Pedro Correia Pereira da Silva

Textile moisture sensor matrix for monitoring of disabled and bed-rest patients

This paper presents the development of a moisture sensor matrix based on textile materials provided with conductive yarns. The measurement principle is based on the measurement of electrical resistance of the textile. The main purpose of this work is to support research on the prevention of pressure ulcers in people committed to bed rest or using wheelchairs. In the first stage of development, the project is studying the relation between physical parameters, exposure time and the levels of discomfort and pain experienced by the patients. In a later stage, the underlying measurement and evaluation principles will be used to develop single sensors or sensor matrixes to be connected to active patient monitoring systems able to warn in situations of excess of moisture and/or pressure (produced by sweat, open wounds, incontinence, etc.).

Operative Conditions Evaluation for Efficient Building Retrofit—A Case Study

The implementation of energy efficiency measures into the existing building stock is essential to meet the 2020 targets set by the European Union (EU) Energy Performance of Buildings Directive (EPBD) and reinforced with the “EPBD-recast”. Thus, energy refurbishment of existing buildings is fundamental to achieve these goals. However, energy issues should not be the only concerns since the indoor environmental quality (IEQ) is also as important. When planning a building retrofit it is then necessary to consider the energy efficiency requirements as well as the IEQ. To do so, the main problems of the existing buildings should be identified. This work presents a study carried out in a large office building to identify the main pathologies related to the energy efficiency and to the IEQ. The main objective of this study was to characterize the actual situation of a building that represents a great number of the Portuguese office buildings in order to identify the principal problems that occurs in this type of buildings, to support the development of a refurbishment project of the building that can optimize both the energy efficiency and the relevant parameters to the IEQ and that are also solutions with potential to be used in other buildings.

Adaptive Quadruped Locomotion: Learning to Detect and Avoid an Obstacle

Autonomy and adaptability are key features in the design and construction of a robotic system capable of carrying out tasks in an unstructured and not predefined environment. Such adaptability is generally observed in animals, biological systems that often serve as inspiration models to the design of robots. The autonomy and adaptability of these systems partially arises from their ability to learn.

RESEARCH ON THE PORTUGUESE BUILDING STOCK AND ITS IMPACTS ON ENERGY CONSUMPTION – AN AVERAGE U-VALUE APPROACH

Abstract The article aims to evaluate the Portuguese building stock energy policies and strategy for energy saving in buildings among the EU members. It was found out the average heat transfer coefficients of the main structural elements of Portuguese Buildings and analyzed the U-values of this elements considering different time periods. The fundamentals of this study were funded by the Agency for Development and Innovation (ADI) and co-financed by the European Regional Development Fund (FEDER) through the Operational Program for Competitiveness Factors (POFC) assigned to the Building Physics and Construction Technology Laboratory with the reference SB Tool SPT_2011_4.

Visually guided gait modifications for stepping over an obstacle: a bio-inspired approach

There is an increasing interest in conceiving robotic systems that are able to move and act in an unstructured and not predefined environment, for which autonomy and adaptability are crucial features. In nature, animals are autonomous biological systems, which often serve as bio-inspiration models, not only for their physical and mechanical properties, but also their control structures that enable adaptability and autonomy—for which learning is (at least) partially responsible. This work proposes a system which seeks to enable a quadruped robot to online learn to detect and to avoid stumbling on an obstacle in its path. The detection relies in a forward internal model that estimates the robot’s perceptive information by exploring the locomotion repetitive nature. The system adapts the locomotion in order to place the robot optimally before attempting to step over the obstacle, avoiding any stumbling. Locomotion adaptation is achieved by changing control parameters of a central pattern generator (CPG)-based locomotion controller. The mechanism learns the necessary alterations to the stride length in order to adapt the locomotion by changing the required CPG parameter. Both learning tasks occur online and together define a sensorimotor map, which enables the robot to learn to step over the obstacle in its path. Simulation results show the feasibility of the proposed approach.

Sensitivity analysis of a crawl gait multi-objective optimization system

This paper describes the analysis of a stable crawl gait multi-objective optimization system that combines bio-inspired Central Patterns Generators (CPGs) and a multi-objective evolutionary algorithm. In order to optimize the crawl gait, a multi-objective problem, an optimization system based on NSGA-II allows to find a set of non-dominated solutions that correspond to different motor solutions. The experimental results highlight the effectiveness of this multi-objective approach.

Optimization of stable quadruped locomotion using mutual information

Central Pattern Generators (CPG)s have been widely used in the field of robotics to address the task of legged locomotion generation. The adequate configuration of these structures for a given platform can be accessed through evolutionary strategies, according to task dependent selection pressures. Information driven evolution, accounts for information theoretical measures as selection pressures, as an alternative to a fully task dependent selection pressure. In this work we exploit this concept and evaluate the use of mean Mutual Information, as a selection pressure towards a CPG configuration capable of faster, yet more coordinated and stabler locomotion than when only a task dependent selection pressure is used.

Reinforcement learning: Solving two case studies

Reinforcement Learning algorithms offer interesting features for the control of autonomous systems, such as the ability to learn from direct interaction with the environment, and the use of a simple reward signalas opposed to the input-outputs pairsused in classic supervised learning. The reward signal indicates the success of failure of the actions executed by the agent in the environment. In this work, are described RL algorithmsapplied to two case studies: the Crawler robot and the widely known inverted pendulum. We explore RL capabilities to autonomously learn a basic locomotion pattern in the Crawler, andapproach the balancing problem of biped locomotion using the inverted pendulum.