Search

The appearance of industry 4.0 and the internet of things allowed to shorten the gap between the consumer and the product industry, with the introduction of new digital processes. With this in mind, a project of an electro-pneumatic laboratory prototype to support the teaching of the industry 4.0 concepts was proposed. For the construction of the laboratory system was developed a typical industrial electro-pneumatic process (at scale), for which some support components were constructed using 3D modelling. For the automation part of the this system, the control platform of the programmable logic controller, type of programming language and creation of the code were developed. For the supervision system and remote digital control, the human machine interface is based in web pages using a common web browser, with the possibility of decentralized access in every tablet and smartphone. This prototype was simulated and tested, and it will help in the teaching of the 4.0 industry concepts.

This work addresses the automatic segmentation of the joint capsule in ultrasound images of the metacarpophalangeal joint using an adapted version of the well known UNet model. These images are used in the diagnosis of rheumatic diseases, one of the main causes of impairment and pain in developed countries. The identification of the joint capsule gives important clues about the presence or Rheumatoid Arthritis. This structure can be used to extract metrics to help quantify the disease stage and progression. The solution proposed here has the potential to reduce the burden on the radiologists as well as the subjectivity of the diagnosis by providing quantitative measurements, such as the synovitis area. The proposed approach was compared with two other works present in the literature. Results show that our solution outperforms the two reference methods with 90% of the joint capsules identified with a DICE higher than 0.67.

Rheumatic heart disease remains a major burden in the developing countries. The World Heart Federation proposed guidelines for the echocardiographic detection of the disease, in which the mitral leaflets’ morphology assessment is a key indicator. The drawback is that these guidelines are dependent on the clinician experience. To overcome this limitation, we propose an automatic segmentation of the mitral leaflets using a new method based on convolutional neural network, specifically the UNet architecture. The results indicate a median DICE coefficient of 0.74 in PLAX and 0.79 in A4C for the anterior mitral leaflet segmentation, while median DICE of 0.60 in PLAX and 0.69 A4C are met for the posterior leaflet. A visual evaluation of this segmentation approach by two cardiologists is in line with the numerical results. The false detection due to overestimation and artifacts remains an issue to be addressed in the future.

Rheumatic heart disease is the serious consequence of repeated episodes of acute rheumatic fever. It is the major cause of heart valve damage resulting in morbidity and mortality. Its early detection is considered vital to control the disease's progression. The key manifestations that are visible in the early stages of this disease are changes in the thickness, shape and mobility of the mitral valve leaflets. Echocardiography based screening is sensitive enough to identify these changes in early stages of the disease. In this work, an automatic approach is proposed to measure, quantify and analyze the thickness of the anterior mitral leaflet, in an echocardiographic video. The shape of the anterior mitral leaflet is simplified via morphological skeletonization and spline modelling to get the central line of the leaflet. To analyze the overall thickness from the tip to its base, the anterior mitral leaflet is divided into four quartiles. In ach quartile the thickness is measured as the length of the line segment resulting from the intersection of the contour with the normal direction of the central point of each quartile. Finally, the thickness is analyzed by measuring the variance per quartile, divided by leaflet position (open, straight and closed). The comparison between the normal and pathological leaflets are also presented, exhibiting statistical significant differences in all quartiles, especially near the tip of the leaflet.

In this work a fully automatic system to identify the extensor tendon on ultrasound images of the metacarpophalangeal joint is proposed. These images are used to diagnose rheumatic diseases which are one of the main causes of impairment and pain in developed countries. The early diagnosis of these conditions is crucial to a proper treatment and follow-up and so, a system such as the one proposed here, could be useful to automatically extract relevant information from the resulting images. This work is an extension of a previous published work which uses manual annotations of the skin line, metacarpus and phalange to guide the extensor tendon segmentation. By introducing automatic segmentations of all structures, we expect to create a fully automatic system, which is more interesting to the possible end-users. Results show that, despite an expected loss in the performance, it is still possible to correctly identify the extensor tendon with a Confidence of 88% considering a maximum allowed Modified Hausdorff Distance of 0.5mm.

Nowadays, enterprises in global markets must achieve high levels of performance and competitiveness to stay “alive”. According to several authors and as frequently mentioned by reports of practical case studies, one of the most relevant sources of competitive advantage is the innovation capacity. The identification and quantification of the existing or potential innovation risks in a collaborative environment, is an important element for the wide adoption of the innovation ecosystem paradigm. However, models to understand the innovation risks in a collaborative environment are lacking. To address this issue, this paper introduces an approach based on a qualitative assessment, including a quantitative basis, whose development was supported by fuzzy logic for analyzing the level of risk in co-innovation projects. Finally, based on experimental results from a Portuguese collaborative network, a discussion about the benefits and challenges found are discussed.

This paper presents a mixed-integer linear programming model for a two-stage one-dimensional cutting stock problem that appears in the make-to-order steel industry. In this problem, the ingots in stock must be cut into intermediate pieces (billets) to be heated in a furnace and then molded into a bar with the section indicated in the production order. This bar is then cut to obtain the final bars with the desired lengths. The main objective is to reduce the waste in the production. A heuristic approach to this problem is proposed that can be easily implemented into the industry and produces solutions with an optimal gap less than 10% in our computational results.

Currently, due to the global competitiveness and the need for cost reduction, companies are more and more interested in increasing the availability of their production systems. Moreover, Internet is becoming indispensable for the distribution of information throughout the world, becoming critical to implement distance supervision systems which detect and diagnose faults. Thus, the concepts of Industrial Internet of Things and Industry 4.0 arise, where from a large amount of available information decisions can be quickly taken, preventing the occurrence of faults and failures. For this reason, the system proposed in this paper is an Internet based fault diagnosis system (FDSvI), it has applicability in a wide range of industrial processes and it has been applied and tested on a gantry robot. This system was developed using software like the graphical programming software LabVIEW® using the Datalogging and Supervisory Control LabVIEW module and the OPC Servers for the communication between Siemens® S7-1214C programmable controllers and the fault diagnosis system (FDS).

This work presents a new approach for the iden­tification of the joint capsule in ultrasound images of the metacarpophalangeal joint. These images are used to diagnose rheumatic diseases which are one of the main causes of impair­ment and pain in developed countries. The early diagnosis of these conditions is crucial to a proper treatment and follow-up and so, this work contributes to the automatic extraction of relevant information from the resulting images. The algorithm uses the metacarpus, phalange and extensor tendon positions to create a region of interest. Next, a split and merge approach is used to identify the joint capsule, where the split is done using the Simple Linear Iterative Clustering algorithm and the merge is achieved with a special region growing with shape constraints. After that, the results are refined using a Localizing Active Contours method. Results shown that the segmentation is possible with 60% of the joint capsules identified with a Dice Coefficient higher than 0.7.

The progress of age-related macular degeneration (AMD) can be evaluated through the quantification of drusen. In the literature, drusen are usually located by thresholding the distance between their limiting boundaries. However, Dufour et al. [1] proposed the detection of drusen by using textural features in conjunction with a random forest (RF). In this paper, we extend the work of Dufour et al. by adding new features and by using multi-label classification. The new features are the distance between the limiting boundaries of drusen and the respective wavelet coefficients. The area under the ROC curve (AUC) and Dice coefficient (DC) of our implementation of the method of Dufour et al. were, respectively, 92.03% and 69.72%, while our method obtained 92.81%, 71.88%. Moreover, the proposed method can identify individually drusen present in clusters. The individualized drusen information allows the exploration of new range of metrics that go beyond the total drusen area or volume, such as drusen size, which is used to categorize the stages of AMD. Additionally, we evaluated using automatic segmentations to compute the features. The automatic segmentations were applied in two settings: for test data alone and for both training and test data. The AUC and DC for first situation were, respectively, 92.42% and 71.31% and for the second case were 91.93% and 70.21%. These results suggest that the method is robust to variability of the segmentation of drusen's limiting boundaries.

In the area of medicine, x-rays are very useful to check if the patient suffers from brain death. Their diagnosis is made using free text. This type of record difficult the process of making qualitative analysis in order to automatically detect possible brain problems. This project aims to make qualitatively and quantitatively analysis of Brain Computed Tomography (CT) diagnosis using text analysis tools as is Natural Language Processing and Text Mining. In this work a set of related words that can means patterns in CT reports was detected. The dataset was provided by the Centro Hospitalar do Porto-Hospital de Santo Antonio and it contains information about patient deaths and CT done to the brain. With the analysis made, a new research and analysis perspectives of structured and unstructured texts in this field was opened.

The paper proposes SmartFetch, a storage strategy that relies on a combination of techniques aimed at efficiently supporting selective jobs that are only concerned with a subset of the entire dataset in systems such as Hadoop and Spark. We combine the use of an appropriate data-layout with data indexing tools to improve the data access speed and significantly shorten total job execution time. An extensive experimental evaluation of SmartFetch shows that, by avoiding reading irrelevant blocks, it can provide significant speedups when compared to the basic Hadoop and Spark implementations. Further, our system also outperforms other implementations that use several variants of the techniques we have embedded in SmartFetch.

Rheumatic arthritis (RA) is an autoimmune disease that causes irreversible damage to joints and other physiological structures. The Metacarpophalangeal (MCP) joint is one of the first regions to suffer alterations. These alterations are visible with high frequency ultrasound devices, which are used to quantify inflammatory activity in the MCP due to RA. The accurate segmentation of the bone surface and the identification of the MCP capsule region remains a challenge in ultrasound image processing. In this article we aim to make a contribution to this problem by incorporating prior knowledge of the bone and joint regions anatomy into our segmentation algorithm. The log Gabor filter is used for speckle noise reduction and to extract ridge-like structures from the images, while the phase is left unchanged. After thresholding, scores are generated, based on the intensities and areas of the resulting regions, enabling the selection of the structure that best matches the bone. Finally, segmented joint bones are processed to calculate the initial seeds of joint capsule region. Experimental results demonstrate the accuracy of the proposed segmentation algorithm. The mean pixel error between the automatic segmentation and the reference images were 4.4 pixel. The bone regions not segmented were, on average, 5.4%.

This paper extents the by now classic sensor fusion complementary filter (CF) design, involving two sensors, to the case where three sensors that provide measurements in different bands are available. This paper shows that the use of classical CF techniques to tackle a generic three sensors fusion problem, based solely on their frequency domain characteristics, leads to a minimal realization, stable, sub-optimal solution, denoted as Complementary Filters^3 (CF^3). Then, a new approach for the estimation problem at hand is used, based on optimal linear Kalman filtering techniques. Moreover, the solution is shown to preserve the complementary property, i.e. the sum of the three transfer functions of the respective sensors add up to one, both in continuous and discrete time domains. This new class of filters are denoted as Complementary Kalman Filters^3 (CKF^3). The attitude estimation of a mobile robot is addressed, based on data from a rate gyroscope, a digital compass, and odometry. The experimental results obtained are reported.

Drusen quantification is important for evaluating age-related macular degeneration (AMD) progress. Most methods for retinal layers segmentation in optical coherence tomography (OCT) depend heavily on prior information. This improves robustness, but also has the downside of increasing surface rigidity. Hence, those algorithms normally smooth drusen borders, as significant local variations are not expected. In this work, we propose to integrate sparse higher order potentials (SHOPs) into a multi-surface segmentation framework to cope with local boundary variations caused by drusen. The algorithm was evaluated in a database of 20 patients with AMD. The mean unsigned error for the inner retinal pigment epithelium (IRPE) and Bruch's membrane (BM) was 5.65 +/- 6.26 and 4.37 +/- 5.25 mu m, respectively. These results are relative to the average of two experts, whose inter-observer variability was 7.30 +/- 6.87 mu m for IRPE and 5.03 +/- 4.37 mu m for BM. The use SHOPs resulted in a successful segmentation of the IRPE. The remaining boundaries were also successfully segmented., This work has been supported by FCT (Fundação para a Ciˆencia e Tecnologia) in the scope of the project UID/EEA/04436/2013. J.O. wishes to acknowledge the Portuguese funding institution Fundação Calouste Gulbenkian for the Ph.D. Grant (process 126501) and to ENERMETER - Sistemas de Medição, Lda for their support., info:eu-repo/semantics/publishedVersion

A fuzzy linguistic controller has been developed and implemented with the aim to cope with interactions between control loops due to coupling effects. To access the performance of the proposed approach several experiments have also been conducted using the classical PID controllers in the control loops. A mixing process has been used as test bed of all controllers experimented and the corresponding dynamic model has been derived. The successful results achieved with the fuzzy linguistic controllers suggests that they can be an alternative to classical controllers when in the presence of process plants where automatic control as to cope with coupling effects between control loops.

Mammography is the most used diagnosis method for the breast cancer. The challenge of this exam is to obtain good contrast and resolution with small radiation doses. In recent years, several efforts have been done to improve the detection efficiency of mammograms by using the potential offered by digital image processing. In this work, the potential benefits of applying the wavelet transform for microcalcifications enhancement in the digital mammograms is studied. Several contrast enhancement methods based on wavelets found in literature were adjusted and applied to a digital mammogram dataset. Their performance was evaluated by appropriate quantitative metrics, and the advantages and disadvantages of each them are described in this study. This study represents a good starting point to choose an adequate enhancement method based on wavelet transform for a specific problem.

This paper presents the experimental validation of a new method for mobile robot global self-localization in unstructured environments, i.e. that does not need any beacons or other artifacts structuring the environment. The method resorts to a PCA-based positioning sensor, filtered in a Bayesian probabilistic grid and combined with linear Kalman filters to estimate the global pose of mobile robots. In the implemented system, the information of the environment is captured only with onboard sensors installed in a differential drive robot: encoders, compass, and 2D depth sensor pointed to the ceiling. The use of PCA in a Bayesian probabilistic grid allows to fuse the highly compressed PCA database information, obtained with the low computational effort, in an environment where repetitive scenarios can occur. To avoid the negative impact in the localization estimate caused by the corrupted data existing in the 2D depth sensor, an extension to the classic PCA algorithm is suggested. Thus, the proposed method allows the self-localization of mobile robots in indoor environments with bounded accuracy and working in a wide range of illumination conditions.

The main goal of this paper is to present a visual odometry system, for localization of mobile robot in indoor unstructured environments, using only ceiling depth images, captured by a Kinect sensor. The use of odometric sensors is a common practice for localization of mobile robots. The method proposed in this work exploits information from an independent source of depth data and thus allows to complement or substitute the use of classic odometric sensors, like wheels encoders, with well known limitations. The experimental validation of the proposed solution shows that the method is able to accurately compute the attitude and linear velocities that allow a more precise mobile robot localization, even in presence of corrupted data from the sensor. Furthermore, the method works in an extended range of lighting conditions, without the need to perform any specific feature extraction.

Diabetic retinopathy has been revealed as the most common cause of blindness among people of working age. For monitoring the pathology image registration algorithms applied to retinal images is very useful. In this work, a novel vessel-based retinal image registration approach is proposed. The segmentation of the vasculature is performed by a multi-agent system model. All these information is then used in a Robust Point Matching Iterative Closest Point algorithm improved by a Region Bootstrap approach. With this preliminary study, the novelty of integrating all these algorithms for image registration preceded by a multi-agents system for image edges detection seems to be efficient for temporal retinal image registration. Consequently, a system developed on basis of this approach could help in screening programs for the diabetic retinopathy prevention.

Most autistic people present some difficulties in developing social behavior, living in their own world. This study has the goal to improve the social life of children with autism with a main focus in promoting their social interaction and communication. It is necessary to call for children’s attention and enforce their collaboration, where a robot, LEGO MindStorm, behaves as a mediator/promoter of this interaction. A set of experiments designed to share objects and fulfill simple orders, by the 11 years old autistic child at the time of daily routine work and in-game with the robot, are described. The generalization of the acquired skills by the child in new contexts and environments are also tested. Results are described showing the outcomes of the experiments., Fundação para a Ciência e a Tecnologia (FCT) - R&D projecto RIPD/ADA/109407/2009

Presently, the mainstream approach to appearance-based localization with local features uses a quantized representation. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity and information content properties. Having demonstrated the advantages of the non-quantized representation, the paper proposes a localization method based on it, and mechanisms to reduce the computational burden this approach would carry, if taken straightforwardly. This reduction is achieved with context cues provided by gist and by exploring two simplifying assumptions about the training data.

This paper presents a gait multi-objective optimization system that combines bio-inspired Central Patterns Generators (CPGs) and a multi-objective evolutionary algorithm. CPGs are modeled as autonomous differential equations, that generate the necessary limb movement to perform the required walking gait. In order to optimize the walking gait, four conflicting objectives are considered, simultaneously: minimize the body vibration, maximize the velocity, maximize the wide stability margin and maximize the behavioral diversity. The results of NSGA-II for this multi-objective problem are discussed. The effect of the inclusion of a behavioral diversity objective in the system is also studied in terms of the walking gait achieved. The experimental results show the effectiveness of this multi-objective approach. The several walking gait solutions obtained correspond to different trade-off between the objectives., This work is funded by FEDER Funding supported by the Operational Program Competitive Factors - COMPETE and National Funding supported by the FCT - Portuguese Science Foundation through project PTDC/EEACRO/ 100655/2008. Thanks to Dr. St ? ephane Doncieux from the Institut des Systmes Intelligents et de Robotique (ISIR) of the Pierre and Marie Curie University (UPMC)

SAFE-PORT is a recently started project addressing the complex issue of determining the best configurations of resources for harbour and port surveillance and protection. More specifically, the main goal is to find, for any given scenario, an adequate set of configuration solutions - i.e., number and type of sensors and equipments, their locations and operating modes, the corresponding personnel and other support resources - that maximize protection over a specific area. The project includes research and development of sensors models, novel algorithms for optimization and decision support, and a computer-based decision support system (DSS) to assist decision makers in that task. It includes also the development of a simulation environment for modelling relevant aspects of the scenario (including sensors used for surveillance, platforms, threats and the environment), capable to incorporate data from field-trials, used to test and validate solutions proposed by the DSS. Test cases will consider the use of intelligent agents to model the behaviour of threats and of NATO forces in a realistic way, following experts' definitions and parameters.

Nowadays the common use of biological information in forensic identification not only allows to consider its use as a regular piece of evidence but also opens new perspectives for more complex cases. In any paternity dispute case in which the genetic profiles of the mother (mgt), the child (cgt) and the putative father (pfgt) are available, most of the times, there is no doubt about the use of this kind of evidence. Here the objective is to discuss problems of disputed paternity for which there is no biological information about the putative father. The data sets considered are composed of biological information of the mother, of the child and of one or more individuals genetically related with the putative father. In the cases mentioned here the biological information is obtained from brothers of the putative grandfather. The objective is to compare the only one ancestor cases results and the ones in which it is possible to have more than one ancestor. Although these are not the most common situations there is notice of their occurrence in Portuguese courts.

Intelligent Systems require the ability to reason with incomplete information, because in the real world complete information is hard to obtain, even in the most controlled situation. In recent years, many formalisms have been proposed tacking the matter of uncertain, incomplete in logic programs and databases. However, qualitative models and qualitative reasoning have been around in Artificial Intelligence research for some time, in particular due the growing need to offer support in decision-making processes. The evaluation of knowledge that stems out from logic programs becomes a point of research. The Quality-of- Information concept demonstrated their applicability in many dynamic environments and for decision making purposes. In this paper we present an illustrative example of the inference process in decisions in healthcare environments. Under the Extended Logic Programming paradigm to knowledge representation and reasoning, we present the evolutive perspective of the inference process to achieve logical programs (or theories) corresponding to the best theorems to solve a problem or take a decision. For the evaluation of the best theories we use a quantification of the quality-of- information that stems out from a logic program., (undefined)

Traffic flow, analysis and control is gaining high relevance, as the number of circulating vehicles continuously increases. This article proposes a computer vision based platform, which automatically detects vehicles in order to infer the traffic conditions. The developed real time detection algorithm is based on a dual background subtraction technique, incorporating the one known has Codebook and an edges one. These two layers interact mutually allowing the compensation of individuality weaknesses. The traffic flow parameters are extracted comparing the detected vehicles with a known model of the road lanes, which can be automatically generated based on the vehicles trajectory analysis over time. The achieved results demonstrate that the developed algorithm is able to correctly understand the traffic flow state, even in the presence of adverse situations that are typical of an outdoor application.

This article presents a system developed for the industry of bottling beer. The system has to perform the inspection of various items in the final stage, meaning after the production phase where the bottles are already in the crate. The items to inspect are the following: whether the crate is correct (with the correct color), whether the crate is broken, whether the crate is fully populated, i.e., all bottles are present, to check for bottles without caps and whether the capsule is the correct one. The work uses techniques of computer vision for these verifications and also principal components analysis (PCAs) for the recognition of the capsules. This system is currently installed in the assembly line and the results indicate high efficiency and confidence in the obtained solution.

Autonomous adaptive locomotion over irregular terrain is one important topic in robotics research. In this article, we focus on the development of a quadruped locomotion controller able to generate locomotion and reaching visually acquired markers. The developed controller is modeled as discrete, sensory driven corrections of a basic rhythmic motor pattern for locomotion according to visual information and proprioceptive data, that enables the robot to reach markers and only slightly perturb the locomotion movement. This task involves close-loop control and we will thus particularly focus on the essential issue of modeling the interaction between the central nervous system and the peripheral information in the locomotion context. This issue is crucial for autonomous and adaptive control, and has received little attention so far. Trajectories are online modulated according to these feedback pathways thus achieving paw placement. This modeling is based on the concept of dynamical systems whose intrinsic robustness against perturbations allows for an easy integration of sensory-motor feedback and thus for closed-loop control. The system is demonstrated on a simulated quadruped robot which online acquires the visual markers and achieves paw placement while locomotes.

This article introduces the progresses made on the development of an automatic visual inspection for automotive metal components. These components may present three types of defects, which are: central hole closed or partially closed; absence of thread on the bolts; burr on the weld connections. For each type of defect different image processing and analysis algorithms were tested and a specific setup (type and pose of the cameras and illumination) was developed. The results suggest a good efficiency of the vision system and its potential full spreading industrialization.

This paper describes the development of a project based on fuzzy logic applied to color histograms for color grading wood boards. During this development a fuzzy min-max inference system, with bell membership functions adjusted to the histogram, was implemented and evaluated. This system performs image matching. Images given as training samples are used to define the classes that determine the several wood board color intervals. In that way the system is capable to classify an image by its color in order to group wood boards with the same tonality-color in a short period of time.

This paper presents the framework of an interface between wireless sensor networks and personal devices like PDAs, cellular phones and laptops. It possesses a flexible architecture that can be adapted easily to display any kind of data received from the network sensors using content description. The most relevant properties of this system are: portability (it can be used on any device with a standard browser), expandability (it can act as a gateway for higher systems), adaptability (the information can be presented in many different ways) and scalability (several sensor networks can be controlled at the same time). This system is currently being used display information retrieved from a Bluetooth based wireless sensor network platform which operates onboard of an unmanned aerial vehicle (UAV).

This paper presents an approach for image texture segmentation based on the wavelets transform and on a fuzzy grammar inference system. It was developed for the Portuguese cork industry, specifically for the quality control in the cork parquet sector. The main purpose was to deal with major quality issues related with texture features. The segmentation procedure reveals a good performance indicated by high classification rates. This approach was integrated in a vision system leading to an industrial prototype that has already been tested, revealing good perspectives of full industrialization.

This paper addresses a system for fast object tracking based on texture cues, by using the wavelet transform and a fuzzy grammar classifier. The method is based on wavelet type features. The feature vector consists of 6 characteristics extracted from the wavelet detail images for each colour component. These texture characteristics automatically generate a fuzzy rule using a fuzzy inference classifier based on a fuzzy grammar. A learning phase is required for each texture but only uses one sample. This 2D tracking system of textured objects in image sequences is demonstrated on a robotic application using the platform developed by Sony – AIBO robot. The application ensures a real time tracking approach and can be parameterized in order to be flexible in face of different types of textures.

In this work a hybrid technique that includes probabilistic and optimization based methods is presented. The method is applied, both in simulation and by means of real-time experiments, to the heating unit of a heating, ventilation air conditioning (HVAC) system. It is shown that the addition of the probabilistic approach improves the fault diagnosis accuracy.

This article addresses the problem of generating timed trajectories and temporally coordinated movements for two wheeled vehicles, when relatively low-level, noisy sensorial information is used to steer action. The generated trajectories have controlled and stable timing (limit cycle type solutions). Incoupling of sensory information enables sensor driven termination of movement. We build on a previously proposed solution in which timed trajectories and sequences of movements were generated as attractor solutions of dynamic systems. We present a novel system composed of two coupled dynamical architectures that temporally coordinate the solutions of these dynamical systems. The coupled dynamics enable synchronization of the different components providing an independence relatively to the specification of their individual parameters. We apply this architecture to generate temporally coordinated trajectories for two vision-guided mobile robots in a non-structured simulated environment, whose goal is to reach a target within a certain time independently of the environment configuration or the distance to the target. The results illustrate the robustness of the proposed decision-making mechanism and show that the two vehicles are temporal coordinated: if a robot movement is affected by the environment configuration such that it will take longer to reach the target, the control level coordinates the two robots such that they terminate approximately simultaneously.

We present an attractor based dynamics that autonomously generates temporally discrete movements and movement sequences stably adapted to changing online sensory information. Autonomous differential equations are used to formulate a dynamical layer with either stable fixed points or a stable limit cycle. A neural competitive dynamics switches between these two regimes according to sensorial context and logical conditions. The corresponding movement states are then converted by simple coordinate transformations into spatial positions of a robot arm. Movement initiation and termination is entirely sensor driven. In this article, the dynamic architecture was changed in order to cope with unreliable sensor information by including this information in the vector field. We apply this architecture to generate timed trajectories for a Puma arm which must catch a moving ball before it falls over a table, and return to a reference position thereafter. Sensory information is provided by a camera mounted on the ceiling over the robot. We demonstrate that the implemented decision-mechanism is robust to noisy sensorial information. Further, a flexible behavior is achieved. Flexibility means that if the sensorial context changes such that the previously generated sequence is no longer adequate, a new sequence of behaviors, depending on the point at which the changed occurred and adequate to the current situation emerges.

In this work, a fault-tolerant control scheme is applied to a air handling unit of a heating, ventilation and air-conditioning system. Using the multiple-model approach it is possible to identify faults and to control the system under faulty and normal conditions in an effective way. Using well known techniques to model and control the process, this work focuses on the importance of the cost function in the fault detection and its influence on the reconfigurable controller. Experimental results show how the control of the terminal unit is affected in the presence a fault, and how the recuperation and reconfiguration of the control action is able to deal with the effects of faults.

This paper presents an application independent embedded platform for a wireless distributed data acquisition and control system, and describes its application in the scenario of controlling the information processing and communications between sensors and actuators onboard of an autonomous flying robot, in a “fly-by-wireless” approach. The system, which was designed and implemented, comprises a set of nodes composed by microcontrollers, wireless communication modules based on Bluetooth technology, and sensing/actuation devices. This paper also presents several experimental results which denote encouraging performance characteristics for the developed system, not only in the context of the proposed application, but for other wireless applications as well.

Desktop robots are suitable for various production line systems in industrial applications like dispensing, soldering, screw tightening, pick'n place, welding or marking. Despite their capabilities to meet diverse requirements, they have to be programmed off-line using way points and path information. Misalignments in the workspace location during loading cause injuries in the workpiece and tool. Further, in modern flexible industrial production, machinery must adapt to changing product demands, both to the simultaneous production of different types of workpieces and to product styles with short life cycles. In this paper, visual data processing concepts on the basis of fuzzy logic are applied to enable an industrial desktop robot to raise its flexibility and address these problems that limit the production rate of small industries. Specifically, a desktop robot performing dispensing tasks is equipped with a CCD camera. Visual information is used to autonomously change previously off-line stored robot programs for known workpieces or to call worker's attention for unknown/misclassified workpieces. A fuzzy inference classifier based on a fuzzy grammar, is used to describe/identify workpieces. Fuzzy rules are automatically generated from features extracted from the workpiece under analysis. Regarding the evaluation of the system performance, different types of workpieces were tested and a good rate performance, higher than 90%, was achieved. The obtained results illustrate both the flexibility and robustness of the proposed solution as well as its capabilities for good classification of workpieces. The overall system is being implemented in an industrial environment.

A nonlinear regression structure comprising a wavelet network and a linear term is proposed for system identification. The theoretical foundation of the approach is laid by proving that radial wavelets are orthogonal to linear functions. A constructive procedure for building such models is described and the approach is tested with experimental data.

This paper presents a qualitative reasoning approach for rule based controllers design. Through the proposed methodology the controllers are designed based on causal relationships between subsystems, and the control actions are inferred from samples of both controlled and noncontrolled variables. These causal relationships form a heuristic model of the system. Based on the heuristic model and the current state of the process, control actions can be inferred. Moreover, instead of continuous real-valued variables the process variable behaviour is represented through its qualitative values. In order to facilitate the relationships analysis among process variables a systematic methodology for description of system structures is proposed. These techniques have been successfully applied in simulation studies of a mixing process.

In this paper a hierarchical structure of fuzzy neural networks (FNNs) and how to train it for fault isolation given an appropriate data patterns, are presented. Fault symptoms concerning multiple simultaneous faults are harder to learn than those associated with single faults. Furthermore, the larger the set of faults, the larger the set of fault symptoms will be and, hence, the longer and less certain the training outcome. In order to overcome this problem, the proposed approach has a hierarchical structure of three levels where several FNNs are used. Thus, a large number of patterns are divided into many smaller subsets so that the classification can be carried out more efficiently. One of the advantages of this approach is that multiple faults can be detected in new data even if the network is trained only with data representing single abrupt faults. A continuous binary distillation column having several actuated valves with PID loops has been used as test bed for the proposed approach.

An on-line fault detection and diagnosis system, which has been designed to cope with transient behaviours of the process, is described in this paper. The system consists of a knowledge based approach coupled with a hierarchical structure of fuzzy neural networks. Fault detection is performed through the knowledge based system. The hierarchical structure of fuzzy neural networks performs the fault diagnosis task. The aim of this approach is to diagnose multiple simultaneous faults from only single fault symptoms. A chemical process has been used as a test bed of the current approach.