracking control system, where the neuro-dynamic programming algorithm in the Dual Heuristic dynamic programming configuration was applied. The second layer is a trajectory generator where the Fuzzy Logic systems were used. The presented control system generates and realises trajectory of the wheeled mobile robot within the complex task of goal-seeking and obstacle avoiding. The proposed hierarchical control system works on-line, its performance was verified using the wheeled mobile robot Pioneer 2-DX.

关键词： neuro-dynamic programming Fuzzy System Mobile Robot Neural Networks Path Planning Sensor-Based Navigation

来源：评论

学校读者我要写书评

暂无评论

Design and experimental verification: Health indicator-based decentralized optimal fault-tolerant control for modular robot manipulators via adjustable event-triggered mechanism

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 243卷

作者： Pan, Qiang Ma, Bing An, Tianjiao Dong, Bo Zhu, Mingchao Li, Yuanchun Changchun Univ Technol Dept Control Sci & Engn Changchun 130012 Peoples R China Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China

In this paper, a novel health indicator-based decentralized event-triggered optimal fault-tolerant control method is proposed for modular robot manipulators (MRMs). First, the subsystem dynamic model is established by utilizing the joint torque feedback (JTF) technique. Second, the developed global controller consists of a model based robust compensator and a health indicator-based optimal fault-tolerant controller, to address the model uncertainties and guarantee the faulty system stable operation, respectively. Considering the actuator output capability, a health indicator-based two-level judgment condition switching threshold strategy is designed for emergency treatment of sudden failures. On the basis of the neuro-dynamic programming (NDP) algorithm, the improved value function, reflecting the unknown faults and the health status of actuator, is approximated online under the event-triggered critic-only neural network structure. By addressing the Hamilton-Jacobi- Bellman equation, the health indicator-based decentralized event-triggered optimal fault-tolerant control strategy can be obtained. Finally, the tracking error of closed-loop MRM system can be demonstrated uniformly ultimately bounded through the Lyapunov theory. Furthermore, the experimental results obtained from the MRMs platform demonstrate the effectiveness of the proposed control method.

关键词： Modular robot manipulators neuro-dynamic programming Health indicator Event-triggered mechanism Fault-tolerant control

来源：评论

学校读者我要写书评

暂无评论

A Nonlinear Finite-Time Robust Differential Game Guidance Law

引用

SENSORS 2022年第17期22卷 6650-6650页

作者： Xi, Axing Cai, Yuanli Xi An Jiao Tong Univ Sch Automat Sci & Engn Xian 710049 Peoples R China

In this paper, a robust differential game guidance law is proposed for the nonlinear zero-sum system with unknown dynamics and external disturbances. First, the continuous-time nonlinear zero-sum differential game problem is transformed into solving the nonlinear Hamilton-Jacobi-Isaacs equation, a time-varying cost function is developed to reflect the fixed terminal time, and the robust guidance law is developed to compensate for the external disturbance. Then, a novel neural network identifier is designed to approximate the unknown nonlinear dynamics with online weight tuning. Subsequently, an online critic neural network approximator is presented to estimate the cost function, and time-varying activation functions are considered to deal with the fixed final time problem. An adaptive weight tuning law is given, where two additional terms are added to ensure the stability of the closed-loop nonlinear system and so as to meet the terminal cost at a fixed final time. Furthermore, the uniform ultimate boundedness of the closed-loop system and the critic neural network weights estimation error are proven based upon the Lyapunov approach. Finally, some simulation results are presented to demonstrate the effectiveness of the proposed robust differential game guidance law for nonlinear interception.

关键词： guidance law neuro-dynamic programming differential game nonlinear system

来源：评论

学校读者我要写书评

暂无评论

dynamic compensator-based near-optimal control for unknown nonaffine systems via integral reinforcement learning

引用

neuroCOMPUTING 2024年 564卷

作者： Lin, Jinquan Zhao, Bo Liu, Derong Wang, Yonghua Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China Beijing Normal Univ Sch Syst Sci Beijing 100875 Peoples R China Southern Univ Sci & Technol Sch Syst Design & Intelligent Mfg Shenzhen 518055 Peoples R China Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA

In this paper, a dynamic compensator-based near-optimal control approach for unknown nonaffine nonlinear systems is developed by using integral reinforcement learning. Since system dynamics is unknown, it is difficult to obtain the optimal control policy via neuro-dynamic programming. To address this problem, a general dynamic compensator is introduced as the virtual control input to augment the unknown nonaffine nonlinear system as a partially unknown affine system. For the augmented system, a novel quadratic value function is designed with the system states, the actual control input and the virtual control input. The optimal control of the augmented system can be regarded as the near-optimal control for the original system since the novel optimal value function is an upper bound of the original optimal value function. In order to avoid the identification of system dynamics, the integral reinforcement learning framework is utilized to derive the optimal control based on the solution of Hamilton-Jacobi-Bellman equation via the critic-only structure. Meanwhile, the weight learning rule of the critic neural network is presented with the experience replay technique to relax the persistence of excitation condition. Moreover, the uniform ultimate boundedness of weight estimation errors and the stability of the closed-loop system are guaranteed by using the Lyapunov's direct method. Finally, simulation results of two examples demonstrate the effectiveness of the developed dynamic compensator-based near-optimal control method.

关键词： neuro-dynamic programming Adaptive dynamic programming Reinforcement learning Optimal control Neural networks dynamic compensator

来源：评论

学校读者我要写书评

暂无评论

REINFORCEMENT LEARNING USING QUANTUM BOLTZMANN MACHINES

引用

QUANTUM INFORMATION & COMPUTATION 2018年第1-2期18卷 51-74页

作者： Crawford, Daniel Levit, Anna Ghadermarzy, Navid Oberoi, Jaspreet S. Ronaghe, Pooya 1QB Informat Technol 1QBit Vancouver BC Canada Univ British Columbia Dept Math Vancouver BC Canada Simon Fraser Univ Sch Engn Sci Burnaby BC Canada Univ Waterloo Inst Quantum Comp Waterloo ON Canada Univ Waterloo Dept Phys & Astron Waterloo ON Canada

We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.

关键词： Reinforcement learning Machine learning neuro-dynamic programming Markov decision process Quantum Monte Carlo simulation Simulated quantum annealing Restricted Boltzmann machine Deep Boltzmann machine General Boltzmann machine Quantum Boltzmann machine

来源：评论

学校读者我要写书评

暂无评论

SIMULATION-BASED OPTIMIZATION FOR NONLINEAR OPTIMAL CONTROL

引用

IFAC Proceedings Volumes 2002年第1期35卷 387-392页

作者： Niket S. Kaisare Jong Min Lee Jay H. Lee School of Chemical Engineering Georgia Institute of Technology Atlanta GA 30332 U.S.A.

Optimal control of systems with complex nonlinear behaviour such as steady state multiplicity results in a nonlinear optimization problem that needs to be solved online at each sample time. We present an approach based on simulation, function approximation and evolutionary improvement aimed towards simplifying online optimization. Closed loop data from a suboptimal control law, such as MPC based on successive linearization, is used to obtain an approximation of the 'cost-to-go' function, which is subsequently improved through iterations of the Bellman equation. Using this offline-computed cost approximation, an infinite horizon problem is converted to an equivalent single stage problem — substantially reducing the computational burden. This approach is tested on continuous culture of microbes growing on a nutrient medium containing two substrates that exhibits steady state multiplicity. Extrapolation of the cost-to-go function approximator can lead to deterioration of online performance. Some remedies to prevent such problems caused by extrapolation are proposed.

关键词： Optimal Control Continuous Bioreactor Multiple Steady States neuro-dynamic programming Cybernetic Modeling Klebsiella oxytoca

来源：评论

学校读者我要写书评

暂无评论

Event-triggered-based Decentralized Optimal Control of Modular Robot Manipulators Using RNN Identifier

引用

JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS 2022年第3期106卷 55-55页

作者： Pan, Qiang Li, Yuanchun Ma, Bing An, Tianjiao Zhou, Fan Changchun Univ Technol Dept Control Sci & Engn Changchun 130021 Peoples R China

In this paper, an event-triggered-based decentralized tracking control method is proposed for modular robot manipulators (MRMs) using a recurrent neural network (RNN) and neuro-dynamic programming (NDP). The joint torque feedback (JTF) technique is introduced to model the MRM subsystems. The cost function of each subsystem consists of a tracking error fusion function and a term summarizing the RNN identifier errors. The event-triggered Hamiltonian-Jacobi-Bellman (ETHJB) equation is solved by constructing a critic neural network using NDP, and a decentralized optimal tracking control policy under the event-triggered framework can be obtained. The closed-loop MRM system is shown to be uniformly ultimately bounded under the Lyapunov stability theorem. Finally, the experimental results verify that the proposed control method is superior to the time-triggered optimal control policy and the observer-critic-based event-triggered optimal control policy proposed in the previous work of the author.

关键词： Modular robot manipulators Joint torque feedback technique neuro-dynamic programming Event-triggered mechanism Decentralized tracking control

来源：评论

学校读者我要写书评

暂无评论

A hydrographical network optimization under flood conditions

引用

IFAC Proceedings Volumes 2009年第19期42卷 367-372页

作者： Majdi Argoubi Ismahène Hadj Khalifa Abdelkader El Kamel LAGIS Ecole Centrale de Lille Cité scientifique BP48 Villeneuve d'Ascq F59650 France

Abstract A decision support system (DSS) is developed for integrated, real-time flood control in a multi-reservoir system. The DSS integrates a geographic information system (GIS) with an optimization module, and a graphical dialog interface to allow an effective use by system operators. A neuro-dynamic programming technique (NDP), which overcomes numerous limitations of stochastic dynamic programming (SDP), is introduced to determine the optimal release policy under flood conditions. Results obtained in a real-world case study are finally presented.

关键词： Multi-reservoir system neuro-dynamic programming GIS DSS

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：