The problem of precise modeling of Synchronous Generator (SG) devices is demanding and crucial for monitoring, stability, and control of electric grids and microgrids. SGs are known to exhibit nonlinear behavior, and because they may work in a wide range of operating points due to different electric network phenomena like load changes, current intermittent renewable energy resources, temperature variations, topological changes, etc., the modeling task of SG can be a challenging problem. This paper proposes a new method to find a global model for a synchronous generator from the input and output measurement data using state-of-the-art methods in artificial intelligence (AI) like fuzzy clustering, subspace identification, and Takagi–Sugeno (T-S) fuzzy modeling. The fuzzy C-means method is utilized to cluster the measurement data, and then using a subspace identification method based on Markov parameters concepts, the dynamic model of SG for each cluster is obtained in the form of a state space model. A Takagi–Sugeno fuzzy model is applied to determine the corresponding outputs based on the measured inputs and the available state space models. The effectiveness of the proposed approach is illustrated by applying it to the data obtained from simulations on a known fourth-order SG nonlinear model and the data obtained from real-world experimental tests.

Electric vehicle physical parameters highly influence the modeling of its different systems. Although a simulation using data acquired from field tests can have satisfactory results, the parameters inaccuracy, due to either insufficient information or wear, can prevent a better performance. In this paper, 10 electric vehicle physical parameters are adjusted/calibrated by three metaheuristic algorithms: Particle Swarm Optimization, Genetic Algorithms, and Simulated Annealing. Moreover, tests on real short and long distance data sets were used in order to validate the proposed framework to EV model calibration. The results achieved indicate that parameter calibration is effective in the reduction of the modeling error.

Prediction of key variables is an important part of the monitoring, control, and optimization of industrial processes, since it is important to anticipate certain behaviors so that the correct actions can be taken. To assess which algorithm is best suited to the prediction of a number of key variables at various stages of wastewater treatment plants (WWTP), five computational algorithms were researched: Artificial Neural Network, Long Short-Term Memory, deep learning Transformer model, Adaptive Neuro-Fuzzy Inference System, and Gaussian Mixture Model. With these models, techniques already well established in the state-of-the-art are evaluated, as well as more recent methods that have been exhibiting good performance in variable prediction regression problems. These algorithms were evaluated in four WWTP case studies, in which the objective is to predict the following key variables: total suspended solids, nitrate and nitrite, ammonia and ammonium, and biochemical oxygen demand. The learning process of each algorithm was performed using extensive tests in order to select the input variables, and define the topologies and hyper-parameters of the presented models by cross-validation. The results indicate that it is possible to adequately predict the four variables, and the best results were achieved by the Transformer algorithm, which presents the lower error values in the considered metrics.

This paper presents a novel feature selection method based on the conditional mutual information (CMI). The proposed High Order Conditional Mutual Information Maximization (HOCMIM) method incorporates high order dependencies into the feature selection procedure and has a straightforward interpretation due to its bottom-up derivation. The HOCMIM is derived from the CMI’s chain expansion and expressed as a maximization optimization problem. The maximization problem is solved using a greedy search procedure, which speeds up the entire feature selection process. The experiments are run on a set of benchmark datasets (20 in total). The HOCMIM is compared with eighteen state-of-the-art feature selection algorithms, from the results of two supervised learning classifiers (Support Vector Machine and K-Nearest Neighbor). The HOCMIM achieves the best results in terms of accuracy and shows to be faster than high order feature selection counterparts.

This paper proposes a methodology for iterative learning of multi-input multi-output (MIMO) fuzzy models focusing on dynamic system identification. The first step of the proposed method is the learning of the antecedent part of the fuzzy system, which is learned iteratively, where fuzzy rules can be added or merged based on the presented novelty detection and similarity criteria defined by a recursive extension of the Gath-Geva clustering algorithm. Then, the consequent part consists in the direct implementation of a non-recursive fuzzy approach that uses global least squares, Observer Kalman Filter Identification (OKID) and the Eigensystem Realization Algorithm (ERA). The proposed method is validated using experimental data from a real quadrotor aerial robot, a nonlinear dynamic system. Using quantitative performance metrics, the proposed method is compared with Hammerstein-Wiener models (H.-W.), nonlinear autoregressive models with exogenous input (NARX), and state-space models using subspace method with time-domain data (N4SID), other MIMO system identification techniques. The proposed method achieved better results compared to other techniques, showing the importance and versatility of learning based on novelty detection for MIMO problems.

This paper proposes an iterative learning approach to learn a fuzzy system composed of a sum of multiple univariate zero-order Takagi-Sugeno (T-S) fuzzy systems. The learning algorithm is based on the backfitting algorithm, and new fuzzy rules are iteratively added based on a novelty detection criterion, which gives the novelty degree of a new data by a value between zero and one, allowing an easier rule creation threshold's definition. In order to validate the performance of the proposed approach, 10 benchmark data sets are used to compare the proposed approach with two well-known state-of-the-art methods, the Extreme Learning Machine (ELM), and the Support Vector Regression (SVR), and with the GAM-ZOTS approach, which model is similar to the proposed approach. From the results, it is concluded that the proposed approach outperforms ELM, SVR and GAM-ZOTS in almost all data sets.

A proof of concept of a purely virtual test platform for critical cyberphysical systems in closed-loop is presented in this work. An H∞direct adaptive fuzzy controller is formulated to tackle the wheel slip tracking problem in Antilock-Braking System over a CAN network. A Lyapunov function for the nonlinear control system is derived using the Riccati equation solution in order to prove stability and robustness with respect to network-induced delays, data packet losses, and model uncertainty. Simulation results show that high performance and robustness are achieved.

Current smart factories, and technologies such as cyber-physical systems and Internet of Things have transformed the working environments, that now incorporate digital machines with information technology. Integrated automated systems require being accurate and dependable even though operating in a non-predictable environment. The needs for testing, quality assurance, and maintenance for such types of systems are continuously increasing, and testing frameworks are often used to execute automated tests on those systems. With the objective of providing a support and enabling infrastructure for testing cyber-physical systems in closed-loop, it was designed and developed the KhronoSim testing platform. This paper presents the KhronoSim platform and architecture. It is modular, extensible and usable in multiple application domains. It features real-time control and enables the joint and flexible integration of simulation models and physical components or subsystems to build a closed-loop test environment. Furthermore, the paper presents a case study, displaying the flexibility and modularity of the KhronoSim platform and its capacity of integrating solutions from external sources, simulators, communication protocols, power sources, electrical inputs/outputs, demonstrating that it is a robust platform that is useful for testing and simulation of complex systems, yet allowing the use of physical and virtual systems alike.

Soft sensors are widely applied in many industrial systems for predicting quality variables in real-time; examples of soft sensors applications can be found in pulp and paper mills, cement kilns, polymerization processes and so on. However, there are several peculiarities that make soft sensors development difficult in some processes. One of these characteristics is the multiple operating mode scenarios, which is characterized by different operating regions of process, e.g. summer-winter operation of a refinery, batch processes, etc. In this paper, a regularized version of mixture of expert models, based on elastic net regularization, is employed for predicting the acidity value, a quality indicator variable of process, in a batch polymerization process. The proposed method allowed the application of 27 experts to compose the final model and attaining better prediction performance when compared to other state-of-the-art algorithms. The proposed method is compared to the predictive modeling state-of-the-art methods, such as support vector machines (SVM), decision trees (DT), and the elastic net model (EN).

In this paper a semi-supervised regression model based on co-training is applied on the soft sensor context, together with a feature ranking approach which has the purpose of removing irrelevant features. The description of both the methods of semi-supervised regression and feature ranking, as well as the theorethical foundation of the proposed feature ranking approach are also given. To evaluate the proposed methodology, a real-world polymerization industrial process was used as example. The results demonstrate that the devised feature ranking and selection improves the semi-supervised regression model.

The paper proposes a methodology to self-evolve an online fuzzy logic controller (FLC). The proposed methodology does not require any initialization at all, it can start with an empty set of fuzzy control rules or with a simple collection of fuzzy control rules obtained from an expert operator. The FLC design is online, using only the input/output data obtained during the normal operation of the system while it is being controlled. The FLC is composed of a simple structure, where each input variable has its own set of fuzzy control rules, and is evaluated individually by the proposed methodology avoiding the high increase in the number of fuzzy control rules. The FLC structure and their antecedent and consequent parameters are both online modified by the proposed methodology. Only simple information about the system and controller is need, specifically the universe of discourse of the input and output variables, an information that is mandatory to control any process. The performance of the proposed methodology is tested on a simulated continuous-stirred tank reactor (CSTR) system where the results show that the proposed methodology has the capability of designing the FLC in order to successfully controlling the CSTR system by evolving/modifying the FLC structure when unknown regions of operation are reached (unknown for the controller).

A common step in most of water treatment plants is the chemical coagulation. The chemical coagulation is the process of destabilizing the colloidal particles suspended in raw water by the addition of coagulants. Generally, the determination of the quantity of coagulant to be added to water is made manually by jar tests. However, the manual control has slow response to changes of raw water and it requires intensive laboratory analysis. To reduce the manual effort and to improve the response to change in raw water quality, this work proposes the determination of the coagulant dosage using dynamic neural network modeling using the available sensors as input of the model. The case of study is a large scale water treatment plant in Ceará, Brazil, where the kinds of coagulants added to water are the aluminum sulphate (AS) and poly aluminum chloride (PAC). Several dynamic neural network models with different combinations of the input variables have been evaluated. The best solution found is composed by a nonlinear autoregressive with exogenous input (NARX) model having three input variables, the pH in raw and coagulated water, and the turbidity in the coagulated water, with coefficient of determination of R2 = 0.95 and R2 = 0.91 for the AS and PAC dosage prediction, respectively.

This paper proposes a method for adaptive identification and predictive control using an online sequential extreme learning machine based on the recursive partial least-squares method (OS-ELM-RPLS). OL-ELM-RPLS is an improvement to the online sequential extreme learning machine based on recursive least-squares (OS-ELM-RLS) introduced in [1]. Like in the batch extreme learning machine (ELM), in OS-ELM-RLS the input weights of a single-hidden layer feedforward neural network (SLFN) are randomly generated, however the output weights are obtained by a recursive least-squares (RLS) solution. However, due to multicollinearities in the columns of the hidden-layer output matrix caused by the presence of redundant input variables or by a large number of hidden-layer neurons, the problem of estimation the output weights can become ill-conditioned. In order to circumvent or mitigate such ill-conditioning problem, it is proposed to replace the RLS method by the recursive partial least-squares (RPLS) method. The identification methodology is proposed for two application problems: (1) construction of a inferential model, and (2) the learning of a model for the Generalized predictive control (GPC) algorithm. The integration of the proposed adaptive identification method with the GPC results in an adaptive predictive control methodology. To validate and demonstrate the performance and effectiveness of the proposed methodologies, they are applied on modeling of two public regression data sets and on control of the flow through a simulated valve.

The paper proposes a new framework to learn a Fuzzy Logic Controller (FLC), from data extracted from a process while it is being manually controlled, in order to control nonlinear industrial processes. The learning of the FLC is performed by a hierarchical genetic algorithm (HGA). First, the fuzzy c-means (FCM) clustering algorithm is applied to initialize the HGA population, in order to reduce the computational cost and increase the performance of the HGA. The HGA is composed by five hierarchical levels and it is an automatic tool since it does not require any prior knowledge concerning the structure (e.g. the number of rules) and the database (e.g. antecedent and consequent fuzzy sets) of the FLC, and concerning the selection of the adequate input variables and their respective time delays. After the extraction of the FLC by the proposed method, in order to obtain a better control results, if necessary, the learned FLC can be improved manually by using the information transmitted by a human operator, and/or the learned FLC could be easily applied to initialize the required fuzzy knowledge-base of adaptive controllers. In order to improve the results of the learned FLC, a direct adaptive fuzzy controller is applied. Moreover, the proposed method is applied on control of the dissolved oxygen in an activated sludge reactor within a simulated wastewater treatment plant. The results are presented, showing that the proposed method successfully extracted the parameters of the FLC.

A novel adaptive evolving Takagi-Sugeno (T-S) model identification method is investigated and integrated in a control architecture to control of nonlinear processes is investigated. The proposed system identification approach consists of two main steps: antecedent T-S fuzzy model parameters identification and consequent parameters identification. First, a new unsupervised fuzzy clustering algorithm (NUFCA) is introduced to combine the K-nearest neighbor and fuzzy C-means methods into a fuzzy modeling method for partitioning of the input-output data and identifying the antecedent parameters of the fuzzy system. Then, a recursive procedure using a particle swarm optimization (PSO) algorithm is exploited to construct an online fuzzy model identification and adaptive control methodology. For better demonstration of the robustness and efficiency of the proposed methodology, it is applied to the identification of a model for the estimation of the flour concentration in the effluent of a real-world wastewater treatment plant (WWTP), and identification and control, using a generalized predictive controller (GPC), of a real experimental setup composed of two coupled DC motors. The results show that the developed evolving T-S fuzzy model methodology can identify nonlinear systems satisfactorily and can be successfully used for a prediction model of the process for the GPC.

This paper proposes a mixture of univariate linear regression models (MULRM) to be applied in time-varying scenarios, and its application to soft sensor problems. Offline and online solutions of MULRM will be obtained using the Expectation-Maximization Algorithm. A forgetting factor will be introduced in the online solution to discount the information of already learned data, so that it can be applied in time varying settings. The solution of the proposed method allows its online and recursive application in any regression problem, without the necessity of storing any past value of data. The recursive solution of the MULRM will then be applied in two time-varying real-world prediction problems. The proposed method is compared with four state of art algorithms. In all the experiments, the proposed method always exhibits the best prediction performance.

In this work, two alternative methodologies for modeling and predicting gas emissions of NO, NO2and SO2are presented. The first method involves hard modeling strategies with Parsimonious Multivariate Least Squares (PMLS) assuming simple polynomial functions as base model. The second is a soft modeling approach using Extreme Learning Machine (ELM). In this work we found that both methods have similar capabilities for data description, providing an in depth analysis of the system under study. Results also reveal further insights in predicting gas emissions and enlighten on which of the factors can be useful for prediction, and consequently for system characterization and emission abatement.

This paper proposes a learning algorithm for single-hidden layer feedforward neural networks (SLFN) called genetically optimized extreme learning machine (GO-ELM). In the GO-ELM, the structure and the parameters of the SLFN are optimized by a genetic algorithm (GA). The output weights, like in the batch ELM, are obtained by a least squares algorithm, but using Tikhonov's regularization in order to improve the SLFN performance in the presence of noisy data. The GA is used to tune the set of input variables, the hidden-layer configuration and bias, the input weights and the Tikhonov's regularization factor. The proposed method was applied and compared with four other methods over five benchmark problems available in a public repository. Besides it was applied in the estimation of the temperature at the burning zone of a real cement kiln plant.

This paper proposes a method for fault detection and replacement of the sensor responsible by the measurement of the burning zone temperature in a rotary cement kiln. The control of the burning zone temperature is crucial for the control of kiln temperature and therefore for the control of the cement quality, pollutant emissions, and consumed energy. However the flying dust within the kiln can block the pyrometer sensor, causing faults in the temperature sensor. Exploring the analytical redundancy that usually exist in industrial processes, the proposed methodology uses a neural network trained using an online sequential extreme learning machine to online construct a model to estimate the burning zone temperature. Using the error between the measured and estimated temperatures, faults in the measurement can be detected and thus the replacement of the measured temperatures by the estimated output is made.

This work addresses the problem of controlling unknown and time varying plants for industrial applications. To deal with such problem several Self-Tuning Controllers with a Proportional Integral and Derivative (PID) structure have been chosen. The selected controllers are based on different methodologies, and some use implicit identification techniques (Single Neuron and Support Vector Machine) while the others use explicit identification (Dahlin, Pole placement, Deadbeat and Ziegler-Nichols) based in the Least Squares Method. The controllers were tested on a real DC motor with a varying load. The results have shown that all the tested methods were able to properly control an unknown plant with varying dynamics.

This paper proposes a new method for identification problems for industrial applications based on a Takagi-Sugeno (T-S) fuzzy model. The learning of the T-S model is performed from input/output data to approximate unknown nonlinear processes by a coevolationary genetic algorithm (GA). The proposed method is an automatic tool since it does not require any prior knowledge concerning the structure (e.g. the number of rules) and the database (e.g. antecedent fuzzy sets) of the T-S fuzzy model, and concerning the selection of the adequate input variables and their respective time delays. The proposed methodology is able to design all the parts of the T-S fuzzy prediction model and it is composed by five hierarchical levels. To validate and demonstrate the performance and effectiveness of the proposed algorithm, it is applied on Box-Jenkins benchmark problem.

The paper proposes an adaptive fuzzy predictive control method for industrial processes, which is based on the Generalized predictive control (GPC) algorithm. To provide good accuracy in the identification of unknown nonlinear plants, an online adaptive law is proposed to adapt a T-S fuzzy model. It is demonstrated that the tracking error remains bounded. The stability of closed-loop control system is studied and proved via the Lyapunov stability theory. To validate the theoretical developments and to demonstrate the performance of the proposed control, the controller is applied on a simulated laboratory-scale liquid-level process. The simulation results show that the proposed method has good performance and disturbance rejection capacity in industrial processes.

This paper proposes a method for online variable selection and model learning (AdaFSML-RLS) to be applied in industrial applications in the context of adaptive soft sensors. In the proposed method the model learning is made online and recursivelly, i.e it is not necessary to store the past values of data while learning the model. Furthermore, the proposed method has the capability of tracking the real time correlation coefficient between each variable and the target, allowing the knowledge about the importance of variables over the time. Moreover, in this method is not necessary to have any knowledge about the process or variables. The method was sucessfully applied in two datasets, an artificial dataset and in a real-world dataset.

Ensemble Methods (EMs) are sets of models that combine their decisions, or their learning algorithms, or different data to obtain good predictions. The motivations are the possibility of improving the generalization capability and the overall system performance. However, several issues are at stake in EM development, such as the design of models that disagree as much as possible on the same data, the selection of some of them and their optimal combination to enhance the robustness of the ensemble. Since there is no unified procedure to implement these steps, this paper proposes a new methodology to design Neural Network (NN) ensembles using a Genetic Algorithm (GA). Firstly, a set of NNs with high degree of diversity is produced. The aim is to draw a different training data set for each NN by applying bootstrap. The architecture of the NN is selected by varying the number of hidden neurons, activation functions and initialization of weights. Secondly, a GA is employed to select both the best subset of NNs and the optimal combination strategy for ensuring the accuracy and the robustness of the ensemble. Experiments on well-known data sets are reported to evaluate the effectiveness of the proposed methodology.

In spite of several technical advances made in recent years by the automotive industry, the driver's behaviour still influences significantly the overall fuel consumption. With the rise of smartphones adoption, there are also new opportunities to increase the awareness to this issue. The main aim of this paper is to present a new smartphone application that will help drivers reduce the fuel consumption of their vehicles. This is accomplished by using the smartphone's sensors and the vehicle state to detect the driving pattern and suggest new behaviours in real time that will lead to a more efficient driving experience. The preliminary results show the potential for significant energy savings and their relevance for changing the drivers' behaviour.

The paper proposes a stable indirect adaptive fuzzy predictive control, which is based on a discrete-time Takagi-Sugeno (T-S) fuzzy model and on the Generalized predictive control (GPC) algorithm. The T-S fuzzy model is used to approximate the unknown nonlinear plant, that to provide good accuracy in identification of unknown model parameters, three online adaptive laws are proposed. It is demonstrated that the tracking error remains bounded. The stability of closed-loop control system is studied and proved via the Lyapunov stability theory. To validate the theoretical developments and to demonstrate the performance of the proposed control, the controller is applied on a nonlinear simulated laboratory-scale liquid-level process. The simulation results show that the proposed method has a good performance and disturbance rejection capacity in industrial processes.

The paper proposes a new method to automatically extract all fuzzy parameters of a Fuzzy Logic Controller (FLC) in order to control nonlinear industrial processes. The learning of the FLC is performed from controller input/output data and by a hierarchical genetic algorithm (HGA). The algorithm is composed by a five level structure, where the first level is responsible for the selection of an adequate set of input variables. The second level considers the encoding of the membership functions. The individual rules are defined on the third level. The set of rules are obtained on the fourth level, and finally, the fifth level, selects the elements of the previous levels, as well as, the t-norm operator, inference engine and defuzzifier methods which constitute the FLC. To demonstrate and validate the effectiveness of the proposed algorithm, it is applied to control a simulated water tank level process.

The paper proposes an adaptive fuzzy predictive control method. The proposed controller is based on the Generalized predictive control (GPC) algorithm, and a recurrent fuzzy neural network (RFNN) is used to approximate the unknown nonlinear plant. To provide good accuracy in identification of unknown model parameters, an online adaptive law is proposed to adapt the consequent part of the RFNN, and its antecedent part is adapted by back-propagation method. The stability of closed-loop control system is studied and proved via the Lyapunov stability theory. A nonlinear lab oratory-scale liquid-level process is used to validate and demonstrate the performance of the proposed control. The simulation results show that the proposed method has good performance and disturbance rejection capacity in industrial processes and outperforms the PID and the classical GPC controllers.

Industries are faced with the choice of suitable process control policies to improve costs, quality and raw material consumption. In the paper pulp industry, it is important to estimate quickly the Chemical Oxygen Demand (COD), a parameter that is highly correlated to product quality. Soft Sensors (SSs) have been established as alternative to hardware sensors and laboratory measurements for monitoring and control purposes. However, in real setups it is often difficult to get sufficient data for SS development. This work proposes Ensemble Methods (EMs) as a way to improve the SS performance for small datasets. EMs use a set of models to obtain better prediction. Their success is usually attributed to the diversity. Bootstrap and noise injection are used to produce diverse models. Several combinations of EMs are compared. The SS is successfully applied to estimate COD in a pulp process.

The paper proposes a method to select the best variables and respective time-lags for industrial applications when the objective is the estimation of a target variable using the information content of empirical data. No further information is assumed about the process. The problem of jointly selecting the best variables and the respective time-lags is treated as a variable selection problem. This assumption implies an increase of input dimensionality and multicollinearity into input space. Then, a multidimensional mutual information estimator based on the l-nearest neighbor algorithm is used in a forward search procedure to select the best variables and and respective time-lags. To verify the performance of selected variables and delays, the method was successfully applied in two data sets. A least squares support vector machine was used as the main model for the soft sensor in both cases.

This paper proposes a method for Soft Sensors design using a Multilayer Perceptron model based on co-evolutionary genetic algorithms, called CEV-MLP. This method jointly and automatically selects the best input variables and the best configuration of the network for the prediction setting. The CEV-MLP is constituted by three levels, the first level selects the best input variables and respective delays set, the second level is composed by the parameters of hidden layers to be optimized (number of neurons in the hidden layers and transfer function), and the third level is the combination of first and second level. The method was successfully applied, and compared with two state-of-the-art methods, in three real datasets. In all the experiments, the proposed method shows the best approximation accuracy, while all the design of the prediction setting is performed automatically.

In this paper an adaptive fuzzy control strategy for dissolved oxygen concentration (DO) control of an activated sludge process is proposed and evaluated in a benchmark simulation model. The controller uses DO concentration error feedback and manipulates the flow control valves supplying air to the bioreactor cells. The results of simulation shows that this adaptive controller can optimize control rules resulting in an accurate controls of dissolved oxygen.

The paper presents an adaptive fuzzy predictive control based on discrete-time Takagi-Sugeno (T-S) fuzzy model. The proposed controller is based on Generalized predictive control (GPC) algorithm, and a discrete-time T-S fuzzy model is employed to approximate the unknown nonlinear process. To provide a better accuracy in identification of unknown parameters of the model, it is proposed an on-line adaptive law which ensures that the tracking error remains bounded. The stability of closed-loop control system is proved/studied via the Lyapunov stability theory. To validate the theoretical developments and to demonstrate the performance of the proposed control is simulated as nonlinear system a laboratory-scale liquid-level process. The simulation results show that the proposed method has a good performance and disturbance rejection capacity in industrial process.

This paper proposes a new method for input variable and delay selection (IVDS) for Soft Sensors (SS) design. The IVDS algorithm is composed by the following steps: (1) Time delay selection; (2) Identification and exclusion of redundant variables; (3) Best variables subset selection. The IVDS algorithm proposed in this work performs the delay and variable selection through two distinct methods, mutual information (MI) is applied to delay selection and for variable selection a multilayer perceptron (MLP) based approach is performed. It is shown in the case studies that the application of the delay selection before applying the variable selection increases the generalization of the MLP-model. The algorithm uses the relative variance tracking precision (RV TP) criterion and the mean square error (MSE) to evaluate the precision of soft sensor. Simulation results are presented showing the effectiveness of the method.

Wireless Sensor Networks (WSN) is an emerging technology that is developed with a large number of useful applications. On the other hand, Artificial Neural Networks (ANN) have found many successful applications in nonlinear system and control, digital communication, pattern recognition, pattern classification, etc. There are many similarities between WSN and ANN. For example, the sensor node itself can be seen as a neuron since the WSN application show characteristics such as distributed processing, massive parallelism, adaptively, inherent contextual information processing, fault tolerance and low computation. This paper examines the possibility of embedding ANN and WSN into a Smart Table. Prototypal results have shown that ANN models are good candidates for using it deployed into low cost System-on-a-Chip (SoC).

Mobile robotics is a challenging research area, with produced results that were unthinkable several years ago. There exist algorithms and methods capable of performing difficult tasks such as detect/classify objects, skill learning and SLAM. From the initial design steps, the real-time software architecture of a robotic platform requires great attention. The problem is difficult, because various components, such as sensing, perception, localization, and motor control, are required to operate and interact in real-time. This makes the system a very complex one. This paper presents a real-time control architecture designed for mobile robots and intelligent vehicles. Moreover, an example of application of the control structure consisting on a system for learning to classify places, using laser range data, is reported.

Localization is an important problem in autonomous mobile robots navigation. To solve this problem, robots must also be able to learn, maintain and update models of their environments. This paper describes a full implementation of a simultaneous localization and map building (SLAM) method. SLAM is the problem of an autonomous vehicle starting at an unknown position which then incrementally builds a world map and estimates the robot absolute pose according to the map. An extended Kalman filter (EKF) is used for estimation and data fusion. For perception, the method combines an adaptive break point detector, first and second order analysis, and the RANSAC algorithm for robust fitting of laser scan data in order to extract a model composed of line segments and their uncertainty. A dynamic cache is proposed and introduced in the world model in order to speedup the map search in the measurement prediction and feature matching phases of SLAM. Experimental results of simulation and real-robot experiments with a Nomad 200 are presented demonstrating the effectiveness of the SLAM methods and improvements attained with the cache of feature method.

Mobile robots must be able to build their own maps to navigate in unknown worlds. Expanding a previously proposed method based on the fuzzy ART neural architecture (FARTNA), this paper introduces a new online method for learning maps of unknown dynamic worlds. For this purpose the new Prune-able fuzzy adaptive resonance theory neural architecture (PAFARTNA) is introduced. It extends the FARTNA self-organizing neural network with novel mechanisms that provide important dynamic adaptation capabilities. Relevant PAFARTNA properties are formulated and demonstrated. A method is proposed for the perception of object removals, and then integrated with PAFARTNA. The proposed methods are integrated into a navigation architecture. With the new navigation architecture the mobile robot is able to navigate in changing worlds, and a degree of optimality is maintained, associated to a shortest path planning approach implemented in real-time over the underlying global world model. Experimental results obtained with a Nomad 200 robot are presented demonstrating the feasibility and effectiveness of the proposed methods.

For mobile vehicle navigation in dynamic environments it is desirable that robots have a model of the dynamic aspects of the world. In this paper we present a method for detection and tracking of multiple moving objects using sensor information. The method uses particle filters to estimate objects states, and sample based joint probabilistic data association filters to perform the assignment of features detected from sensor data to filters. A perception mechanism, based on occupancy grids, is presented to distinguish between mobile features and static objects. Experimental results from a real-time implementation using a laser range sensor are presented demonstrating the feasibility and effectiveness of the presented methods.

Mobile robots must be able to build their own maps to navigate in unknown worlds. Expanding a previously proposed method [Rui Araujo et al., April 1999], based on the fuzzy ART neural architecture (FARTNA), this paper introduces a new on-line method for learning maps of dynamic worlds. For this purpose the Prune-Able fuzzy ART neural architecture (PAFARTNA) is introduced. It extends the FARTNA self-organizing neural network to include the ability to selectively perform the following additional operation on recognition categories: remove, directly update spatial span, or forced create. A method is proposed for the perception of object removals, and then integrated with PAFARTNA. Experimental results obtained with a Nomad 200 robot are presented demonstrating the feasibility and effectiveness of the proposed methods.

In this paper, we address the problem of navigating an autonomous mobile robot in an unknown indoor environment. The parti-game multiresolution learning approach is applied for simultaneous and cooperative construction of a world model, and learning to navigate through an obstacle-free path from a starting position to a known goal region. The paper introduces a new approach, based on the application of the fuzzy ART neural architecture, for on-line map building from actual sensor data. This method is then integrated, as a complement, on the parti-game world model, allowing the system to make a more efficient use of collected sensor information. Then, a predictive on-line trajectory filtering method, is introduced in the learning approach. Instead of having a mechanical device moving to search the world, the idea is to have the system analyzing trajectories in a predictive mode, by taking advantage of the improved world model. The real robot will only move to try trajectories that have been predicted to be successful, allowing lower exploration costs. This results in an overall improved new method for goal-oriented navigation. It is assumed that the robot knows its own current world location-a simple dead-reckoning method is used for localization in our experiments. It is also assumed that the robot is able to perform sensor-based obstacle detection (not avoidance) and straight-line motions. Results of experiments with a real Nomad 200 mobile robot are presented, demonstrating the effectiveness of the discussed methods.

This paper introduces a new approach, based on the application of the fuzzy ART neural architecture, for online map building from actual sensor data collected with a mobile robot. This method is then integrated as a complement, on the parti-game learning approach, allowing the system to make a more efficient use of collected sensor information. Also, a predictive online trajectory filtering method is introduced on the learning approach. Instead of having a mechanical device (robot) moving to search the world the idea is to have the system analysing trajectories in a predictive mode, by taking advantage of the improved world model. The real robot will only move to try trajectories that have been predicted to be successful, allowing lower exploration costs. This results on an overall new and powerful method for simultaneous and cooperative construction of a world model, and learning to navigate from an initial position to a goal region on an unknown world. It is assumed that the robot knows its own current world location. It is additionally assumed that the mobile robot is able to perform sensor-based obstacle detection (not avoidance), and straight-line motions. Results of experiments with a real Nomad 200 mobile robot will be presented, demonstrating the effectiveness of the proposed methods.

This paper addresses the problem of learning sensor-based navigation of a mobile robot on, an indoor environment, where the location, size, and shape of obstacles is assumed to be initially unknown to the robot. We use the parti-game multiresolution approach for simultaneous learning of a world model, and learning to navigate from a start position to a goal region on the world. These two learning abilities are cooperating and enhancing each other in order to improve the overall system performance. It is assumed that the robot knows its own current world location. It is only additionally assumed that the mobile robot is able to perform sensor-based obstacle detection (not avoidance), and that it is able to perform straight-line motions. Results of experiments with a real Nomad 200 mobile robot will be presented.

Flexible robotic systems, for example systems to be used in parts assembly automation, require robot manipulators featuring among other capabilities, the capacity of executing reliable fine motions. This requirement leads to the need of using sensors and so to the need of searching for techniques for efficient processing and integration of sensory data. The paper addresses issues regarding the integration of sensors for flexible robotics, namely, force/torque, tactile and proximity range sensors. The authors are concerned with sensory integration for fine motion control, the following subjects being addressed: the architecture of the control system integrating force/torque, tactile and distance sensors and algorithms for position and force control using task-space sensory feedback.>