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 controlle...
详细信息
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.
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 cond...
详细信息
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.
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 propo...
详细信息
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-timerecurrentlearning (RTRL) algorithm is superior to that of the DFRNN and RNN for the non-linear time-invariant and time-variant channels.
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 equalize...
详细信息
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.
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 dir...
详细信息
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-timerecurrentlearning (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.
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 distributio...
详细信息
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.
Williams and Zipser (1989) proposed two analogue learningalgorithms for fully recurrent networks. The first method is an exact gradient-following algorithm for problems where data consists of epochs. The second metho...
详细信息
Williams and Zipser (1989) proposed two analogue learningalgorithms 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-timerecurrentlearning (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 learningalgorithm 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.
作者:
T. ChovanT. CatfolisK. MeertUniversity 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 timerecurrent networks, which are inh...
详细信息
Neural network based control schemes are generally designed by implementing feedforward neural network models in standard control engineering structures. Introduction of discrete timerecurrent 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.
暂无评论