Structure learning of graphical models for task-oriented robot grasping

In the collective imaginaries a robot is a human like machine as any androids in science fiction. However the type of robots that you will encounter most frequently are machinery that do work that is too dangerous, boring or onerous. Most of the robots in the world are of this type. They can be found in auto, medical, manufacturing and space industries. Therefore a robot is a system that contains sensors, control systems, manipulators, power supplies and software all working together to perform a task. The development and use of such a system is an active area of research and one of the main problems is the development of interaction skills with the surrounding environment, which include the ability to grasp objects. To perform this task the robot needs to sense the environment and acquire the object informations, physical attributes that may influence a grasp. Humans can solve this grasping problem easily due to their past experiences, that is why many researchers are approaching it from a machine learning perspective finding grasp of an object using information of already known objects. But humans can select the best grasp amongst a vast repertoire not only considering the physical attributes of the object to grasp but even to obtain a certain effect. This is why in our case the study in the area of robot manipulation is focused on grasping and integrating symbolic tasks with data gained through sensors. The learning model is based on Bayesian Network to encode the statistical dependencies between the data collected by the sensors and the symbolic task. This data representation has several advantages. It allows to take into account the uncertainty of the real world, allowing to deal with sensor noise, encodes notion of causality and provides an unified network for learning. Since the network is actually implemented and based on the human expert knowledge, it is very interesting to implement an automated method to learn the structure as in the future more tasks and object features can be introduced and a complex network design based only on human expert knowledge can become unreliable. Since structure learning algorithms presents some weaknesses, the goal of this thesis is to analyze real data used in the network modeled by the human expert, implement a feasible structure learning approach and compare the results with the network designed by the expert in order to possibly enhance it.

Stress Concentration Factor and Fatigue Life Evaluation in offshore tubular KT-Joints

In the last few decades, offshore field has grown fast especially after the notable development of technologies, explorations of oil and gas in deep water and the high concern of offshore companies in renewable energy mainly Wind Energy. Fatigue damage was noticed as one of the main problems causing failure of offshore structures. The purpose of this research is to focus on the evaluation of Stress Concentration Factor and its influence on Fatigue Life for 2 tubular KT-Joints in offshore Jacket structure using different calculation methods. The work is done by using analytical calculations, mainly Efthymiou’s formulations, and numerical solutions, FEM analysis, using ABAQUS software. As for the analytical formulations, the calculations were done according to the geometrical parameters of each method using excel sheets. As for the numerical model, 2 different types of tubular KT-Joints are present where for each model 5 shell element type, 3 solid element type and 3 solid-with-weld element type models were built on ABAQUS. Meshing was assigned according to International Institute of Welding (IIW) recommendations, 5 types of mesh element, to evaluate the Hot-spot stresses. 23 different types of unitary loading conditions were assigned, 9 axial, 7 in-plane bending moment and 7 out-plane bending moment loads. The extraction of Hot-spot stresses and the evaluation of the Stress Concentration Factor were done using PYTHON scripting and MATLAB. Then, the fatigue damage evaluation for a critical KT tubular joint based on Simplified Fatigue Damage Rule and Local Approaches (Strain Damage Parameter and Stress Damage Parameter) methods were calculated according to the maximum Stress Concentration Factor conducted from DNV and FEA methods. In conclusion, this research helped us to compare different results of Stress Concentration Factor and Fatigue Life using different methods and provided us with a general overview about what to study next in the future.

A Comparative Analysis of Dynamical Models for Tidal Dissipation in Natural Satellite Ephemerides

The study of the tides of a celestial bodies can unveil important information about their interior as well as their orbital evolution. The most important tidal parameter is the Love number, which defines the deformation of the gravity field due to an external perturbing body. Tidal dissipation is very important because it drives the secular orbital evolution of the natural satellites, which is even more important in the case of the the Jupiter system, where three of the Galilean moons, Io, Europa and Ganymede, are locked in an orbital resonance where the ratio of their mean motions is 4:2:1. This is called Laplace resonance. Tidal dissipation is described by the dissipation ratio k2/Q, where Q is the quality factor and it describes the dampening of a system. The goal of this thesis is to analyze and compare the two main tidal dynamical models, Mignard's model and gravity field variation model, to understand the differences between each model with a main focus on the single-moon case with Io, which can help also understanding better the differences between the two models without over complicating the dynamical model. In this work we have verified and validated both models, we have compared them and pinpointed the main differences and features that characterize each model. Mignard's model treats the tides directly as a force, while the gravity field variation model describes the tides with a change of the spherical harmonic coefficients. Finally, we have also briefly analyzed the difference between the single-moon case and the two-moon case, and we have confirmed that the governing equations that describe the change of semi-major axis and eccentricity are not good anymore when more moons are present.