Neuro-fuzzy position control of demining tele-operation system based on RNN modeling

The paper considers the neuro-fuzzy position control of multi-finger robot hand in tele-operation system—an active master–slave hand system (MSHS) for demining. Recently, fuzzy control systems utilizing artificial intelligent techniques are also being actively investigated in robotic area. Neural network with their powerful learning capability are being sought as the basis for many adaptive control systems where on-line adaptation can be implemented. Fuzzy logic on the other hand has been proved to be rather popular in many control system applications providing a rule-base like structure. In this paper, the design and optimization process of fuzzy position controller is supported by learning techniques derived from neural network where a radial basis function (RBF) neural network is implemented to learn fuzzy rules and membership functions with predictor of recurrent neural network (RNN) model. The results of experiment show that based on the predictive capability of RNN model neuro-fuzzy controller with good adaptation and robustness capability can be designed.     

Neurofuzzy network based self-tuning control with offset eliminating

The design of nonlinear controllers involves first selecting the input and then determining the nonlinear functions for the controllers. Since systems described by smooth nonlinear functions can be approximated by linear models in the neighbourhood of the selected operating points, the input of the nonlinear controller at these operating points can be chosen to be identical to those of the local linear controllers. Following this approach, it is proposed that the input of the nonlinear controller are similarly chosen, and that the local linear controllers are designed based on the integrating and k-incremental suboptimal control laws for their ability to remove offsets. Neurofuzzy networks are used to implement the nonlinear controllers for their ability to approximate nonlinear functions with arbitrary accuracy, and to be trained from experimental data. These nonlinear controllers are referred to as neurofuzzy controllers for convenience. As the integrating and k-incremental control laws have also been applied to implement self-tuning controllers, the proposed neurofuzzy controllers can also be interpreted as self-tuning nonlinear controllers. The training target for the neurofuzzy controllers is derived, and online training of the neurofuzzy controllers using a simplified recursive least squares (SRLS) method is presented. It is shown that using the SRLS method, computing time to train the neurofuzzy controllers can be drastically reduced and the ability to track varying dynamics improved. The performance of the neurofuzzy controllers and their ability to remove offsets are demonstrated by two simulation examples involving a linear and a nonlinear system, and a case study involving the control of the drum water level in the boiler of a power generation system.     

非线性动态系统神经模糊建模与内模/PID双重控制系统设计

非线性动态系统的内模控制要求建立精确的对象正模型和逆模型,这对于大多数实际对象是难以做到.提出了基于一类神经模糊模型的非线性动态系统建模方法,并在此基础上研究了基于神经模糊模型的非线性系统的内模控制设计.基于输入输出数据辨识的对象正模型和逆模型存在着模型失配问题,导致神经模糊内模控制范围变窄和控制鲁棒性降低,为了改善系统的性能,提出了神经模糊内模控制与PID控制结合的双重控制策略.对CSTR的反应物浓度控制研究表明,双重控制策略能有效地拓宽系统可控范围,改善系统性能.仿真结果证明该控制策略简单而有效.     

Fully Evolvable Optimal Neurofuzzy Controller Using Adaptive Critic Designs

A near-optimal neurofuzzy external controller is designed in this paper for a static compensator (STATCOM) in a multimachine power system. The controller provides an auxiliary reference signal for the STATCOM in such a way that it improves the damping of the rotor speed deviations of its neighboring generators. A zero-order Takagi–Sugeno fuzzy rule base constitutes the core of the controller. A heuristic dynamic programming (HDP) based approach is used to further train the controller and enable it to provide nonlinear near-optimal control at different operating conditions of the power system. Based on the connectionist systems theory, the parameters of the neurofuzzy controller, including the membership functions, undergo training. Simulation results are provided that compare the performance of the neurofuzzy controller with and without updating the fuzzy set parameters. Simulation results indicate that updating the membership functions can noticeably improve the performance of the controller and reduce the size of the STATCOM, which leads to lower capital investment.      

Internal Model Control Based on a Neurofuzzy System for Network Applications. A Case Study on the High-Performance Drilling Process

This paper presents the design and implementation of a neurofuzzy system for modeling and control of a high-performance drilling process in a networked application. The neurofuzzy system considered in this work is an adaptive-network-based fuzzy inference system (ANFIS), where fuzzy rules are obtained from input/output data. The design of the control system is based on the internal model control paradigm. The results obtained are significant both in simulation as well as the real-time application of networked control of the cutting force during high-performance drilling processes.     

Developing soft sensors using hybrid soft computing methodology: a neurofuzzy system based on rough set theory and genetic algorithms

This paper presents a hybrid soft computing modeling approach, a neurofuzzy system based on rough set theory and genetic algorithms (GA). To solve the curse of dimensionality problem of neurofuzzy system, rough set is used to obtain the reductive fuzzy rule set. Both the number of condition attributes and rules are reduced. Genetic algorithm is used to obtain the optimal discretization of continuous attributes. The fuzzy system is then represented via an equivalent artificial neural network (ANN). Because the initial parameter of the ANN is reasonable, the convergence of the ANN training is fast. After the rules are reduced, the structure size of the ANN becomes small, and the ANN is not fully weight-connected. The neurofuzzy approach based on RST and GA has been applied to practical application of building a soft sensor model for estimating the freezing point of the light diesel fuel in fluid catalytic cracking unit.     

Structure selection of neurofuzzy networks based on support vector regression

Neurofuzzy networks are being used increasingly to model non-linear dynamic systems, since they have the approximating ability of neural networks and the transparency of fuzzy systems. However, good generalization results can only be obtained if the structure of the network is suitably chosen. It is shown here that the structure of neurofuzzy networks with scatter partitioning can be obtained from the support vectors (SV) of the Support Vector Regression (SVR), since the SVR can be transformed to a neurofuzzy network. The main advantage of this approach is that the structure of the neurofuzzy networks can now be objectively chosen, as the SV are obtained by constrained optimization for a given modelling error bound. Since neurofuzzy networks are linear-inweights networks, the estimate of the weights of the networks can be obtained by the linear least-squares method. The properties of neurofuzzy networks based on the SV are derived, and its performance is illustrated by a simulation example involving a nonlinear system, and the modeling of Southern Oscillation Index.     

Integration of Multiple Feature Groups and Multiple Views into a 3D Object Recognition System

This paper proposes two approaches for utilizing the information in multiple entity groups and multiple views to reduce the number of hypotheses passed to the verification stage in a model-based object recognition system employing invariant feature indexing (P. J. Flynn and A. K. Jain, CVGIP: Image Understand. 55(2), 1992, 119-129). The first approach is based on a majority voting scheme that keeps track of the number of consistent votes cast by prototype hypotheses for particular object models. The second approach examines the consistency of estimated object pose from multiple groups of entities (surfaces) in one or more views. A salient feature of our system and experiment design compared to most existing 3D object recognition systems is our use of a large object database and a large number of test images. Monte Carlo experiments employing 585 single-view synthetic range images and 117 pairs of synthetic range images with a large CAD-based 3D object database (P. J. Flynn and A. K. Jain, IEEE Trans. Pattern Anal. Mach. Intell. 13(2), 1991, 114-132) show that a large number of hypotheses (about 60% for single views and 90% for multiple views on average) can be eliminated through use of these approaches. The techniques have also been tested on several real 3D objects sensed by a Technical Arts 100X range scanner to demonstrate a substantial improvement in recognition time.     

Active learning of visual descriptors for grasping using non-parametric smoothed beta distributions

One of the basic skills for a robot autonomous grasping is to select the appropriate grasping point for an object. Several recent works have shown that it is possible to learn grasping points from different types of features extracted from a single image or from more complex 3D reconstructions. In the context of learning through experience, this is very convenient, since it does not require a full reconstruction of the object and implicitly incorporates kinematic constraints as the hand morphology. These learning strategies usually require a large set of labeled examples which can be expensive to obtain. In this paper, we address the problem of actively learning good grasping points to reduce the number of examples needed by the robot. The proposed algorithm computes the probability of successfully grasping an object at a given location represented by a feature vector. By autonomously exploring different feature values on different objects, the systems learn where to grasp each of the objects. The algorithm combines beta–binomial distributions and a non-parametric kernel approach to provide the full distribution for the probability of grasping. This information allows to perform an active exploration that efficiently learns good grasping points even among different objects. We tested our algorithm using a real humanoid robot that acquired the examples by experimenting directly on the objects and, therefore, it deals better with complex (anthropomorphic) hand–object interactions whose results are difficult to model, or predict. The results show a smooth generalization even in the presence of very few data as is often the case in learning through experience.     

Predicting Chaotic Time Series Using Neural and Neurofuzzy Models: A Comparative Study

The prediction accuracy and generalization ability of neural/neurofuzzy models for chaotic time series prediction highly depends on employed network model as well as learning algorithm. In this study, several neural and neurofuzzy models with different learning algorithms are examined for prediction of several benchmark chaotic systems and time series. The prediction performance of locally linear neurofuzzy models with recently developed Locally Linear Model Tree (LoLiMoT) learning algorithm is compared with that of Radial Basis Function (RBF) neural network with Orthogonal Least Squares (OLS) learning algorithm, MultiLayer Perceptron neural network with error back-propagation learning algorithm, and Adaptive Network based Fuzzy Inference System. Particularly, cross validation techniques based on the evaluation of error indices on multiple validation sets is utilized to optimize the number of neurons and to prevent over fitting in the incremental learning algorithms. To make a fair comparison between neural and neurofuzzy models, they are compared at their best structure based on their prediction accuracy, generalization, and computational complexity. The experiments are basically designed to analyze the generalization capability and accuracy of the learning techniques when dealing with limited number of training samples from deterministic chaotic time series, but the effect of noise on the performance of the techniques is also considered. Various chaotic systems and time series including Lorenz system, Mackey-Glass chaotic equation, Henon map, AE geomagnetic activity index, and sunspot numbers are examined as case studies. The obtained results indicate the superior performance of incremental learning algorithms and their respective networks, such as, OLS for RBF network and LoLiMoT for locally linear neurofuzzy model.     

Efficient non-linear model based predictive control

For a large number of degrees of freedom and/or large dimension systems, non-linear model based predictive control algorithms based on dual mode control can become intractable. This paper proposes an alternative which deploys the closed-loop paradigm that has proved to be very effective for the case of linear time-varying or uncertain systems. The various attributes and computational advantages of the approach are shown to carry over to the non-linear case.     

基于模糊逻辑控制的机器人灵巧手的抓取方式

机器人灵巧手抓取方式控制是整个灵巧手操作规划一个非常重要的环节。该文介绍了3种典型的抓取方式：平行抓取、聚中抓取和镊式抓取。以被抓取物体的尺寸为输入量，抓取方式作为输出量，提出了一种基于模糊逻辑的灵巧手抓取控制算法，并对这种算法进行了推导。在实际的机器人灵巧手遥操作系统中的应用表明，这种基于模糊控制的灵巧手抓取方式控制方法是正确有效的，具有使用价值。     

An intelligent online fault diagnostic scheme for nonlinear systems

An online fault diagnostic scheme for nonlinear systems based on neurofuzzy networks is proposed in this paper. The scheme involves two stages. In the first stage, the nonlinear system is approximated by a neurofuzzy network, which is trained offline from data obtained during the normal operation of the system. In the second stage, residual is generated online from this network and is modelled by another neurofuzzy network trained online. Fuzzy rules are extracted from this network, and are compared with those in the fault database obtained under different faulty operations, from which faults are diagnosed. The performance of the proposed intelligent fault scheme is illustrated using a two-tank water level control system under different faulty conditions .     

Next-generation hearing prosthetics

Neural networks and fuzzy logic are powerful tools for next-generation hearing prosthetics. A neural network, as a function fitter to map the hearing loss to desired gains requirements, provides many benefits over other approaches. The network is able to learn dynamically through experience. It is open and expandable - a physician can easily incorporate new knowledge into the system. Fuzzy logic, on the other hand, is an indispensable tool for the tuning process. It builds a direct and reasonable link between a user's subjective evaluation and the actual required modifications to the gain targets. Again, physicians are free to add new rules to the rule base in reflection of specific needs and patterns. The presented neurofuzzy approach helps hearing prosthetic devices not only in an offline fitting process, but also in online operations. Next-generation hearing prosthetics will be more intelligent than current devices. Hearing aids should be situation-dependent and capable of evolving or adapting. The neurofuzzy approach makes these features possible.     

Generalized neurofuzzy network modeling algorithms usingBezier-Bernstein polynomial functions and additive decomposition

This paper introduces a new neurofuzzy model construction algorithm for nonlinear dynamic systems based upon basis functions that are Bezier-Bernstein polynomial functions. This paper is generalized in that it copes with n-dimensional inputs by utilising an additive decomposition construction to overcome the curse of dimensionality associated with high n. This new construction algorithm also introduces univariate Bezier-Bernstein polynomial functions for the completeness of the generalized procedure. Like the B-spline expansion based neurofuzzy systems, Bezier-Bernstein polynomial function based neurofuzzy networks hold desirable properties such as nonnegativity of the basis functions, unity of support, and interpretability of basis function as fuzzy membership functions, moreover with the additional advantages of structural parsimony and Delaunay input space partition, essentially overcoming the curse of dimensionality associated with conventional fuzzy and RBF networks. This new modeling network is based on additive decomposition approach together with two separate basis function formation approaches for both univariate and bivariate Bezier-Bernstein polynomial functions used in model construction. The overall network weights are then learnt using conventional least squares methods. Numerical examples are included to demonstrate the effectiveness of this new data based modeling approach.     

Integrating a flexible anthropomorphic, robot hand into the control, system of a humanoid robot

This article presents the approaches taken to integrate a novel anthropomorphic robot hand into a humanoid robot. The requisites enabling such a robot hand to use everyday objects in an environment built for humans are presented. Starting from a design that resembles the human hand regarding size and movability of the mechatronical system, a low-level control system is shown providing reliable and stable controllers for single joint angles and torques, entire fingers and several coordinated fingers. Further on, the high-level control system connecting the low-level control system with the rest of the humanoid robot is presented. It provides grasp skills to the superior robot control system, coordinates movements of hand and arm and determines grasp patterns, depending on the object to grasp and the task to execute. Finally some preliminary results of the system, which is currently tested in simulations, will be presented.     

Understanding design patterns — what is the problem?

Design patterns codify proven solutions to recurring design problems. Their proper use within a development context requires that: (i) we understand them; (ii) we ascertain their applicability or relevance to the design problem at hand; and (iii) we apply them faithfully to the problem at hand. We argue that an explicit representation of the design problem solved by a design pattern is key to supporting the three tasks in an integrated fashion. We propose a model‐driven representation of design patterns consisting of triples < MP, MS, T > where MP is a model of the problem solved by the pattern, MS is a model of the solution proposed by the pattern, and T is a model transformation of an instance of the problem into an instance of the solution. Given an object‐oriented design model, we look for model fragments that match MP (call them instances of MP), and when one is found, we apply the transformation T yielding an instance of MS. Easier said than done. Experimentation with an Eclipse Modeling Framework‐based implementation of our approach applied to a number of open‐source software application's raised fundamental questions about: (i) the nature of design patterns in general, and the ones that lend themselves to our approach, and (ii) our understanding and codification of seemingly simple design patterns. In this paper, we present the principles behind our approach, report on the results of applying the approach to the Gang of Four (GoF) design patterns, and discuss the representability of design problems solved by these patterns. Copyright © 2011 John Wiley & Sons, Ltd.     

Workspace Generation for Multifingered Manipulation

In this paper, we propose a novel numerical approach and algorithm to compute and visualize the workspace of a multifingered hand manipulating an object. Based on feasibility analysis of grasps, the proposed approach uses an optimization technique to first compute discretely the position boundary of the grasped object and then calculate the rotation ranges of the object at specified positions within the boundary. In other words, workspace generation with the approach is fulfilled by obtaining reachable boundaries of the grasped object in the sense of both position and orientation, and the discrete boundary points are computed by a series of optimization models. Unlike in workspace generation of other robotic systems where only geometric and kinematic parameters of the robots are considered, all factors including geometric, kinematic and force-related factors that affect the workspace of a hand–object system can be taken into account in our approach to generate the workspace of multifingered manipulation. Since various constraints can be integrated into the optimization models, our method is general and complete, with adaptability to various grasps and manipulations. Workspace generation with the approach in both planar and spatial cases are illustrated with examples. The approach provides an effective and general solution to the long-term open and challenging problem of workspace generation of multifingered manipulation. Part of the work has been published in the Proceedings of IEEE/RSJ IROS2008 and IEEE/ASME AIM2008.