Design of the ISePorto robocup Middle-Size League Robotic Soccer Team: Control, Localisation and Coordination

Proceedings of the 10th Mediterranean Conference on Control and Automation - MED2002 Lisbon, Portugal, July 9-12, 2002

Control and Localisation for the ISePorto Robotic Soccer Team

International Conference on Advanced Robotics, Coimbra, Portugal, Julho 2003

TIGRE - An autonomous ground robot for outdoor exploration

13th International Conference on Autonomous Robot Systems (Robotica), 2013

Neural control of an autonomous robot

This article aims to apply the concepts associated with artificial neural networks (ANN) in the control of an autonomous robot system that is intended to be used in competitions of robots. The robot was tested in several arbitrary paths in order to verify its effectiveness. The results show that the robot performed the tasks with success. Moreover, in the case of arbitrary paths the ANN control outperforms other methodologies, such as fuzzy logic control (FLC).

Haptic robot-environment interaction for self-supervised learning in ground mobility

Dissertação para obtenção do Grau de Mestre em Engenharia Eletrotécnica e de Computadores

2D position system for a mobile robot in unstructured environments

Nowadays, several sensors and mechanisms are available to estimate a mobile robot trajectory and location with respect to its surroundings. Usually absolute positioning mechanisms are the most accurate, but they also are the most expensive ones, and require pre installed equipment in the environment. Therefore, a system capable of measuring its motion and location within the environment (relative positioning) has been a research goal since the beginning of autonomous vehicles. With the increasing of the computational performance, computer vision has become faster and, therefore, became possible to incorporate it in a mobile robot. In visual odometry feature based approaches, the model estimation requires absence of feature association outliers for an accurate motion. Outliers rejection is a delicate process considering there is always a trade-off between speed and reliability of the system. This dissertation proposes an indoor 2D position system using Visual Odometry. The mobile robot has a camera pointed to the ceiling, for image analysis. As requirements, the ceiling and the oor (where the robot moves) must be planes. In the literature, RANSAC is a widely used method for outlier rejection. However, it might be slow in critical circumstances. Therefore, it is proposed a new algorithm that accelerates RANSAC, maintaining its reliability. The algorithm, called FMBF, consists on comparing image texture patterns between pictures, preserving the most similar ones. There are several types of comparisons, with different computational cost and reliability. FMBF manages those comparisons in order to optimize the trade-off between speed and reliability.

Teleoperation of a service robot using a mobile device

Teleoperation is a concept born with the rapid evolution of technology, with an intuitive meaning "operate at a distance." The first teleoperation system was created in the mid 1950s, which were handled chemicals. Remote controlled systems are present nowadays in various types of applications. This dissertation presents the development of a mobile application to perform the teleoperation of a mobile service robot. The application integrates a distributed surveillance (the result of a research project QREN) and led to the development of a communication interface between the robot (the result of another QREN project) and the vigilance system. It was necessary to specify a communication protocol between the two systems, which was implemented over a communication framework 0MQ (Zero Message Queue). For the testing, three prototype applications were developed before to perform the test on the robot.

Integration of a mobile autonomous robot in a surveillance multi-agent system

This dissertation aims to guarantee the integration of a mobile autonomous robot equipped with many sensors in a multi-agent distributed and georeferenced surveillance system. The integration of a mobile autonomous robot in this system leads to new features that will be available to clients of surveillance system may use. These features may be of two types: using the robot as an agent that will act in the environment or by using the robot as a mobile set of sensors. As an agent in the system, the robot can move to certain locations when alerts are received, in order to acknowledge the underlying events or take to action in order to assist in resolving this event. As a sensor platform in the system, it is possible to access information that is read from the sensors of the robot and access complementary measurements to the ones taken by other sensors in the multi-agent system. To integrate this mobile robot in an effective way it is necessary to extend the current multi-agent system architecture to make the connection between the two systems and to integrate the functionalities provided by the robot into the multi-agent system.

The influence of fibre orientation on the post-cracking tensile behaviour of steel fibre reinforced self-compacting concrete

Adding fibres to concrete provides several advantages, especially in terms of controlling the crack opening width and propagation after the cracking onset. However, distribution and orientation of the fibres toward the active crack plane are significantly important in order to maximize its benefits. Therefore, in this study, the effect of the fibre distribution and orientation on the post-cracking tensile behaviour of the steel fibre reinforced self-compacting concrete (SFRSCC) specimens is investigated. For this purpose, several cores were extracted from distinct locations of a panel and were subjected to indirect (splitting) and direct tensile tests. The local stress-crack opening relationship (σ-w) was obtained by modelling the splitting tensile test under the finite element framework and by performing an Inverse Analysis (IA) procedure. Afterwards the σ-w law obtained from IA is then compared with the one ascertained directly from the uniaxial tensile tests. Finally, the fibre distribution/orientation parameters were determined adopting an image analysis technique.

The potential field method and the nonlinear attractor dynamics approach: what are the differences?

One of the most popular approaches to path planning and control is the potential field method. This method is particularly attractive because it is suitable for on-line feedback control. In this approach the gradient of a potential field is used to generate the robot's trajectory. Thus, the path is generated by the transient solutions of a dynamical system. On the other hand, in the nonlinear attractor dynamic approach the path is generated by a sequence of attractor solutions. This way the transient solutions of the potential field method are replaced by a sequence of attractor solutions (i.e., asymptotically stable states) of a dynamical system. We discuss at a theoretical level some of the main differences of these two approaches.

Plastic-damage smeared crack model to simulate the behaviour of structures made by cement based materials

This work proposes a constitutive model to simulate nonlinear behaviour of cement based materials subjected to different loading paths. The model incorporates a multidirectional fixed smeared crack approach to simulate crack initiation and propagation, whereas the inelastic behaviour of material between cracks is treated by a numerical strategy that combines plasticity and damage theories. For capturing more realistically the shear stress transfer between the crack surfaces, a softening diagram is assumed for modelling the crack shear stress versus crack shear strain. The plastic damage model is based on the yield function, flow rule and evolution law for hardening variable, and includes an explicit isotropic damage law to simulate the stiffness degradation and the softening behaviour of cement based materials in compression. This model was implemented into the FEMIX computer program, and experimental tests at material scale were simulated to appraise the predictive performance of this constitutive model. The applicability of the model for simulating the behaviour of reinforced concrete shear wall panels submitted to biaxial loading conditions, and RC beams failing in shear is investigated.

The impact of PBL on transferable skills development in management education

Attention to transferable skills is growing in higher education. Problem-based learning (PBL) is increasingly used in management education for its promising potential to, amongst others, promote transferable skills, including problem-solving, critical thinking and teamwork skills. However, this relationship is seldom assessed. In this study, I use structural equation modelling to examine the effectiveness of PBL, measured through students’ perceptions of satisfaction and skills development. Results show the development of transferable skills is explained by interaction with tutors and a host company, and defining teamwork rules. Satisfaction is explained by skills development, assessment issues, defining teamwork rules and understanding how organisations work. I draw conclusions and recommendations.

Generating timed trajectories foran autonomous robot

Tese de Doutoramento Programa Doutoral em Engenharia Electrónica e Computadores

Off-line simulation inspires insight: a neurodynamics approach to efficient robot task learning

There is currently an increasing demand for robots able to acquire the sequential organization of tasks from social learning interactions with ordinary people. Interactive learning-by-demonstration and communication is a promising research topic in current robotics research. However, the efficient acquisition of generalized task representations that allow the robot to adapt to different users and contexts is a major challenge. In this paper, we present a dynamic neural field (DNF) model that is inspired by the hypothesis that the nervous system uses the off-line re-activation of initial memory traces to incrementally incorporate new information into structured knowledge. To achieve this, the model combines fast activation-based learning to robustly represent sequential information from single task demonstrations with slower, weight-based learning during internal simulations to establish longer-term associations between neural populations representing individual subtasks. The efficiency of the learning process is tested in an assembly paradigm in which the humanoid robot ARoS learns to construct a toy vehicle from its parts. User demonstrations with different serial orders together with the correction of initial prediction errors allow the robot to acquire generalized task knowledge about possible serial orders and the longer term dependencies between subgoals in very few social learning interactions. This success is shown in a joint action scenario in which ARoS uses the newly acquired assembly plan to construct the toy together with a human partner.

Development of a thermoelectric generator for the exhaust of a vehicle

Dissertação de mestrado integrado em Engenharia Mecânica