3D Visual Data-Driven Spatiotemporal Deformations for Non-Rigid Object Grasping Using Robot Hands

Sensing techniques are important for solving problems of uncertainty inherent to intelligent grasping tasks. The main goal here is to present a visual sensing system based on range imaging technology for robot manipulation of non-rigid objects. Our proposal provides a suitable visual perception system of complex grasping tasks to support a robot controller when other sensor systems, such as tactile and force, are not able to obtain useful data relevant to the grasping manipulation task. In particular, a new visual approach based on RGBD data was implemented to help a robot controller carry out intelligent manipulation tasks with flexible objects. The proposed method supervises the interaction between the grasped object and the robot hand in order to avoid poor contact between the fingertips and an object when there is neither force nor pressure data. This new approach is also used to measure changes to the shape of an object’s surfaces and so allows us to find deformations caused by inappropriate pressure being applied by the hand’s fingers. Test was carried out for grasping tasks involving several flexible household objects with a multi-fingered robot hand working in real time. Our approach generates pulses from the deformation detection method and sends an event message to the robot controller when surface deformation is detected. In comparison with other methods, the obtained results reveal that our visual pipeline does not use deformations models of objects and materials, as well as the approach works well both planar and 3D household objects in real time. In addition, our method does not depend on the pose of the robot hand because the location of the reference system is computed from a recognition process of a pattern located place at the robot forearm. The presented experiments demonstrate that the proposed method accomplishes a good monitoring of grasping task with several objects and different grasping configurations in indoor environments.

The Influence of Space Layout, Technology and Teaching Approach on Student Learning: An Architectural Technology Perspective

Some would argue that there is a need for the traditional lecture format to be rethought in favour of a more active approach. However, this must form part of a bipartite strategy, considered in conjunction with the layout of any new space to facilitate alternative learning and teaching methods. With this in mind, this paper begins to examine the impact of the learning environment on the student learning experience, specifically focusing on students studying on the Architectural Technology and Management programme at Ulster University. The aim of this study is two-fold: to increase understanding of the impact of learning space layout, by taking a student centered approach; and to gain an appreciation of how technology can impact upon the learning space. The study forms part of a wider project being undertaken at Ulster University known as the Learning Landscape Transition Project, exploring the relationship between learning, teaching and space layout. Data collection was both qualitative and quantitative, with use of a case study supported by a questionnaire based on attitudinal scaling. A focus group was also used to further analyse the key trends resulting from the questionnaire. The initial results suggest that the learning environment, and the technology within it, can not only play an important part in the overall learning experience of the student, but also assist with preparation for the working environment to be experienced in professional life.

Computational models for improved diagnosis and prognosis of stroke using robot-based biomarkers

Stroke is a leading cause of death and permanent disability worldwide, affecting millions of individuals. Traditional clinical scores for assessment of stroke-related impairments are inherently subjective and limited by inter-rater and intra-rater reliability, as well as floor and ceiling effects. In contrast, robotic technologies provide objective, highly repeatable tools for quantification of neurological impairments following stroke. KINARM is an exoskeleton robotic device that provides objective, reliable tools for assessment of sensorimotor, proprioceptive and cognitive brain function by means of a battery of behavioral tasks. As such, KINARM is particularly useful for assessment of neurological impairments following stroke. This thesis introduces a computational framework for assessment of neurological impairments using the data provided by KINARM. This is done by achieving two main objectives. First, to investigate how robotic measurements can be used to estimate current and future abilities to perform daily activities for subjects with stroke. We are able to predict clinical scores related to activities of daily living at present and future time points using a set of robotic biomarkers. The findings of this analysis provide a proof of principle that robotic evaluation can be an effective tool for clinical decision support and target-based rehabilitation therapy. The second main objective of this thesis is to address the emerging problem of long assessment time, which can potentially lead to fatigue when assessing subjects with stroke. To address this issue, we examine two time reduction strategies. The first strategy focuses on task selection, whereby KINARM tasks are arranged in a hierarchical structure so that an earlier task in the assessment procedure can be used to decide whether or not subsequent tasks should be performed. The second strategy focuses on time reduction on the longest two individual KINARM tasks. Both reduction strategies are shown to provide significant time savings, ranging from 30% to 90% using task selection and 50% using individual task reductions, thereby establishing a framework for reduction of assessment time on a broader set of KINARM tasks. All in all, findings of this thesis establish an improved platform for diagnosis and prognosis of stroke using robot-based biomarkers.

Projeto de uma antena para controlo wireless de um robot

A comunicação e transmissão de informação sem fios tornou - se uma realidade cada vez mais utilizada pelas sociedades contemporâneas. A nível profissional, as forças armadas de cada país acharam conveniente modernizar os seus meios, por forma a aumentar a eficiência e a segurança em determinadas tarefas. Nesse sentido, o Exército português adquiriu um robot (ROVIM) cuja função é desempenhar ações de reconhecimento e vigilância de modo a obter informações de forma segura. O objetivo desta dissertação é dimensionar e construir uma antena para controlo wireless do robot (ROVIM). As especificações técnicas desta antena requerem dois modos de operação, um com uma largura de feixe larga e outro com uma largura de feixe estreita. Para alcançar esses objetivos dimensionou-se e construiu-se duas antenas. Na dissertação são construídas duas antenas, a primeira é uma antena Yagi – Uda convencional e a segunda é uma antena com uma estrutura nova que permite a regulação do ganho e da largura de feixe a -3 dB. A primeira antena será o modelo base da segunda antena, que apresenta a inovação do controlo das caraterísticas de radiação. Esse controlo é possível através da introdução de díodos e do respetivo circuito de polarização na estrutura da antena. Inicialmente, as antenas foram dimensionadas e simuladas recorrendo ao programa de simulação CST MWS, de modo a operarem na banda dos 2,4 GHz. Após a construção das antenas, as caraterísticas de radiação foram medidas recorrendo à câmara anecoica e ao network analyzer, permitindo assim a comparação dos resultados medidos com os simulados.

Modello di simulazione del processo di gestione ordini e di outbound in linguaggio Arena

La tesi ha l'obiettivo di analizzare e tradurre in un modello di simulazione il processo di evasione di ordini dal sito di stoccaggio di un’azienda di e-commerce al fine di valutarne le possibili evoluzioni. In prima analisi sono stati evidenziati i principali motivi che spingono i clienti a preferire gli store online rispetto a quelli fisici e come alcuni dei vantaggi siano il frutto dell’efficienza della gestione dell’outbound. Si è passati, quindi, all’esame del caso di studio, alla scomposizione delle singole fasi di lavorazione degli ordini e alla loro traduzione in linguaggio Arena. Il modello ottenuto è stato valutato grazie alla comparazione dei risultati di statistiche automatiche e manuali, frutto della simulazione, con i dati reali. La fase finale ha riguardato, invece, la valutazione in termini di efficienza di una possibile evoluzione del sistema che consiste nell’introduzione di un robot addetto al packing: il modello è stato modificato e le statistiche del caso as-is sono state confrontate con quelle frutto della nuova simulazione. Con i dati utilizzati è stato dimostrato come un unico robot garantisca prestazioni superiori rispetto allo stato attuale e risulti più che sufficiente per la mole di lavoro di una giornata tipo. Nei periodi dell’anno caratterizzati da un aumento esponenziale degli acquisti, tuttavia, potrebbe essere necessario affiancare alla soluzione automatica quella manuale.

Studio e ottimizzazione di un layout. Il caso Luxottica.

Studio e ottimizzazione del layout dello stabilimento Luxottica di Sedico. La prima fase è stata quella di raccolta ed elaborazione dati per arrivare alla divisione in famiglie dei prodotti. Successivamente è stata svolta l'analisi dell'AS-IS (valutazione delle aree, from-to delle distanze, dei viaggi e dei costi). Sono state individuate quindi le criticità e sviluppato il nuovo layout. Sono stati analizzati i costi di movimentazione del TO-BE e sono stati confrontati con l' AS-IS.

Sanford Rossen's design for a robot professor, December 1950

Drawing class. 1949

FROG (formulation of a robot organization that generalizes) : a hardwardware [sic] experiment in machine cognition /

Vita.