Digital twins (DTs) for tower crane operations support task simulation before execution, prediction of movement trajectories, and hazard alert generation for nearby personnel and surrounding structures. These capabilities improve situational awareness and support operator decision-making in real-time. To implement such DT systems, suitable simulation platforms should balance modeling accuracy, computational requirements, and integration with sensing and control components. This paper benchmarks two widely used platforms—NVIDIA Isaac Sim and Gazebo—focusing on their applicability to resource-constrained, real-time environments. We evaluate GPU resource usage, including processing load, memory consumption, power draw, and overall performance. Results show that while Isaac Sim achieves higher frame rates (82 FPS), it consumes significantly more power (175W), whereas Gazebo, operating at 75 FPS, demonstrates much higher performance per watt, achieving 2.89 FPS/W compared to Isaac Sim’s 0.47 FPS/W. These results suggest Gazebo can have practical advantages for deploying lightweight, energy-efficient DTs in crane operations.

Digital Twin (DT) technology creates virtual replicas of physical systems for monitoring and optimization. This papers investigates the effects of DT simulations on GPU systems, evaluating processing, memory usage, and power consumption. It shows that adjusting rendering quality can improve performance. It also demonstrates the importance of optimizing energy consumption and performance for sustainable deployment, highlighting advancements in GPU technology and energy management.

An area of robotics, assistive robotics, has been growing rapidly with recent advances in computing, control systems and instrumentation. Physio therapeutic procedures like gait rehabilitation and learning are often used for teaching and recovery of people with disabilities, especially children with cerebral palsy (CP), as the reinforcement of mobility is fundamental for the health and subsequent independence of the patient. These processes can benefit from assistive technologies to expedite the treatment, reducing physical strain of physiotherapists, increasing the efficiency of techniques and promoting better precision and repeatability for therapeutic movements. This paper presents the modeling and control of an omnidirectional mobile platform for applications in assistive robotics, aiming to expand this paradigm to incorporate greater possibilities of movement during the rehabilitation process. For this to be realized, the paper discusses questions such as the effects of holonomic approximations on dynamic modeling, proposes a control architecture, and introduces a physical prototype in the form of a low-cost generalized omnidirectional robotic platform integrated in ROS.

Demand for ocean-based high-quality and sustainable fish protein soared in the last decade. Unlike precision agriculture, aquaculture remains an under-equipped farming activity. The aquaculture industry has provided remarkable contributions to the Sustainable Development Goal of zero hunger based on providing animal-based protein for human consumption worldwide. The success of the aquaculture industry hinges on appropriate monitoring of key water quality indicators to ensure both animal health and optimal productivity. In this context, the present work presents a cloud-based LoRaWAN system for quasi-real-time tracking of essential water quality parameters by integrating Internet of Things (IoT) sensor devices. The proposed approach harnesses the power of Long Range (LoRa) technology - especially the LoRa Wide Area Network (LoRaWAN) protocol - to facilitate efficient, large-scale monitoring focusing on data security and scalability. With practical insights drawn from IoT system deployment at an industrially relevant aquaculture farm in Brazil, this research provides a comprehensive look into the system's capabilities, drawbacks, and end-user feedback, offering a blueprint for future aquaculture innovations.

Advanced technological solutions are needed to improve the control and prediction of incidents, promoting a safer work environment. Cargo handling operations are critical in sectors such as construction, shipping, and manufacturing, but they pose significant safety risks due to the dynamic and unpredictable nature of load motion. Dynamic modeling has emerged as a valuable tool in the industrial context, allowing for the simulation and analysis of various factors over time. This approach provides a detailed understanding of risk elements, such as excessive workload, training deficiencies, and inadequate equipment maintenance. It also facilitates the evaluation of intervention strategies without real risks, such as implementing training programs and new safety procedures. This paper addresses improving the safety and efficiency of cargo handling operations through the integration of kinematic and dynamic systems modeling, Inertial Measurement Unit (IMU)11Intelligent 9-axis absolute orientation sensor from Bosch©sensors, and Robot Operating System (ROS)22https://www.ros.org. The proposed system aims to predict load movement, monitor in real-time, validate and improve prediction accuracy, and enhance safety through predictive maintenance and operational adjustments.

This article reviews computer vision technologies for detecting and tracking objects in industrial cargo handling activities. We have proposed a dataset and a methodology for identifying people, containers, cages, equipment, boxes, and piping, in real-time operation. Our experimental results demonstrate that our artificial neural network model effectively detects and segments objects in non-sparse environments using an annotated industrial image dataset, achieving average precision up to 95% for most classes, including 93% of test instances. This improved perception capability enhances operators' decision-making and accident prevention.

Despite the critical role of fertilizers in modern agriculture, the lack of properly labeled datasets has significantly hindered advancements in automated fertilizer analysis. To address this gap, this paper introduces three novel datasets tailored for the development and validation of fertilizer detection and classification systems. First, a synthetic dataset is generated using a surface simulator that combines images of individual fertilizer grains, providing a highly controlled yet diverse data source for preliminary algorithm testing. Second, a controlled environment dataset is created under optimal yet realistic conditions to offer a balance between controlled experiments and applicability in natural settings. Third, a real-environment dataset is compiled under challenging field conditions, which presents the complexities of real-world agricultural data collection. Together, these datasets not only enhance the training and testing of machine learning models but also pave the way for substantial improvements in precision agriculture by enabling more accurate and efficient fertilizer management. This paper details the creation, characteristics, and potential applications of these datasets, aiming to set a new standard for dataset quality and utility in agricultural research.

Fisheries and aquaculture industries notably contribute to animal-source protein production worldwide. Climate change is creating environmental conditions suitable for harmful algal blooms (HAB) on a global scale. Some phytoplankton species can also release toxins, which may cause large-scale marine mortality with knock-on effects on coastal economies. Reliable phytoplankton monitoring and early HAB detection are also essential in climate-resilient solutions for aquaculture applications. Currently, phytoplankton monitoring is primarily based on traditional microscopy. However, it is time-consuming and requires an experienced taxonomist. There is a need to expedite and automate phytoplankton monitoring to support aquaculture industries. Analytical instruments based on microscopy coupled with artificial intelligence (AI) models may be vital to monitoring applications. Digital plankton data sets are usually imbalanced and reflect natural environmental differences. The lack of data to represent minority species/genera prevents AI models from understanding some taxa completely. It compromises system reliability for HAB monitoring applications. The present study investigates state-of-the-art models for class imbalance problems tailored for HAB monitoring within multi-trophic aquaculture farms from Brazil, South Africa, and Scotland. A unified benchmark database covering publicly available microscopic image-based datasets supported phytoplankton modelling. AI deep collaborative models and threshold moving techniques provided the best results compared to standard architectures. It prevailed, especially for low-abundant yet toxic organisms.

Technological progress is allowing for a more efficient and safe crane operation, reducing the risks associated with heavy machinery use in construction and logistics industries. To enhance crane operations, this study aims to develop a collision-free path planning model for crane manipulation.To accomplish this, we have created a simulation environment that serves as a digital twin of the physical crane operating environment, employing reinforcement learning (RL) techniques, where the agent learns to improve its performance by interacting with the operating environment. We evaluated two different reward methods for our Deep Deterministic Policy Gradient (DDPG) algorithm: an adapted method and a proposed method. Our results indicate that the proposed reward method yielded superior training performance compared to the adapted method. These results demonstrate the potential benefits of implementing the proposed reward method in crane operations.

The corrosion inspection process in ship tanks used by the oil industry for the production, storage, and disposal of oil, which is known as Floating Production Storage and Offloading (FPSO), is predominantly manual. It requires a long production downtime, and is an unhealthy job for inspectors. In the literature, some works proposed methods for corrosion segmentation. However, none of them classifies the level of corrosion in accordance with the International Association of Classification Societies (IACS) standard. This work proposes the use of U-Net-based network for segmentation of pitting corrosion, and also provides a corrosion level analysis algorithm relating the identified pitting to the IACS standard. Furthermore, data augmentation methods are adopted to make the dataset more diversified, aiming to generalize the neural network learning. The results indicate a mean squared error of only 0.1639 using the proposed method, and an intersection-of-union of 0.9453. In addition, we compared our method with classical methods such as Canny, Laplacian, Otsu, and Sobel methods, where a relevant advantage is obtained with U-Net.

This complete work on innovative practices, presents the proposal of a hybrid model between Problem-Based Learning (PBL) and the SCRUM agile project management framework, which seeks to facilitate the control and management of the teaching process, during the activities of students’ learning, in the face of difficulties still encountered such as: I. material support; II. students’ responsibility in the task; III. division of tasks; and IV. contribution and performance in tasks. We carried out a case study to validate the proposal, including SCRUM practices (such as the structure of the Daily Scrum), during the performance of PBL activities in an undergraduate class in Software Engineering, during the second semester of 2019. To investigate what was accomplished and discuss its results, we used the technique of Discourse of the Collective Subject (DCS) as a way to capture the impression of the students who participated in the study. Through the study of the resulting DCS, it was possible to identify that SCRUM practices enhanced the PBL process with regard to the control and management of teams in the projects developed in the discipline, which allowed us to conclude the adequacy of the proposed model and its potential to contribute to the student’s teaching-learning process.

This paper presents a programming exercise recommender system based on the Student’s Multiple Abilities and Skills (SMAS) model, which is developed from Item Response Theory and Elo System Classification, for estimation of multiple student’s abilities. This model assumes that programming exercises have many ways to be solved (paths) and each path requires different abilities from the student. To evaluate the recommender system, an experiment was conducted in a class of Algorithms and Data Structures I. For this study case, the recommender was connected to an Online Judge system that had a programming problem base. The results show that the proposed recommender has the ability to indicate relevant problems according to the student’s abilities.

This article presents a multi-skills estimation model for students using Online Judge systems. It is understood that there is not only one way to solve programming problems; and, for each solution form, a skill set is needed for the solution to be successful. The proposed model is based on performance expectations and integrates the Elo model, to estimate student’s abilities and problems, to the Multidimensional Item Response Theory model, which estimates the probability of success for each solution path. To validate the proposed model, a case study was carried out with students from the computing area, who solved problems on the beecrowd Online Judge platform. The proposed model was applied to the generated database. According to these results, it is observed that, in cases where the students got the solution right, more than 60% of the paths chosen by students are in accordance with paths indicated by the proposed model.

The present work presents an artificial neural network architecture for the restoration of images damaged by underexposure and overexposure. The problem is relevant in computer vision applications that are applied in conditions where the limitation of the sensor prevent the scene details from being adequately represented in the captured image. This research presents an attention-based architecture composed of two convolutional neural networks, where one performs a preprocessing of the input image, while the other performs the restoration and enhancement of the degraded image. Regarding the evaluation of research results, a broad range of image quality metrics is used to assess the quality of the results produced by the model. The obtained results indicate that the proposed architecture is able to enhance images damaged by exposure heterogeneity, offering gains over state-of-art models in real data.

Fertilizers are fundamental compounds to balance nutrients in the soil, ensuring its fertility for food production. In the industry of fertilizers, a common task is the overhaul of the pipelines that convey the material through production lines, which need to be performed periodically, to avoid duct blockages. Traditionally, this task is carried out manually, which requires interruption of production. Therefore, it implies time consumption and waste of money, in the case of unnecessary inspection. To avoid needless production stoppage, in this paper is presented a non-invasive overhaul method for sediment detection in the pipelines of fertilizer production lines based in neural networks. The proposed model uses thermal images to estimate the volume of sediments into pipelines. Furthermore, as it is difficult to obtain images of several pipeline blockage conditions, a methodology for artificial dataset creation is also provided. The results indicate the feasibility of the proposed methodology.

The process of size analysis of grains in the fertilizer industry is slow, because it is performed by sieves. As an alternative to this mechanized process, digital image techniques have been used to segment and analyze particles in the quality analysis of the grains. However, most deterministic methods for image segmentation do not present high performance when there is no background in the scene, which provides the contrast with the object to be segmented. Furthermore, these methods only ensure its accuracy for segmentation of the objects class considered in the algorithm calibration. Therefore, taking into account this constraint and the great variety of grain size in the fertilizer production process, this paper proposes to use a neural network, U-net, for generalization of grain segmentation, considering a fully covered surface scene, where there is no background. Besides, to show the advantages of proposed solution, a comparison of neural network with deterministic methods is also provided.

Discharges of treated industrial wastewater may impair the receiving surface water quality. Biological early warning systems (biosensors) for continuous holistic water quality monitoring may better tackle the wide range of potential threats from industrial activities (e.g. oxygen depletion, metal traces, chemical toxins). Commercial biosensor solutions based on mussels and oysters behavioural assessment have enabled overall water quality monitoring of industrial effluents. Although burrowing clams present worldwide ecological and economic importance and their behavioural changes are potential indicators of concerning environmental conditions, current technologies do not allow their use as biosensors. Proposing an experimental monitoring setup and comprehend the behavioural patterns of burrowing clams in different water quality conditions are the first steps towards reliable biosensor solutions for water quality assessment. The present work proposes an vision-based tool to assess clams’ behavioural patterns in different levels of water contamination. It may be basis for building holistic biosensor technology based on clams behavioural assessment for industrial effluent monitoring and early alarm. The proposed system measures the total occupied area by animals through a data acquisition system and data processing pipeline. An off-the-shelf camera setup registers top-view images of the animals inside a container. An image segmentation algorithm properly identify the clams and enables behavioral assessment. System suitability is explored in a case study using the yellow clam Amarilladesma mactroides and DCOIT contaminant. The performance of a Watershed and a machine learning segmentation models are investigated. Obtained results indicate both models can achieve high performance in this task. Behavioural tracking stage enables the use of statistical functions to observe behavioural changes in the animals, which may be proxy to overall water quality condition.

This Research to Practice Full Paper presents a proposed model to estimate the multiple skills of students in massive online environments that provide programming exercises, whose assessment methods occur automatically without human intervention. The proposed model is based on the M-ERS model and incorporates, from the TrueSkill model, the uncertainty regarding the student's skills. To validate the model, a database from the URI Online Judge platform was used and the M-ERS and TriMElo models were applied to compare the performance and behavior of the two models. The empirical results show that the proposed model updates student's skills more smoothly, according to the correctness or error of the exercise, according to the uncertainty of the skills.

This Full Paper in the category Research-to-Practice presents a proposed model for assessing source codes through static analysis, an applied experiment and results. The presence of computation is constantly growing in the contemporaneous world, and in that way, the demand for professionals capable to develop and maintain software is also in constant growth. The present work aims to present and discuss the results obtained by applying the proposed model based in TFIDF to a dataset. Results showed that by enabling the comparison of different skills present on each source code, the proposed model offers an asset for teachers to identify potential weaknesses on a student's set of computer programming skills, and therefore be able to work on solutions for their educational development.

This Innovative Practice of a Full Paper presents new ways of teaching classes. The teaching methodology of the algorithm disciplines of the first years of Computer Engineering courses directly affects student performance throughout the course. The current education system is in transition, taking slow steps in new ways of learning. By promoting self-reflection and critical thinking, students can develop problem-solving skills and observe an application of the tools learned. A proposed methodology includes new structuring of the discipline "Algorithms and Data Structures I" at the Universidade Federal do Rio Grande (FURG), with the learning of a modern programming language and the transformation of the classic classroom model to new methods and dynamics. Computational thinking is fundamental at the beginning of the course. From this, all students receive a introduction course at the beginning of the college year to immerse in dynamics to practice logic. Classes began, students received an extension to the basic learning of the discipline (the fundamentals of algorithms and Python as a modern programming language) and at the same time they received an assignment, a problem resolution, where they had space and time to develop a game with the theme of their choice. The activity requires teamwork and creativity. As lectures run as workshops, allowing collaboration and project creation, with the help of teachers and older students as tutors. To complete the program, an event made available by the university was used as an environment, for visitors, scholars as well for high school juniors interested in software, to attend and learn about. As a preliminary result of the new implementation methodology, after 4 years, there was an increase in the approval and average grade of learners.

This research presents a work in which we identify and systematize how the vertiginous growth of social media allows the monitoring of public opinions, with a special focus on analyzing the feelings of the population's opinionated arguments about Education. We have brought together different methods in order to produce better results for the classification and summarization of various documents considering education as the basis of analysis. The proposed model is based on the steps of i) classification of patterns based on Deep Learning; ii) analysis of contexts and visualization of different associative paths in publications through the Implicative Statistical Analysis; and iii) validation of opinion abstracts. The results presented in this study refer to the database made up of 42,062 publications related to the city. The collective social discourses, resulting from the analysis of the summarize the opinions of 820 posts that presented representative terms for the education axis in the negative polarity, of the total of 975 posts classified by the dataset.

In this full paper, research to practice, we present a classroom experience, in which we apply a teaching personalization model in an introductory computer science class. Students in this discipline are freshmen at the university and have different backgrounds related to solving programming problems. The traditional approach is standardized, tending to not serve each student in the best way and that is why we have adopted this group as a case study. We use the ELO-based model to recommend specific learning objects for each student, in order to match the student's ability with the difficulty of the problem. The learning objects correspond to programming problems in an online platform for automatic submission and evaluation. The experiment was divided into three stages. In the first, the student was able to freely choose problems from the platform repository. In the second stage, problems were randomly recommended (as a control). In the third stage, the recommendation was made using the model adopted. Students were encouraged to give feedback on their experience described in a free text and in the labeling of hashtags about the learning object. In addition, the rates of success, error, withdrawal and the frequency of access to the online platform were also collected. We observed that the students had a higher engagement (in terms of a higher frequency of use, a higher hit rate, and the production of positive feedbacks) at the stage when the recommendation matched the proposed model.

This Research to Practice Work in Progress paper presents a proposal for source code assessment through static analysis. The presence of computation is constantly growing in the contemporaneous world, and in that way, the demand for professionals capable to develop and maintain software is also in constant growth. The present work aims to develop a model where teachers can identify potentially weakness on student's set of skills for programming, and therefore be able to work on solutions for their educational development. Preliminary results show that it is possible to identify prominent skills used to solve a given problem, but also that it is possible to compensate the lack of those skills with others.

This complete article, from the research to practice category, presents an experiment carried out combining two models used to evaluate student skills, ELO Multidimensional and M-ERS. The objective of this experiment is to estimate and map the history of their multiple skills, in that way it was carried out incorporating the characteristic of the Multidimensional ELO - to track the history of multiple skills, and M-ERS - to estimating multiple skills that can be compensatory. To validate the experiment, we used a database composed of user submissions from an Online Judge platform from Brazil. Through the experiment results obtained, we concluded that for online programming problems platforms, the combination of both models proved to be satisfactory, through it was possible to map and observe the evolution of student's multiple skills.

The production of food for all the population in the world became the biggest concern. The population continues to grow and the number of farmable lands has been decreasing. To make the lands more productive, fertilizers are used on a larger scale. To guarantee the quality of the product, particle size analysis are made by mechanical sieving. With the time, the wear-out of the sieving in the fertilizer industry the results of the particle size analysis will be erroneous. So the computer vision appears as an alternative that is non-invasive and less time-consuming. In this context, this paper has the objective to develop a grain surface simulator capable of generating virtual images with overlapping grains, since there is a difficulty to obtain annotated data of images of fertilizers. In order to validate the proposed simulator using a DIP algorithm, noises are added in the virtual images to compare with the reality in the industry, to show how well the particle size analysis with computer vision were handled towards adversities. The results of the overlapping analysis show that when the virtual image has a fewer number of grains, the DIP algorithm can identify the majority of grains, consequently with less error in the particle size analysis. Different noises, at different intensities, have their effects analyzed on the algorithm. As the analyzes in this study match with the reality showing the consequences, tendencies, and errors of the overlapping of grains and noises in the images, the simulator developed here matches with reality and is extremely useful to facilitate the study of complex cases of application of visual computing and digital image processing in particle size analysis of fertilizers.

Even though the oil industry importance is notable, oil exploitation may cause impairment of aquatic organisms due to the risk of oil spills. In this context, the development of low-cost and effective aquatic pollution sensors has paramount importance. The present study proposes the association of Nonlinear Autoregressive (NAR) neural network and Exponentially Weighted Moving Average (EWMA) control chart in the behavioral analysis of Perna perna mussels. Bivalve mollusks were instrumented with hall effect sensors and magnets, maintained under controlled environmental conditions and exposed to different concentrations of diesel S-500 Water-Accommodated Fraction. Behavioral data were acquired before (3 days) and along (44 hours) toxicological exposure. NAR neural network was used to forecast the Average Opening Amplitude (AOA) of Perna perna mussels under a non-toxicological environment. It was effective in predicting non-exposed behavior of mussels and allowed to consider individual's adaptive nature. EWMA control chart was employed to evaluate the residues among neural network forecast and experimental AOA. The exposure of bivalves to diesel WAF provided a discrepancy among the predicted and experimental AOA. Hence, EWMA control chart has provided out of control (unpredictable) values throughout the toxicological exposure period. The association of NAR neural networks and EWMA control charts is a potential tool in online monitoring of aquatic environments and considers individual peculiarities of each bivalve which leads to the development of more accurate aquatic pollution biosensors.

The continuous growth of the naval and offshore industries require that the processes be steady and reliable, forcing the industries to keep up and dealing with the most modern methods of development. Among these processes, the welding is one of the most commons that has been used widely in the construction of oil platforms. The welding is used in many areas, beyond the naval, it being dangerous for the welder because the surroundings contain fumes and radiation. Once the welding is an usual procedure and the surroundings of the work space can be harmful to human's health, bring more automation for the welding process can improve the productivity levels and move human operators away from danger. However in the naval industry the projects are individualized, making the process of implementation of robotic cells difficult. Using modular robots turn the weld more reliable but are not a optimal solution due it still need a human operator near the process to change the robot's parameters and detect possible errors. So, this work proposes a architecture to turn these robots into autonomous systems, being able to detect the features of the groove to be weld, perform the welding with minimum of human interference or none and inspect the final product.

This Research to Practice Full Paper describes an study with Problem Based Learning (PBL). PBL promotes knowledge through the motivational appeal that problematization arouses. However, there are still points to be explored and potentialized, with the use of technologies to achieve Motivation. Thus, in this study we seek to understand how students' motivation to learn can be affected by sending automatic motivational triggers (sounds, notifications, etc.) during the execution of activities, in order to stimulate certain behaviors, such as studying, doing the task, complete an activity. The methodology for the validation of the triggers was developed in two moments: (i) in 2017 with the participation of 60 students of the Software Engineering course; and (ii) in 2018 with 23 students of the second year of the Computer Engineering course. At the end of each of these studies, students' views were grouped by class and expressed through the construction of the Discourse Collective Subject (DCS). Thus, this study contributes to the discussion and presentation of the DCS as an approach capable of assisting teachers during the evaluation of the activities proposed in the classroom, mainly because it makes it possible to observe the opinion of a group as a single subject.

The deaf have conquered rights in the area of education and, in recent years, with the increase of the enrollment of deaf people in higher education institutions, there is a need to develop new signs in Brazilian Sign Language (LIBRAS) for specific technical terms of several areas of knowledge and related to computing this scenario is no different. Motivated by the entrance of a deaf student in Information Systems undergraduate program of a Public Institution located in the south of Brazil, this work aims to elaborate technical signals of the Information System courses in LIBRAS and to develop a glossary with an interface adapted for the deaf. The construction of this repository of signs in LIBRAS is based on Vygotsky, who worked on defectology and emphasized the use of signs and symbols for the individual's cognitive development. The deaf student used the glossary in the classroom, which allowed a better understanding of the contents presented. Pedagogical evaluation was performed through descriptive analysis and data collection using the intensive direct observation method and questionnaires. The computational glossary in deaf education presents the potential to develop the capacities that are deprived by the existing communication difficulties, allowing interaction between deaf students, teachers and interpreters.

This Research Full paper presents a systematic analysis. The objective of this work is to identify the educational context in which u-Learning was applied, as well as to evaluate which technologies are used to analyze the learning process in the period from 2012 to 2019. The quantitative analysis of the publications verified 5347 productions associated to the areas of sustainability, homecare, health, education, among others. The qualitative study of the data revealed: (i) the definition of u-Learning processes, referring to the individual behavioral repertoire, modified by the acquisition of certain knowledge; (ii) evaluation of the learning related to concrete situations in which the individual can manifest the knowledge in the acquired behaviors; and as for the application (iii) it was verified the inexistence of models for analysis of these process of change of behavior. Thus, from our research it was possible to observe, as a priority, the use of technologies as an instrument for the learning process, not being used in the measurement of knowledge. The findings point to the purpose of future studies that may indicate possible behavioral models that allow analyzing the behavior change and consequently the ubiquitous learning process.

In this work in progress we present an experiment to evaluate our learning object recommendation model. In the experiment, we propose the construction of a bot chat as interface of the recommendation system. The system will recommend programming problems to a group of students based on their behaviors in an online platform of programming problems. The students' development and their motivation to participate will be analyzed to verify the accuracy of our model.

Image restoration and image enhancement are critical image processing tasks since good image quality is mandatory for many image applications. We are particularly interested in the restoration of ill-exposed images. These effects are caused by sensor limitation or optical arrangement. They prevent the details of the scene from being adequately represented in the captured image. We proposed a deep neural network model due to the number of uncontrolled variables that impact the acquisition. The proposed network can converge in a representative model from the training data, loss, optimization and activation functions. The obtained results are evaluated using several image quality index which indicate that the proposed network is able to improve images damaged by heterogeneous exposure. Furthermore, our method offers a significant gain over the state-of-the-art methods both in simulated data and real data.

In the fertilizer industry, granulometric analysis is an important quality control of the product. Usually, this process is done mechanically, through sieving, which makes the process slow. As an alternative to this, a methodology based on digital image processing for fertilizer classification is proposed. This approach allows to measure feret's diameter, area, volume and mass, important indicators to characterize fertilizers. The results obtained were validated with sieved samples and demonstrate the applicability of the method as a low cost alternative to the traditional method of granulometry of fertilizers.

The Electric-Arc Welding process is affected by several physical phenomena which have a direct impact on the final product quality. To understand and improve weld deposition is a key challenge to upgrade the overall metallic welding process. However, controlling the welding process of continuously fed melting wire electrode is still an open problem, which has not yet been solved. In order to study the phenomenon involved in the metallic transfer in linear welding, we employ a high-speed camera and laser lighting equipment to record the deposition images using two distinct imaging setups. Combining the image acquisition setup with voltage, current and wire speed data, we are able to obtain a dataset of distinct welding conditions, which allow us to observe critical aspects of the deposition. We present an acquisition methodology for generating a weld image dataset, as well as a software tool that makes possible to analyze, process and visualize each frame from recorded linear welding, providing per sample statistics and a framework to draw annotations of the due video. Through visual information and inferential statistics, we are able to identify how each parameter influences the weld of thick steel plates. Furthermore, we believe the tools provided will enable researchers to evaluate the deposition process and, thus, foster the development of hardware, software, and control techniques related to the field.

The use of robots is increasing in different industries, as in the case of large metal structures. The use of mobile robots meets the needs of these industries: it can be easily moved in the production line, with gains in repeatability and process efficiency, reducing rework costs. The poor configuration of the robotic and welding system generates problems in the internal structure and the surface of the weld, thus compromising the final quality of the piece. Visual inspections are common to identify problems that may have occurred during these processes. Inspections that use x-rays, ultrasound, or thermal cameras require additional equipment and highly trained inspectors to analyze the results and detect problems. This work presents a computer vision system based on a passive monocular camera for analysis of weld bead textures. Images of weld beads with and without discontinuities are captured and a dimensional reduction algorithm known as Principal Component Analysis (PCA) is applied to select the main characteristics that describe each group. Afterward, the Support Vector Machine (SVM) supervised learning method is applied to recognize the patterns of image groups, making it possible to classify new images of weld beads as welds with or without discontinuities. The system makes use of the same camera coupled to the robot responsible for conducting the welding, without the need for additional sensors, and assists the welding inspector in the evaluation of the performed process.

Digital cameras work through transforming the scene's radiance into an electrical charge. Optical arrangement, sensors, and embedded electronics often limit the accuracy of the representation. Scenes with a dynamic range above the capability of the camera or poor lighting are challenging conditions, which usually result in low contrast images. Soft clipping is usually compensated by transforming the power and shifting the image's histogram. However, under extreme conditions, ill exposure results in severe clipping that requires interpolation and painting. We introduce a model of convolutional neural network to perform signal reconstruction and interpolation. It is designed to be used on sRGB images. The results are evaluated using several metrics of image quality that indicate that the proposed network can improve images that are damaged by different conditions of exposure. In addition, our method offers a substantial gain over state-of-the-art methods.

Convolutional neural networks (CNNs) are powerful machine learning models that have become the state of the art in several problems in the areas of computer vision and image processing. Nevertheless, the knowledge of why and how these models present an impressive performance is still limited. There are visualization techniques that can help us to understand the inner working of neural networks. However, they have mostly been applied to classification models. In this paper, we evaluate the application of visualization methods to networks where the input and output are images of proportional dimensions. The results show that visualization brings visual cues associated with how these systems work, helping in their understanding and improvement. We use the knowledge obtained from the visualization of an image restoration CNN to improve the architecture's efficiency with no significant degradation of its performance.

This research presents a full paper in which we identify and systematize the new forms of access to information and communication experienced by contemporary society and their potentialities in the development of teaching environments. The called u-PBL corresponds to PBL combined with the use of ubiquitous environments for teachers, learning tools for learning activities and collaborative learning environments for students, ensuring meaningful learning. Studying the main works that report the use of u-PBL, benefits were found for the teaching learning process. The methodology was a bibliographical review of the articles published between 2010 and 2018, in the bases Google Scholar and ScienceDirect. As a result of this analysis, emerged (i) environments adapted to different user profiles; (ii) different pedagogical activities in u-PBL; (iii) different methodologies of educational activities addressed when using u-PBL; and (iv) different technological languages implementing the environments used. It was concluded that u-PBL could be applied as a teaching-learning aid tool, acting directly and/or indirectly in areas such as Health, Computing, Environment, etc. Also, the need for studies that report the development of u-PBL interfaces that allow constant immersion of the student into the teaching-learning environment.

This research presents a work in progress in which we propose a mapping of digital experiences through the analysis of the behavior of a group of users from the social site Facebook with regard to the self perception of the interactive processes provided by some tools made available in this digital environment. We believe that the user of social networks, even when only recognizing the movements of their production process, access and information sharing reveals initial connection structures that act as mediating agents in the construction of social representations. Thus, the focus of interest is to observe the characteristics and properties conferred to the technological artifacts highlighting the correlation between the processes of distributed cognition and the participation in activities of collaborative construction in digital medium. This research assumed an exploratory nature, being the method employed essentially quantitative from the use of a structured questionnaire to perform the data collection organized by three sessions: a) characterization of the respondents; b) indication of the number of social networks that it is part of; c) evaluation scale composed of 15 variables on various aspects of interaction in the social network Facebook. The instrument was answered from a Likert scale of `5' (five) points, with values between `0' (zero) and `4' (four), zero being `totally disagree' and `4' (four) “I totally agree”. The questionnaire was applied on a university campus during the month of October 2017, with 10.79% of students enrolled in the institution responding to the instrument. The data obtained from the analyzes of the assertions of the questionnaire were examined by the SPSS software, through which the Principal Component Analysis (PCA) was used a multivariate statistical technique that consists in reducing a number of original variables in components not related to priori, aiming at reducing data to facilitate its interpretation.

The main contribution of this work is the development of a qualitative analysis on the behavior of a group of university students and teachers in relation to the type of motivation revealed by a process of awareness about their domestic electric energy consumption. The identification of this behavior profile enables the organization of motivational messages that, when sent to users of mobile technologies, can enhance the ubiquitous learning process in this work related to environmental education. The methodological approach used was the Discourse of the Collective Subject, which is a method that allows the researcher to know and describe descriptive opinions and representations, allowing the delineation of behavioral profiles. In the results we can observe the need for greater clarity regarding the information related to energy consumption. However, for this information to achieve a change in consumer behavior it is necessary that it be customized. This information can auxiliary to the learning process, due to the fact that technology is increasingly integrated with “anytime” and “anywhere” human actions and behaviors, providing a learning process that can be obtained on any occasions, contingencies, circumstances and contexts.

This research-to-practice full paper proposals a metric of multiple skills for learning of programming students. This kind of system often need to diagnose the student's skill level. In the same way it needs to know the level of difficulty learning objects in its database. Such information makes it possible to make an appropriate match between student and the learning object. To model such tasks, we have adapted the ELO technique to apply a matchmaking process similar to that used in choosing opponents in chess tournaments or online matches. We used as a case study a virtual learning environment which has a repository with programming problems and the users interaction log. In this work we propose an extension to the traditional ELO model. In the classical model, ELO is a scalar value for each student and for each learning object. The extended model considers ELO as a multidimensional quantity, where each dimension is a skill in solving programming problems. The enumeration of the skills was made using the literature as well as statistical data of relevance of the attributes. The results are presented in this work.

This research presents a work in progress in which we discuss the potentialities and challenges in the development of Persuasive Technologies (PTs) and the possible opportunities of use in the most diverse areas. However, we emphasize the impact of the use of Pts as a motivational agent of the teaching and learning process. More precisely, this work investigates the use of PT as a mediator of characteristics related to the individual's perception of emotions and behavior. More precisely we propose the the Fogg Behavior Model (FBM) transcription for a computer tool. To do this we use the Fuzzy Logic. In order to validate the framework, we present a application in a scenario focused on the reduction of electric energy consumption. The results validate the proposed modeling as it relates to the measurement of the indexes of ability and motivation.

Sonar images pose hindrances when being elucidated for applications such as underwater navigation and localization. On the other hand, satellite images are simpler to be interpreted, but require GPS that is unavailable underwater due to absorption phenomena. Thus, we propose a neural network capable of translating an acoustic image acquired underwater to a textured image. We called the process sonar-to-satellite translation. We adopted a state-of-the-art neural architecture on a dataset comprised of sonar data and their respective satellite images. The experimental results show our method can extract interesting features from acoustic images and generate an informative texture image.

Forward-looking sonars (FLS) are perception sensors that are not affected by underwater turbidity. FLS are used in Remotely Operated Vehicles (ROVs) to help them in the tasks of exploration, navigation and region mapping. Besides the advantages of working with acoustic images rather than optical images, the former presents various challenges inherent to their construction. Classic Computer Vision (CV) algorithms do not achieve the same success with acoustic images. Furthermore, data-driven approaches are dictating the state-of-the-art in several tasks that require feature extraction. For example, Convolutional Neural Networks (CNNs) are already been used in several CV problems such as classification, image matching, image retrieval, place recognition and one-shot learning. CNNs are showing promising results for problems with FLS images as well. Unfortunately, there are as not as many public datasets and methods for FLS problems as we have for optical images. Knowing that CNNs are capable of mapping correctly millions of images into thousands of labels, we are proposing a novel framework of feature learning strategy for FLS images. In order to evaluate how well the methods generalize, we selected three different FLS annotated datasets for our experiments. Two of them are real-world FLS images from a harbour environment from different locations. The third is generated from a custom 3D scene integrated with open-source underwater robot simulators. In our experiments, we compared our method with state-of-the-art approaches in an unknown environment achieving superior results.

The research on robot tracking has focused on the problem of information fusion from redundant parametric estimations, though the aspect of choosing an adaptive fusion policy, that is computationally efficient, and is able to reduce the impact of un-modeled noise, are still open issues. The objective of this work is to study the problem of underwater robot localization. For this, we have considered a task relying on inertial and geophysical sensory. We propose an heuristic model that performs adaptable fusion of information based on the principle of contextually anticipating the localization signal within an ordered neighborhood, such that a set of nodes properties is related to the task context, and the confidence on individual estimates is evaluated before fusing information. The results obtained show that our model outperforms the Kalman filter and the Augmented Monte Carlo Localization algorithms in the task.

In this paper, a study on nonlinear state estimation methods for Hybrid Unmanned Aerial Underwater Vehicles (HUAUVs) is presented. Based on a detailed dynamic model simulation, we analyse and elect the best nonlinear algorithm among those presented in the state-of-the-art literature addressing local derivative-free nonlinear Kalman Filters (KFs): the Unscented Kalman Filter (UKF), the Cubature Kalman Filter (CKF) and the Transformed Unscented Kalman Filter (TUKF). Here, these three nonlinear probabilistic estimators were compared in terms of the Root Mean Square Error (RMSE) and the average execution time over Monte Carlo simulations. We simulated real-world conditions for our in-production HUAUV prototype using Inertial Measurement Unit (IMU) data and state augmentation for sensor data filtering and trajectory estimation. We have concluded that the CKF proved to be the most interesting KF to low-cost on-board applications for high dimensional state spaces.

The first Persuasive Technology (PT) emerged in the 1970s, and was being defined as an interactive computer system used to change human behavior. Research has shown the viability of these technologies in a variety of contexts such as advertising, reducing energy consumption, promoting healthy or well-being behavior and education. This research identifies and systematizes this area of knowledge, from the identification of the main works that relate the use of PTs in education. The methodology used was review of the works published between 2010 and 2017 of the state-of art, in the bases of Google Scholar, Springer, Elsevier, ACM. As a result of the analysis of the articles, we highlight as main focus the use of (i) PTs adapted to different user profiles; (ii) PTs applied in different pedagogical activities; (iii) PTs for different methodologies of educational activities; (iv) PTs developed in different technological languages. The PTs can be applied as learning aid instruments, acting directly and/or indirectly in the areas of Social Assistance, Health, Environment, Research and Development, Education and Advertising. Given this scenario, we observed the need to foster publications that problematize the interfaces of PTs in Education, especially architectures and/or technologies that involve, for example, Cyber-Physical Systems, that can extend the educational (physical) environment to the virtual world, in order to leave the student immersed constantly in a teaching environment.

The study of the motivational aspect and its relevance to the comprehension of the efficacy of learning has been the subject matter of several researches. According to the Self-determination Theory (SDT) there is a relation between the context, the motivation, and the performance of individuals in a given task. Thus, a continuum is defined between intrinsic, extrinsic, and lack of motivation; so individuals intrinsically motivated would perform optimally. In order to adequate the communication module of the system Sapiens for the learning of efficient energy consumption, this work has proposed to develop an instrument to evaluate the level of situational motivation of individuals, and to design persuasive messages to increase the engagement on the task, based on the motivation profiles described by SDT. For this, a methodology was defined comprising the following stages: (i) bibliographic research of the state-of-art scales to assess motivation; (ii) design of a data collection instrument in the form of a structured questionnaire; (iii) evaluation of the instrument considering an heterogeneous sample of 589 college, high-school, technical, master, and doctoral students, aged between 14 and 80 years, at three different situations (the library, the classroom, and leisure); (iv) design of the persuasive messages to enhance the user engagement on the task. The resulting instrument was named Ubiquitous Situational Motivation Scale (USMS), consisted in 18 questions presented as a 7-points Likert Scale, that measures four motivational factors with Cronbach alpha coefficients ranging from 0.61 to 0.86. Our study revealed that subjects' motivation profile varied according to the context, so leisure activities were respectively more related to intrinsic motivation than the library and the classroom activities, and suggests that classroom activities are probably more related to external regulation. The results were also consistent with the continuum hypothesis of SDT. The evaluation with potential users showed that the persuasive messages designed based on the motivational profiles were positively rated. From these results the persuasive module will integrated to the Sapiens platform so the performance of the users can be studied.

Recommendation systems use computational techniques to select items in a personalized way to users, taking into account criteria such as history and interest. However, several authors point out that the process of recommendation in education requires models beyond the user's taste, in order to catalyze students' learning. In addition, feedback involves the student's experience. In this work we present a recommendation system of learning objects supported by a cognitive pedagogical model. The central idea of the system is to find an object that adequately challenges the student without bothering with similar problems or becoming discouraged when faced with problems beyond his or her ability. We integrate learning models into game models to integrate them into learning models. We used as a case study a virtual learning environment which has a repository with programming problems. The results indicate that, in general, when students choose more appropriate problems (ELOs similar to theirs), they get a greater number of correct answers in their submissions. When the student choose problems that do not seem to be challenging, in general, they make wrong submissions or give up learning on the platform.

Microalgae are unicellular organisms that presents limited physical characteristics such as size, shape or even the present structures. Classifying them manually may require great effort from experts since thousands of microalgae can be found in a small sample of water. Furthermore, the manual classification is a non-trivial operation. We proposed a deep learning technique to solve the problem. We also created a classified dataset that allow us to adopt this technique. To the best of our knowledge, the present work is the first one to apply this kind of technique on the microalgae classification task. The obtained results show the capabilities of the method to properly classify the data by using as input the low resolution images acquired by a particle analyzer instead of pre-processed features. We also show the improvement provided by the use of data augmentation technique.

In recent years, Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many image restoration applications. The knowledge of how these models work, however, is still limited. While there have been many attempts at better understanding the inner working of CNNs, they have mostly been applied to classification networks. Because of this, most existing CNN visualization techniques may be inadequate to the study of image restoration architectures. In the paper, we present network inversion, a new method developed specifically to help in the understanding of image restoration Convolutional Neural Networks. We apply our method to underwater image restoration and dehazing CNNs, showing how it can help in the understanding and improvement of these models.

Optical images display drastically reduced visibility due to underwater turbidity conditions. Sonar imaging presents an alternative form of environment perception for underwater vehicles navigation, mapping and localization. In this work we present a novel method for Acoustic Scene Matching. Therefore, we developed and trained a new Deep Learning architecture designed to compare two acoustic images and decide if they correspond to the same underwater scene. The network is named Sonar Matching Network (SMNet). The acoustic images used in this paper were obtained by a Forward Looking Sonar during a Remotely Operated Vehicle (ROV) mission. A Geographic Positioning System provided the ROV position for the ground truth score which is used in the learning process of our network. The proposed method uses 36.000 samples of real data for validation. From a binary classification perspective, our method achieved 98% of accuracy when two given scenes have more than ten percent of intersection.

The need for convergence between technology and shipbuilding processes is identified in the Brazilian shipbuilding industry so that it has a greater competitiveness against the shipyards belonging to the Tiger Cub Economies. In this perspective, wireless sensor networks and identification technologies have gained space regarding industrial solutions. This paper proposes an Internet of Things (IoT) based architecture using RFID and GPS for identification and tracking of blocks in shipyards. A hardware architecture is presented with the objective of identifying, mapping and tracking blocks and consequently the vehicles used in their transport, in a shipyard and offshore.

The robotic welding processes have been highly widespread in manufacturing industries due to large-scale production. An area where these processes are widely applied are shipyards, where there are necessary hundreds to thousands of kilograms of weld by hour. However, systems that operate in open-air environments are vulnerable to sundry disturbances, noises in measures, as well as possible unavailability of measurement of some system states, required for the controller. Taking it into account, in this work, a Robust Model Reference Adaptive Control is proposed to regulate the velocity of a nonlinear motor of a linear welding robot. Furthermore, an Extended Kalman Filter is implemented to estimate the system states and attenuate measurement noises. The proposed control system demonstrated a very good performance with fast convergence and small error.

Welding is an important operation in manufacturing processes and it can represent a highly relevant amount of production costs, depending on material workpieces and required weld quantity. In mechanised and robotised welding processes, robot's travel velocity is an important parameter, which requires a proper regulation to obtain a good quality for weld beam. Then, in this work, a nonlinear model of a robot motor with their identified parameters is presented and a sliding mode control is proposed to regulate robot velocity. Furthermore, an Unscented Kalman Filter and a Cubature Kalman Filter are implemented, separately, for output system estimation. The control system with both estimators presented satisfactory tracking performances, in simulations, converging fast and with very small chattering.

Real-time and embedded systems (RTES) encompass a variety of embedded and real-time properties and requirements which defines them. Timing behavior of RTES physical and logical subsystems is as important as their functional behavior. These systems must define, in addition to their functional properties, the control of several peripheral components, of their constraints, communication interfaces and temporal and non-functional requirements. Understanding the representation and treatment of several properties of real-time and embedded systems has direct influence in their development, reliability and safety. Therefore, it is pertinent to analyze the properties that represent this domain and to provide strategies for a complete definition of model elements'. This paper aims to provide guidelines for comprehension, application and possible adoption of the UML MARTE (Modelling and Analysis of RealTime and Embedded Systems) profile in specification, modeling and design of real-time and embedded properties of a system. The proposed design strategy is applied to a case study, in the domain of intelligent automation systems, in order to direct the adoption of the constructors of MARTE profile in other development contexts and to describe the semantics and syntax of these builders to strengthen their comprehensibility.

Welding is an important process in the industrial scenario, especially in the shipbuilding industry. This process is recognized by the laborious work and the hazardous work environment. The use of robots to automate the welding process can reduce the human interference and improve the productivity. This paper proposes a system for automated seam tracking based on passive monocular vision. The vision provides a data feedback to the automated robotic welding system allowing quality and productivity gains. A trajectory controller is developed to correct the robot's movement over the seam reference. The controller and a visual algorithm to find the seam reference in a real Gas Metal Arc Welding (GMAW) process are presented. The proposed system allows the automated seam tracking, the trajectory control of the welding torch, and a higher automation level in linear robotic welding. The capabilities of the method is evaluated using a commercial linear welding robot showing its viability.

Pipelines have been used to convey products such as oil, gas, chemicals and water. It means that problems with pipelines would indicate money waste and environment damages. To avoid those problems, inspections are realised periodically. The technology improvement has made possible employing robots and mobile platforms to inspect pipes. The focus of this work is to implement a strategy to acquire the pose of robot or platform inside pipe. The method consists in the use of a technique to fuse information from a low cost IMU and encoder. Simulations are realised using Matlab software.

Three-dimensional virtual worlds have been studied by many researchers around the world, including in educational contexts. A range of possibilities have emerged from this type of environment, such as improvements in distance education and other educational technologies. But there are some problems related to the use of this environment, such as complex authorship tools, which need to be discussed and considered to create situations that encourage use. The goal of this study was to find, analyze, and discuss the studies that focused on these environments, with authorship as the main theme. With this in mind, we conducted a systematic review of published articles in six repositories to extract studies for subsequent analysis using text mining and graph analysis software.

Electric arc welding is a complex task that demands a high degree of control in order to meet the international standards for fusion welding. We present a Vision-Based Measurement (VBM) system and evaluate how different conditions and algorithms impact the measuring of beveled edges. The proposed system integrates hardware and software to image the welding plates using a single CMOS camera as visual sensor, run computer vision algorithms on a FPGA (Field Programmable Gate Array) board, controls the robot movements and adjust the weld pattern and welder equipment parameters. A complete prototype, using a commercial linear welding robot is presented. The evaluation of the system as a groove mapping equipment, considering different processing algorithms combined with noise removal and line segment detection techniques, shows the potential of the approach for shop floor operation.

There are many types of transportation of fluids such as a truck, train and ship. However, it is not suitable and economic practical. The employment of truck vehicles increase problems with traffic and pollution. The transport of train requires high maintenance of structures responsible for training moves. The ship conveys can be used just where there is sea or lagoon. The most method used to convey fluids is pipeline. However, aging, corrosion, mechanical damage and cracks in pipes, depending on which product is been transported, can be hazardous to the environment or monetary loss. One of the solutions to this problem is to realise maintenance of pipelines. To reduce time of maintenance, it is realised inspection before maintenance. However, there are inaccessible structures of pipes, size extreme temperature that makes dangerous realise manual inspection. The development of embedded system and field of instrumentation makes possible the employment of robotics for the execution of inspection tasks. The principal objective of this work is to realise a review about robots inspection, expound differences between robots considering application, adaptability, locomotion, sensors inspection and odometers.

This study intends to consider the operator skill and the environment conditions as variables of Intelligent Maintenance Systems (IMS). In this sense maintenance operations associated with the technical skills and environment factors through sensory perception can represent important strategy to improve the IMS. This approach considers the Cyber-Physical Systems (or CPS) paradigm to acquire human and context factors once that CPS system combines coordinates physical and computational elements. Thus this study proposes the CPS use for taking account the operator's skill and environment conditions for maintenance strategies. This proposal aims the developing of Advanced Human Computer Interface for Intelligent Maintenance Systems that consider the operator's skill and environment. The validation will be accomplished by interface named Toogle where two case studies will be tested.

Intelligent Maintenance Systems (IMS) are data acquisition/analysis systems for predictive maintenance. The IMS provide autonomously (or semi-autonomously) diagnoses, prognostics and health assessment of components. In these systems, factors such as data acquisition and visualization from equipments are very important. In this context, this study has used a Cyber-Physical Systems (or CPS) approach to consider the various aspects present into a maintenance environment. The CPS is a new paradigm that seeks to combine and coordinate physical and computational elements. In this paper, we propose a 2D/3D visualization tool for cyber-physical maintenance environments. This tool works under HTTP protocol and makes possible the real-time visualization and remotely access, allowing users to view, to edit and to access the maintenance data via web browser.

Most existing motion tracking methods works in specific predefined situations and requires large amount of a priori information about the target objects, such as, their shapes, appearances, kinematic structures, possible moves and physically valid poses. This work aims to investigate a generic motion tracking method that allows to reduce the amount of a priori knowledge employed. The proposed 3D tracking method mainly intends to allow the tracking of objects with distinct shapes, including cyclic dependencies between their different parts, and learning their representation models during the motion tracking process. To do so, the Nonparametric Belief Propagation (NBP) technique, the PArticle Message PASsing (PAMPAS) algorithm and the Loose-Limbed probabilistic graphical model are used into this novel approach. The proposed method is applied to distinct and previously unknown objects. The obtained results shown that the method is capable of deal adequately with such situations.

In this paper an automated platform for immersive multiprojection visualization of manufacturing processes is proposed. It admits scenarios with dynamic components and allows Virtual Reality collaborative visualization among geographically distributed users, through multi-CAVE devices. Modules for modeling, converting, visualizing and interacting composes the platform. The proposed system can be applied to CAD projects, models and simulations used in industry. The ideas discussed are then validated through the study of a real case related to the Shipbuilding and Offshore Industries.

This article presents a methodology to extract principal components of large datasets, called C-NLPCA (cascaded nonlinear principal component analysis), and evaluates its use in the extraction of main human movements in image series, aiming for the development of methodologies and techniques for skill transfer from humans to robotic/virtual agents. The C-NLPCA is an original data multivariate analysis method based on the NLPCA (nonlinear principal component analysis). This method has as main features the capability of taking principal variability components from a large set of data, considering the existence of possible nonlinear relations among them. The proposed method is used to extract principal movements from video sequence of human activities, which can be reconstructed in cybernetic and robotic contexts. Aiming for the validation of the method a human moving hand test is presented, where C-NLPCA is applied and the patterns of the obtained movements are confronted with traditional linear techniques.

We propose a new approach to treat a class of cooperative issues in the multi-robot context. These issues are associated with the common use of some entities, called mechanisms. A mechanism can be seen as a generalization of the notion of resource. The robots can modify its state directly or through requests. The robots can also share its utilization. Multi-robot cooperation can be expressed as a distributed decisional process that tends to solve, detect and treat resource conflict situations as well as sources of inefficiency. We discuss these issues and illustrate them through a simulated system which allows a number of autonomous robots to plan and perform cooperatively a set of servicing tasks in a hospital environment.

Discusses a general architecture where various schemes for multi-robot task achievement can be integrated called "M+ Cooperative task achievement". The main originality comes from its ability to allow the robots to detect-in distributed and cooperative manner-resource conflict situations as well as sub-optimalities. Different decisions are performed by the robots such as actions re-scheduling, suppression of redundancies and opportunistic enhancement of the global performance. Finally, we illustrate its use through a simulated system, which allows a number of robots to plan and perform cooperatively a set of tasks in a hospital environment.

We present and discuss a distributed scheme for multi-robot cooperation. It integrates mission planning and task refinement as well as cooperative mechanisms adapted from the contract net protocol framework. We discuss its role and how it can be integrated as a component of a complete robot control system. We also discuss how it handles distributed task allocation and achievement as well as cooperative reaction to contingencies. Finally, we illustrate its use through a simulated system, which allows a number of robots to perform load transfer tasks in a route network environment.