CRIIS - Other Publications

Permanent URI for this collection

http://localhost:4000/handle/123456789/284

Browse

Browsing CRIIS - Other Publications by Issue Date

Jump to a point in the index:
  • Item
    Anechoic Chamber Interference Tests on a Bluetooth Low Energy Front-End Towards a Subcutaneous Glucose Sensor
    ( 2012) Sérgio Santos Silva ; António Paulo Moreira ; Salviano Soares ; António Valente
    Background: The metabolic disorder which entails the absent or reduced control of blood glucose in the body by means of insulin dependence (Type 1) or intolerance (Type 2) affected more than 382 million people in 2013. Although only 13% of patients die from diabetes, there are a significant number of costly, dangerous health complications that appear if the correct control is not taken. Glucose subcutaneous Bluetooth Low-Energy sensor can help patients to constantly monitor their glucose levels and issue alarms to a cellular phone. Several tests regarding interference, robustness and coexistence were made to ensure Quality of Service in order to achieve medical diagnostic status. Materials and Methods: All measurements were performed in a full anechoic chamber with walls, ceiling and floor covered with high loss microwave absorbers. A PC USB Dongle acts as receiver for the Java developed application, where several data sets for each location were recorded.
  • Item
    IntellWheels: Intelligent wheelchair with user-centered design
    ( 2013) Petry,MR ; António Paulo Moreira ; Brígida Mónica Faria ; Luís Paulo Reis
    Intelligent wheelchairs can become an important solution to assist physically impaired individuals who find it difficult or impossible to drive regular powered wheelchairs. However, when designing the hardware architecture several projects compromise the user comfort and the wheelchair normal usability in order to solve robotic problems. In this paper we describe the main concepts regarding the design of the IntellWheels intelligent wheelchair. Our approach has a user-centered perspective, in which the needs and limitations of physically impaired users are given extensive attention at each stage of the design process. Finally, our design was evaluated through a public opinion assessment. A statistical analysis suggested that the design was effective to mitigate the visual and ergonomic impacts caused by the addition of sensorial and processing capabilities on the wheelchair. © 2013 IEEE.
  • Item
    Self-localisation of indoor mobile robots using multi-hypotheses and a matching algorithm
    ( 2013) Pinto,M ; Héber Miguel Sobreira ; António Paulo Moreira ; Hélio Mendonça ; Aníbal Matos
    This paper proposes a new, fast and computationally light weight methodology to pinpoint a robot in a structured scenario. The localisation algorithm performs a tracking routine to pinpoint the robot's pose as it moves in a known map, without the need for preparing the environment, with artificial landmarks or beacons. To perform such tracking routine, it is necessary to know the initial position of the vehicle. This paper describes the tracking routine and presents a solution to pinpoint that initial position in an autonomous way, using a multi-hypotheses strategy. This paper presents experimental results on the performance of the proposed method applied in two different scenarios: (1) in the Middle Size Soccer Robotic League (MSL), using artificial vision data from an omnidirectional robot and (2) in indoor environments using 3D data from a tilting Laser Range Finder of a differential drive robot (called RobVigil). This paper presents results comparing the proposed methodology and an Industrial Positioning System (the Sick NAV350), commonly used to locate Autonomous Guided Vehicles (AGVs) with a high degree of accuracy in industrial environments.
  • Item
    Modeling and simulation of the EMG30 geared motor with encoder resorting to simtwo: The official robot@factory simulator
    ( 2013) José Alexandre Gonçalves ; José Lima ; Paulo José Costa ; António Paulo Moreira
    This paper describes the EMG30 mechanical and electrical modeling and its simulation resorting to SimTwo (Robot@Factory mobile robot competition official simulator). It is described the developed setup applied to obtain the experimental data that was used to estimate the actuator parameters. It was obtained an electro-mechanical dynamical model that describes the motor, its gear box, and the encoder. The motivation to model and simulate the EMG30 is the fact that it is an actuator worldwide popular in the mobile robotics domain, being a low cost 12v motor equipped with encoders and a 30:1 reduction gearbox. The Goal of this work is to provide more realism and new features to the Robot@Factory official simulator, allowing participating teams to produce and validate different robot prototypes and its software, reducing considerably the development time. © Springer International Publishing Switzerland 2013.
  • Item
    Ocean Observation With Coordinated Robotic Platforms Coordination Algorithms Maintain Vehicle Formation
    ( 2013) Nuno Cruz ; Bruno Miguel Ferreira ; Aníbal Matos
    The MARES is a small, torpedo-shaped AUV 1.5 meters long and 32 kilograms in weight in the basic version. In a typical configuration, a PC/104 computational system manages the entire mission, including communications with other devices and a control station. Navigation is provided by the fusion of data from an inertial measurement unit (IMU) and an acoustic system for long baseline localization (LBL), complemented by a small GPS receiver, when the vehicle is at the surface. Four thrusters provide the capability to move as fast as 5 knots and to hover in the water column, with a set of lithium-ion batteries ensuring 10 hours of operation. MARES is a highly modular vehicle, with the ability to integrate a great variety of payload sensors, and it has been operating since 2007, mainly in environmental- monitoring missions. The capability of vehicles to follow a given trajectory and maintain reliable data exchange is among the most relevant topics when it comes to coordination of marine robots.
  • Item
    Object recognition using laser range finder and machine learning techniques
    ( 2013) Andry Maykol Pinto ; Luís Freitas Rocha ; António Paulo Moreira
    In recent years, computer vision has been widely used on industrial environments, allowing robots to perform important tasks like quality control, inspection and recognition. Vision systems are typically used to determine the position and orientation of objects in the workstation, enabling them to be transported and assembled by a robotic cell (e.g. industrial manipulator). These systems commonly resort to CCD (Charge-Coupled Device) Cameras fixed and located in a particular work area or attached directly to the robotic arm (eye-in-hand vision system). Although it is a valid approach, the performance of these vision systems is directly influenced by the industrial environment lighting. Taking all these into consideration, a new approach is proposed for eye-on-hand systems, where the use of cameras will be replaced by the 2D Laser Range Finder (LRF). The LRF will be attached to a robotic manipulator, which executes a pre-defined path to produce grayscale images of the workstation. With this technique the environment lighting interference is minimized resulting in a more reliable and robust computer vision system. After the grayscale image is created, this work focuses on the recognition and classification of different objects using inherent features (based on the invariant moments of Hu) with the most well-known machine learning models: k-Nearest Neighbor (kNN), Neural Networks (NNs) and Support Vector Machines (SVMs). In order to achieve a good performance for each classification model, a wrapper method is used to select one good subset of features, as well as an assessment model technique called K-fold cross-validation to adjust the parameters of the classifiers. The performance of the models is also compared, achieving performances of 83.5% for kNN, 95.5% for the NN and 98.9% for the SVM (generalized accuracy). These high performances are related with the feature selection algorithm based on the simulated annealing heuristic, and the model assessment (k-fold cross-validation). It makes possible to identify the most important features in the recognition process, as well as the adjustment of the best parameters for the machine learning models, increasing the classification ratio of the work objects present in the robot's environment.
  • Item
    FEUPCAR 2.0: Overview of a Low-cost Robot for Autonomous Driving Competitions
    ( 2013) Vidal,AA ; Luís Paulo Reis ; António Paulo Moreira
    Robotic autonomous driving is a very complex task that tries to replicate the human behavior when performing such task. This paper presents a high-level overview of an architecture applicable for small-scale vehicles in autonomous driving competitions. A special emphasis is given on the sensory and navigation sub-systems since they are the most prominent intelligent decision layers. The former is almost entirely based on computer vision, processing the raw image content from two ordinary and inexpensive "web-cams", conveying further relevant information to the later, on a real-time basis. The proposed architecture was implemented with minimal interventions to an Ackermann-like vehicle which was originally designed for recreational purposes, serving as a "proof of concept" of the developed system. Results show that a low-cost, scalable and modular system can be easily integrated on regular small-scale vehicles obtaining exciting results at a minimal cost.
  • Item
    Semi-automatic Virtual Reconstruction of Ancient Roman Houses
    ( 2013) Telmo Oliveira Adão ; Luís Gonzaga Magalhães ; Emanuel Peres Correia
    Video Games may be used with different applications in mind, for entertainment, training and simulation or even as teaching tools. However, the production of contents for such games, namely game scenarios with virtual worlds composed by cities and related elements (streets, buildings, furniture and so on) may require a laborious effort by multidisciplinary teams which lead to an expensive and time consuming solution. In order to avoid the development burden, procedural modeling techniques have been created and applied to generate virtual models of buildings and cities expeditiously with high degree of detail and realism. Nevertheless, most of the existing techniques use complex sets of rules to produce models without being aware of the architectonic structures and its relationships. Thereby, in order to simplify the generation process and rule dealing we propose, in this paper, an ontology-based procedural modeling methodology which integrates an ontological structure, describing city elements and the relationships between each other, and a combined set of procedural techniques to generate roman houses. The preliminary results point to a method capable of producing roman houses expeditiously, including the interiors and the exteriors.
  • Item
    Multi-robot nonlinear model predictive formation control: Moving target and target absence
    ( 2013) Nascimento,TP ; António Paulo Moreira ; Scolari Conceicao,AGS
    This paper describes a novel approach in formation control for mobile robots in the active target tracking problem. A nonlinear model predictive formation controller (NMPFC) for target perception was implemented to converge a group of mobile robots toward a desired target. The team must also maintain a desired formation following a target while it is moving, or follow a leader in the case of target's absence. The structure details of the controller, as well as a mathematical analysis of the formation model used, are presented. Furthermore, results of simulations and experiments with real robots are presented and discussed.
  • Item
    Entropy Diversity in Multi-Objective Particle Swarm Optimization
    ( 2013) Eduardo Pires ; Tenreiro Machado,JAT ; Paulo Moura Oliveira
    Multi-objective particle swarm optimization (MOPSO) is a search algorithm based on social behavior. Most of the existing multi-objective particle swarm optimization schemes are based on Pareto optimality and aim to obtain a representative non-dominated Pareto front for a given problem. Several approaches have been proposed to study the convergence and performance of the algorithm, particularly by accessing the final results. In the present paper, a different approach is proposed, by using Shannon entropy to analyze the MOPSO dynamics along the algorithm execution. The results indicate that Shannon entropy can be used as an indicator of diversity and convergence for MOPSO problems.
  • Item
    Towards Extraction of Topological Maps from 2D and 3D Occupancy Grids
    ( 2013) Filipe Neves Santos ; António Paulo Moreira ; Paulo José Costa
    Cooperation with humans is a requirement for the next generation of robots so it is necessary to model how robots can sense, know, share and acquire knowledge from human interaction. Instead of traditional SLAM (Simultaneous Localization and Mapping) methods, which do not interpret sensor information other than at the geometric level, these capabilities require an environment map representation similar to the human representation. Topological maps are one option to translate these geometric maps into a more abstract representation of the the world and to make the robot knowledge closer to the human perception. In this paper is presented a novel approach to translate 3D grid map into a topological map. This approach was optimized to obtain similar results to those obtained when the task is performed by a human. Also, a novel feature of this approach is the augmentation of topological map with features such as walls and doors.
  • Item
    Robot@Factory: Localization Method Based on Map-Matching and Particle Swarm Optimization
    ( 2013) Andry Maykol Pinto ; António Paulo Moreira ; Paulo José Costa
    This paper presents a novel localization method for small mobile robots. The proposed technique is especially designed for the Robot@Factory which is a new robotic competition presented in Lisbon 2011. The real-time localization technique resorts to low-cost infra-red sensors, a map-matching method and an Extended Kalman Filter (EKF) to create a pose tracking system that is well-behaved. The sensor information is continuously updated in time and space through the expected motion of the robot. Then, the information is incorporated into the map-matching optimization in order to increase the amount of sensor information that is available at each moment. In addition, a particle filter based on Particle Swarm Optimization (PSO) relocates the robot when the map-matching error is high. Meaning that the map-matching is unreliable and robot is lost. The experiments conducted in this paper prove the ability and accuracy of the presented technique to localize small mobile robots for this competition. Therefore, extensive results show that the proposed method have an interesting localization capability for robots equipped with a limited amount of sensors.
  • Item
    Investigation of Underwater Acoustic Networking Enabling the Cooperative Operation of Multiple Heterogeneous Vehicles
    ( 2013) Nuno Cruz ; Bruno Miguel Ferreira ; Kebkal,O ; Aníbal Matos ; Petrioli,C ; Petroccia,R ; Spaccini,D
    In this paper, we investigate the creation of an underwater acoustic network to support marine operations based on static and mobile nodes. Each underwater device combines communication, networking, and sensing capabilities and cooperates with the other devices in coordinated missions. The proposed system is built upon the SUNSET framework, providing acoustic communications and networking capabilities to autonomous underwater vehicles, autonomous surface vessels, and moored systems, using underwater acoustic modems. Specific solutions have been developed and tested to control the underwater nodes acoustically and to instruct the vehicles on keeping a given formation using acoustic links. One of the novelties of our approach has been the development and utilization of a realistic simulation infrastructure to provide a very accurate representation of all the dynamic systems involved in the network, modeling the vehicle dynamics, the acoustic channel, and the communication messages. This infrastructure has been extensively used to investigate and validate the proposed solutions under different environmental conditions before the actual deployment of devices. Several experiments were then conducted in the laboratory and in the field. The experimental results have confirmed the effectiveness of the proposed solutions and the reliability of the proposed simulation framework in estimating system performance.
  • Item
    Stereoscopic Vision System for Human Gesture Tracking and Robot Programming by Demonstration
    ( 2013) Ferreira,M ; Luís Freitas Rocha ; Paulo José Costa ; António Paulo Moreira
    This paper presents a framework for robot programming by demonstration using gesture. It is based on a luminous multi-LED marker which is captured by a pair of industrial cameras. Using stereoscopy the marker supplies a complete 6-DoF human gesture tracking output with both position and orientation. Tests show that the developed setup is industrial grade, being precise for many industrial applications and robust particularly to lighting conditions. Attaching the marker to an operator work tool provides an efficient way to track the human movements without further intrusion in the process. The resulting path is used to generate a program for an industrial manipulator ending the cycle in an human-robot skill transfer framework.
  • Item
    Simulation and control of a spider crab biomechanical model
    ( 2013) Rynkevic,R ; Manuel Santos Silva ; Marques,AM
    One line of research and development in robotics receiving increasing attention in recent years is the development of biologically inspired robots. The idea is to gain knowledge of biological beings and apply the knowledge thus acquired to implement the same methods of locomotion (or at least use the biological inspiration) on the machines we build. It is believed that this way it is possible to develop machines with capabilities similar to those of biological beings in terms of locomotion skills and energy efficiency. One way to better understand the functioning of these systems, without the need to develop prototypes with long and costly development, is to use simulation models. Given these ideas, this work concerns the study of the biomechanics of the spider crab, using the SimMechanics toolbox of Matlab/Simulink. This paper describes the anatomy and locomotion of the spider crab, its modeling and control and the locomotion simulation of a crab within the SimMechanics environment.
  • Item
    An Industrial Robotics Course Based on a Graphical Simulation Package
    ( 2013) Manuel Santos Silva
    In recent years there has been an increasing introduction of industrial robots in the manufacturing industry, with several studies that predict the increased dissemination of robots in industrial and service sectors. On the other hand, there is often the lack of people able to plan the introduction of these equipments in manufacturing environments and to operate it after its inception. This leads to the need to train undergraduates in the operation and programming of industrial robots. Due to the Portuguese economic situation, there is a lack of funding for the higher schools, leading to the need of finding innovative ways to teach these subjects. Bearing in mind these ideas, in this paper is described a course on industrial robotics, which is based in the achievement of the practical training using commercial off-theshelf robot simulation software for off-line programming.
  • Item
    Real-Time and Continuous Hand Gesture Spotting: an Approach Based on Artificial Neural Networks
    ( 2013) Neto,P ; Pereira,D ; Norberto Pires,JN ; António Paulo Moreira
    New and more natural human-robot interfaces are of crucial interest to the evolution of robotics. This paper addresses continuous and real-time hand gesture spotting, i.e., gesture segmentation plus gesture recognition. Gesture patterns are recognized by using artificial neural networks (ANNs) specifically adapted to the process of controlling an industrial robot. Since in continuous gesture recognition the communicative gestures appear intermittently with the non-communicative, we are proposing a new architecture with two ANNs in series to recognize both kinds of gesture. A data glove is used as interface technology. Experimental results demonstrated that the proposed solution presents high recognition rates (over 99% for a library of ten gestures and over 96% for a library of thirty gestures), low training and learning time and a good capacity to generalize from particular situations.
  • Item
    Diffusion of innovation simulation using an evolutionary Algorithm
    ( 2013) Sampaio,L ; Varajao,J ; Eduardo Pires ; Paulo Moura Oliveira
    The diffusion of innovation theory aims to explain how new ideas and practices are disseminated among social system members. A significant number of the existing models is based on the use of parameters which determine the process of innovation adoption, and rely on simple mathematical functions centered in the observation and description of diffusion patterns. These models enable a more explicit diffusion process study, but their use involves the estimation of diffusion coefficients, usually obtained from historical data or chronological series. This raises some application problems in contexts where there is no data or the data is insufficient. This paper proposes the use of evolutionary computation as an alternative approach for the simulation of innovation diffusion within organizations. To overcome some of the problems inherent to existing models an evolutionary algorithm is proposed based on a probabilistic approach. The results of the simulations that were done to validate the algorithm revealed to be very promissing in this context. Simulation experiment results are presented that reveals a very promising approach of the proposed model. © 2013 Springer-Verlag Berlin Heidelberg.
  • Item
    Revisiting Lucas-Kanade and Horn-Schunck
    ( 2013) Andry Maykol Pinto ; António Paulo Moreira ; Paulo José Costa ; Miguel Velhote Correia
  • Item
    Identifying different visual patterns in web users behaviour
    ( 2013) Goncalves,M ; Tânia Vilela Rocha ; Luís Gonzaga Magalhães ; Emanuel Peres Correia ; Maximino Bessa ; Chalmers,A
    On the internet one can find all kinds of information and perform a multitude of tasks such as searching for information about any subject, purchase goods and services, or enquiring about a particular company. When navigating the web, our focus (where we look) can be captured involuntary through a visual stimulus, or may be directed in a controlled manner depending on the task that we are performing. The layouts of web sites range from simple to highly complex. When creating new layouts, knowing what information is most important when a user is performing a task and which areas are supposed to attract his/her attention are important issues in order to make a web site easier to interpret and consequently their usability. In this paper we present an eye tracking study of users' visual behaviour when surfing on websites and investigate if it is possible to determine likely visual patterns. We show that the visual patterns are different depending on the task that is being performed and not on the web site where it is being carried out. © 2011 ACM.