检索结果-内蒙古大学图书馆

A recurrent neural network for variable admittance control in human-robot cooperation: simultaneously and online adjustment of the virtual damping and Inertia parameters

引用

INTERNATIONAL JOURNAL OF INTELLIGENT ROBOTICS AND APPLICATIONS 2020年第4期4卷 441-464页

作者： Sharkawy, Abdel-Nasser Koustoumpardis, Panagiotis N. Aspragathos, Nikos South Valley Univ Mech Engn Dept Fac Engn Qena 83523 Egypt Univ Patras Dept Mech Engn & Aeronaut Rion 26504 Greece

In this manuscript, a recurrent neural network is proposed for variable admittance control in human-robot cooperation tasks. The virtual damping and the virtual inertia of the designed robot's admittance controller are adjusted online and simultaneously. A Jordan recurrent neural network is designed and trained for this purpose. The network is indirectly trained using the real-time recurrent learning algorithm and based on the velocity error between the reference velocity of the minimum jerk trajectory model and the actual velocity of the robot. The performance of the proposed variable admittance controller is presented in terms of the human required effort, the task completion time, the achieved accuracy at the target, and the oscillations during the movement. Its generalization ability is evaluated experimentally by conducting cooperative tasks along numerous straight-line segments using the KUKA LWR robot and by ten subjects. Finally, a comparison with previous developed variable admittance controllers, where only the variable damping or only the virtual inertia is adjusted, is presented.

关键词： Human-robot cooperation Variable admittance controller Jordan recurrent neural network real-time recurrent learning algorithm Minimum jerk trajectory

来源：评论

学校读者我要写书评

暂无评论

time-dependent series variance learning with recurrent mixture density networks

引用

NEUROCOMPUTING 2013年 122卷 501-512页

作者： Nikolaev, Nikolay Tino, Peter Smirnov, Evgueni Univ London Goldsmiths Coll Dept Comp London SE14 6NW England Univ Birmingham Sch Comp Sci Birmingham B15 2TT W Midlands England Maastricht Univ Fac Humanities & Sci Dept Knowledge Engn NL-6200 MD Maastricht Netherlands

This paper presents an improved nonlinear mixture density approach to modeling the time-dependent variance in time series. First, we elaborate a recurrent mixture density network for explicit modeling of the time conditional mixing coefficients, as well as the means and variances of its Gaussian mixture components. Second, we derive training equations with which all the network weights are inferred in the maximum likelihood framework. Crucially, we calculate temporal derivatives through time for dynamic estimation of the variance network parameters. Experimental results show that, when compared with a traditional linear heteroskedastic model, as well as with the nonlinear mixture density network trained with static derivatives, our dynamic recurrent network converges to more accurate results with better statistical characteristics and economic performance. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Mixture density neural networks GARCH models real-time recurrent learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Pipelined functional link artificial recurrent neural network with the decision feedback structure for nonlinear channel equalization

引用

INFORMATION SCIENCES 2011年第17期181卷 3677-3692页

作者： Zhao, Haiquan Zeng, Xiangping Zhang, Jiashu Li, Tianrui Liu, Yangguang Ruan, Da SW Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China SW Jiaotong Univ Sch Informat Sci & Technol Chengdu 610031 Peoples R China Chengdu Univ Informat Technol Ctr Elect Lab Chengdu 610255 Peoples R China Zhejiang Univ Ningbo Inst Technol Ningbo 315100 Peoples R China Belgian Nucl Res Ctr SCK CEN B-2400 Mol Belgium

This paper presents a computationally efficient nonlinear adaptive filter by a pipelined functional link artificial decision feedback recurrent neural network (PFLADFRNN) for the design of a nonlinear channel equalizer. It aims to reduce computational burden and improve nonlinear processing capabilities of the functional link artificial recurrent neural network (FLANN). The proposed equalizer consists of several simple small-scale functional link artificial decision feedback recurrent neural network (FLADFRNN) modules with less computational complexity. Since it is a module nesting architecture comprising a number of modules that are interconnected in a chained form, its performance can be further improved. Moreover, the equalizer with a decision feedback recurrent structure overcomes the unstableness thanks to its nature of infinite impulse response structure. Finally, the performance of the PFLADFRNN modules is evaluated by a modified real-time recurrent learning algorithm via extensive simulations for different linear and nonlinear channel models in digital communication systems. The comparisons of multilayer perceptron. FLANN and reduced decision feedback FLANN equalizers have clearly indicated the convergence rate, bit error rate, steady-state error and computational complexity, respectively, for nonlinear channel equalization. (C) 2011 Elsevier Inc. All rights reserved.

关键词： Functional link artificial neural network real-time recurrent learning algorithm Pipelined architecture Decision feedback structure Nonlinear channel

来源：评论

学校读者我要写书评

暂无评论

Equalisation of non-linear time-varying channels using a pipelined decision feedback recurrent neural network filter in wireless communication systems

引用

IET COMMUNICATIONS 2011年第3期5卷 381-395页

作者： Zhao, H. Q. Zeng, X. P. Zhang, J. S. Li, T. R. SW Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China SW Jiaotong Univ Sch Informat Sci & Technol Chengdu 610031 Peoples R China Chengdu Univ Informat Technol Ctr Elect Lab Chengdu 610255 Peoples R China

To combat the linear and non-linear distortions for time-invariant and time-variant channels, a novel adaptive joint process equaliser based on a pipelined decision feedback recurrent neural network (JPDFRNN) is proposed in this paper. The JPDFRNN consists of a number of simple small-scale decision feedback recurrent neural network (DFRNN) modules and a linear combiner. The cascaded DFRNN provides pre-processing for the linear combiner. Moreover, each DFRNN can provide a local interpolation for M sample points;the final linear combiner presents a global interpolation with good localisation properties. Furthermore, since those modules of non-linear subsection can be performed simultaneously in a pipelined parallelism fashion, this would result in a significant improvement in the total computational efficiency. Simulation results show that the performance of the JPDFRNN using the modified real-time recurrent learning (RTRL) algorithm is superior to that of the DFRNN and RNN for the non-linear time-invariant and time-variant channels.

关键词： recurrent neural nets pipelined decision feedback recurrent neural network filter linear combiner wireless communication systems nonlinear time-varying channels Radio links and equipment Communication channel equalisation and identification learning (artificial intelligence) wireless channels adaptive equalisers time-varying channels adaptive joint process equaliser decision feedback equalisers real-time recurrent learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive non-linear filter using a modular polynomial perceptron

引用

IET SIGNAL PROCESSING 2010年第6期4卷 640-649页

作者： Zhao, H. Q. Zeng, X. P. Zhang, J. S. Liu, Y. G. Li, T. R. SW Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China SW Jiaotong Univ Sch Informat Sci & Technol Chengdu 610031 Peoples R China Zhejiang Univ Ningbo Inst Technol Ningbo 315100 Zhejiang Peoples R China

This study presents a joint adaptive non-linear filter with pipelined second-order polynomial perceptron (PSOVNN) to reduce the computational complexity and improve the non-linear processing capability of adaptive direct-form second-order Volterra (SOV) filter. The PSOVNN is a nesting modular structure comprising a number of modules that are interconnected in a chained form. Each module is implemented by a small-scale direct-form SOV neural network (SOVNN). These cascaded modules can perform a non-linear mapping from the input space to an intermediate space. In addition, the linear filter of the complete PSOVNN performs a linear mapping from the intermediate space to the output space. A modified real-time recurrent learning (RTRL) algorithm is developed, and its performance is evaluated by a series of simulation experiments. Computer simulations indicate that the proposed non-linear filter exhibits better performance over the direct-form SOV filter with less computational complexity.

关键词： nonlinear filters adaptive nonlinear filter Filtering methods in signal processing polynomials Signal processing theory pipelined second-order polynomial perceptron computational complexity adaptive filters linear mapping Algebra second-order Volterra filter SOV neural network real-time recurrent learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of a recurrent neural network to space diversity in SDMA and CDMA mobile communication systems

引用

NEURAL COMPUTING & APPLICATIONS 2001年第2期10卷 136-147页

作者： Benson, M Carrasco, RA Staffordshire Univ Sch Engn & Adv Technol Stafford Staffs England

Linear and non-linear adaptive algorithms are investigated for Space Division Multiple Access (SDMA). SDMA is one of the emerging techniques for multiple access of users in mobile radio, which uses spatial distribution of users for their differentiation. The performance of the linens Square Root Kalman (SRK) algorithm for SDMA is compared to that of the non-linear recurrent Neural Network (RNN) technique. The proposed SDMA-RNN technique is evaluated over Rician fading channels. and it shows improved Bit Error Rate (BER) performance e in comparison with the linear SRK-based technique. The performance of SDMA-RNN is also compared with that of Code Division Multiple Acc ess (CDMA) systems, showing that it could he used as a viable alternative scheme for multiple access of users. Finally, a Hybrid CDMA-SDMA system is proposed combining: CDMA and SDMA-RNN systems. Hybrid CDMA-SDMA exhibits a very good potential for increase in the capacity and the performance of mobile communications systems.

关键词： adaptive space diversity combining Code Division Multiple Access (CDMA) real-time recurrent learning algorithm recurrent neural network Space Division Multiple Access (SDMA)

来源：评论

学校读者我要写书评

暂无评论

A METHOD FOR IMPROVING THE real-time recurrent learning algorithm

引用

NEURAL NETWORKS 1993年第6期6卷 807-821页

作者： CATFOLIS, T Katholieke Universiteit Leuven Belgium

Williams and Zipser (1989) proposed two analogue learning algorithms for fully recurrent networks. The first method is an exact gradient-following algorithm for problems where data consists of epochs. The second method, called the real-time recurrent learning (RTRL) algorithm, uses data described by a temporal stream of inputs and outputs, without time marks or epochs. In this paper we describe a new implementation of this RTRL algorithm. This improved implementation makes it possible to increase the performance of the learning algorithm during the training phase by using some a priori knowledge about the temporal necessities of the problem. The reduction of the computational expense of the training enables the use of this algorithm for more complex problems. Some simulations of a process control task demonstrate the properties of this algorithm.

关键词： TEMPORAL PATTERN RECOGNITION TEMPORAL DATA PROCESSING DYNAMIC NEURAL NETWORKS real-time recurrent learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Process Control using recurrent Neural Networks

引用

IFAC Proceedings Volumes 1994年第10期27卷 135-140页

作者： T. Chovan T. Catfolis K. Meert University of Veszprem Department of Chemical Engineering Cybernetics Egvetem utca 10. PO. Box 158. H-8201 Veszprem Hungary K.U. Leuven Department of Chemical Engineering. Expert Systems Applications Development Group de Croylaan 46. B-3001 Heverlee Belgium

Neural network based control schemes are generally designed by implementing feedforward neural network models in standard control engineering structures. Introduction of discrete time recurrent networks, which are inherently dynamic systems, into those schemes can simplify the design of neural controllers. In this paper we describe the concept of applying recurrent networks trained with the real-time recurrent learning algorithm in the indirect adaptive control schemes. A combined network consisting of the control network and the model network is constructed to allow the simple use of the real-time recurrent learning algorithm, To demonstrate the feasability of the method two simulation examples are presented.

关键词： Process control Neural nets Control system design Artificial intelligence real-time recurrent learning algorithm

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：