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.

Learning for scheduling a portfolio of constraint solvers

Nel lavoro di tesi qui presentato si indaga l'applicazione di tecniche di apprendimento mirate ad una più efficiente esecuzione di un portfolio di risolutore di vincoli (constraint solver). Un constraint solver è un programma che dato in input un problema di vincoli, elabora una soluzione mediante l'utilizzo di svariate tecniche. I problemi di vincoli sono altamente presenti nella vita reale. Esempi come l'organizzazione dei viaggi dei treni oppure la programmazione degli equipaggi di una compagnia aerea, sono tutti problemi di vincoli. Un problema di vincoli è formalizzato da un problema di soddisfacimento di vincoli(CSP). Un CSP è descritto da un insieme di variabili che possono assumere valori appartenenti ad uno specico dominio ed un insieme di vincoli che mettono in relazione variabili e valori assumibili da esse. Una tecnica per ottimizzare la risoluzione di tali problemi è quella suggerita da un approccio a portfolio. Tale tecnica, usata anche in am- biti come quelli economici, prevede la combinazione di più solver i quali assieme possono generare risultati migliori di un approccio a singolo solver. In questo lavoro ci preoccupiamo di creare una nuova tecnica che combina un portfolio di constraint solver con tecniche di machine learning. Il machine learning è un campo di intelligenza articiale che si pone l'obiettivo di immettere nelle macchine una sorta di `intelligenza'. Un esempio applicativo potrebbe essere quello di valutare i casi passati di un problema ed usarli in futuro per fare scelte. Tale processo è riscontrato anche a livello cognitivo umano. Nello specico, vogliamo ragionare in termini di classicazione. Una classicazione corrisponde ad assegnare ad un insieme di caratteristiche in input, un valore discreto in output, come vero o falso se una mail è classicata come spam o meno. La fase di apprendimento sarà svolta utilizzando una parte di CPHydra, un portfolio di constraint solver sviluppato presso la University College of Cork (UCC). Di tale algoritmo a portfolio verranno utilizzate solamente le caratteristiche usate per descrivere determinati aspetti di un CSP rispetto ad un altro; queste caratteristiche vengono altresì dette features. Creeremo quindi una serie di classicatori basati sullo specifico comportamento dei solver. La combinazione di tali classicatori con l'approccio a portfolio sara nalizzata allo scopo di valutare che le feature di CPHydra siano buone e che i classicatori basati su tali feature siano affidabili. Per giusticare il primo risultato, eettueremo un confronto con uno dei migliori portfolio allo stato dell'arte, SATzilla. Una volta stabilita la bontà delle features utilizzate per le classicazioni, andremo a risolvere i problemi simulando uno scheduler. Tali simulazioni testeranno diverse regole costruite con classicatori precedentemente introdotti. Prima agiremo su uno scenario ad un processore e successivamente ci espanderemo ad uno scenario multi processore. In questi esperimenti andremo a vericare che, le prestazioni ottenute tramite l'applicazione delle regole create appositamente sui classicatori, abbiano risultati migliori rispetto ad un'esecuzione limitata all'utilizzo del migliore solver del portfolio. I lavoro di tesi è stato svolto in collaborazione con il centro di ricerca 4C presso University College Cork. Su questo lavoro è stato elaborato e sottomesso un articolo scientico alla International Joint Conference of Articial Intelligence (IJCAI) 2011. Al momento della consegna della tesi non siamo ancora stati informati dell'accettazione di tale articolo. Comunque, le risposte dei revisori hanno indicato che tale metodo presentato risulta interessante.

Self-identification of problems in the process of listening to English in pre-service interpreters

Questa tesi ha come oggetto di studio i problemi riscontrati nelle trascrizioni di testi orali in lingua inglese prodotte da 39 studenti della laurea magistrale in Interpretazione. Nel Capitolo 1 viene presentato l’ascolto, che viene definito prima da un punto di vista storico, poi analizzato come processo composto da quattro fasi, come sostiene Michael Rost (2011). Il capitolo si conclude con l’ascolto nell’ambito dell’interpretazione. Nel Capitolo 2 viene analizzato in maniera contrastiva l’apprendimento dell’ascolto nella prima e nella seconda lingua. I primi due capitoli forniscono le basi per comprendere il caso di studio. Il Capitolo 3 concerne la metodologia dello studio. Vengono presentati il metodo di analisi delle trascrizioni, la categorizzazione dei problemi riscontrati e il processo di creazione del sistema di analisi utilizzato. Nel Capitolo 4 vengono presentati i dati ottenuti seguendo il metodo esposto nel Capitolo 3. Si presentano i problemi riscontrati, che vengono suddivisi in categorie in base a ciò che può averli causati. Il Capitolo 5 è dedicato alle conclusioni. Qui vengono suggerite possibili strategie mirate ad aiutare gli studenti di Interpretazione a migliorare le proprie capacità di ascolto in lingua inglese. Esta tesis quiere analizar los problemas encontrados en transcripciones de textos orales en inglés hechas por 39 estudiantes del máster en Interpretación. En el Capítulo 1 se presenta la escucha, que se define primero desde una perspectiva histórica, y luego como un proceso formado por cuatro fases, como argumenta Michael Rost (2011). El capítulo se cierra con la escucha en el ámbito de la interpretación. En el Capítulo 2 se analizan de forma contrastiva el aprendizaje de la escucha en la primera y segunda lengua. Los primeros dos capítulos constituyen la base para comprender el caso de estudio. El Capítulo 3 atañe a la metodología del estudio. Se presentan el método de análisis de las transcripciones, la categorización de los problemas encontrados y el proceso de creación del sistema de análisis que se ha empleado. En el Capítulo 4 se proporcionan los datos obtenidos gracias al método presentado en el Capítulo 3. Se presentan los problemas encontrados, que han sido divididos en categorías según qué puede haberlos ocasionado. El Capítulo 5 está dedicado a las conclusiones. Aquí se sugieren posibles estrategias cuyo objetivo es ayudar a los estudiantes de Interpretación a mejorar sus capacidades de escucha en inglés.

Learning from experience: Analysis of the civil litigation regarding building structures on the court of bologna in the years 2011/2012

The present work is aimed to the study and the analysis of the defects detected in the civil structure and that are object of civil litigation in order to create an instruments capable of helping the different actor involved in the building process. It is divided in three main sections. The first part is focused on the collection of the data related to the civil proceeding of the 2012 and the development of in depth analysis of the main aspects regarding the defects on existing buildings. The research center “Osservatorio Claudio Ceccoli” developed a system for the collection of the information coming from the civil proceedings of the Court of Bologna. Statistical analysis are been performed and the results are been shown and discussed in the first chapters.The second part analyzes the main issues emerged during the study of the real cases, related to the activities of the technical consultant. The idea is to create documents, called “focus”, addressed to clarify and codify specific problems in order to develop guidelines that help the technician editing of the technical advice.The third part is centered on the estimation of the methods used for the collection of data. The first results show that these are not efficient. The critical analysis of the database, the result and the experience and throughout, allowed the implementation of the collection system for the data.

Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Robotic Manipulation of DLOs for Wiring Harness Assembly: a Machine Learning Approach

In recent times, a significant research effort has been focused on how deformable linear objects (DLOs) can be manipulated for real world applications such as assembly of wiring harnesses for the automotive and aerospace sector. This represents an open topic because of the difficulties in modelling accurately the behaviour of these objects and simulate a task involving their manipulation, considering a variety of different scenarios. These problems have led to the development of data-driven techniques in which machine learning techniques are exploited to obtain reliable solutions. However, this approach makes the solution difficult to be extended, since the learning must be replicated almost from scratch as the scenario changes. It follows that some model-based methodology must be introduced to generalize the results and reduce the training effort accordingly. The objective of this thesis is to develop a solution for the DLOs manipulation to assemble a wiring harness for the automotive sector based on adaptation of a base trajectory set by means of reinforcement learning methods. The idea is to create a trajectory planning software capable of solving the proposed task, reducing where possible the learning time, which is done in real time, but at the same time presenting suitable performance and reliability. The solution has been implemented on a collaborative 7-DOFs Panda robot at the Laboratory of Automation and Robotics of the University of Bologna. Experimental results are reported showing how the robot is capable of optimizing the manipulation of the DLOs gaining experience along the task repetition, but showing at the same time a high success rate from the very beginning of the learning phase.

Smart sampling approaches for Decision-Focused Learning

Many real-word decision- making problems are defined based on forecast parameters: for example, one may plan an urban route by relying on traffic predictions. In these cases, the conventional approach consists in training a predictor and then solving an optimization problem. This may be problematic since mistakes made by the predictor may trick the optimizer into taking dramatically wrong decisions. Recently, the field of Decision-Focused Learning overcomes this limitation by merging the two stages at training time, so that predictions are rewarded and penalized based on their outcome in the optimization problem. There are however still significant challenges toward a widespread adoption of the method, mostly related to the limitation in terms of generality and scalability. One possible solution for dealing with the second problem is introducing a caching-based approach, to speed up the training process. This project aims to investigate these techniques, in order to reduce even more, the solver calls. For each considered method, we designed a particular smart sampling approach, based on their characteristics. In the case of the SPO method, we ended up discovering that it is only necessary to initialize the cache with only several solutions; those needed to filter the elements that we still need to properly learn. For the Blackbox method, we designed a smart sampling approach, based on inferred solutions.

Problems in physics and mathematics contexts with middle and high school classes: vertical and horizontal comparison

My thesis falls within the framework of physics education and teaching of mathematics. The objective of this report was made possible by using geometrical (in mathematics) and qualitative (in physics) problems. We have prepared four (resp. three) open answer exercises for mathematics (resp. physics). The test batch has been selected across two different school phases: end of the middle school (third year, 8\textsuperscript{th} grade) and beginning of high school (second and third year, 10\textsuperscript{th} and 11\textsuperscript{th} grades respectively). High school students achieved the best results in almost every problem, but 10\textsuperscript{th} grade students got the best overall results. Moreover, a clear tendency to not even try qualitative problems resolution has emerged from the first collection of graphs, regardless of subject and grade. In order to improve students' problem-solving skills, it is worth to invest on vertical learning and spiral curricula. It would make sense to establish a stronger and clearer connection between physics and mathematical knowledge through an interdisciplinary approach.

Machine Learning in Automatic Tabulation for Constraint Model Reformulation

Combinatorial decision and optimization problems belong to numerous applications, such as logistics and scheduling, and can be solved with various approaches. Boolean Satisfiability and Constraint Programming solvers are some of the most used ones and their performance is significantly influenced by the model chosen to represent a given problem. This has led to the study of model reformulation methods, one of which is tabulation, that consists in rewriting the expression of a constraint in terms of a table constraint. To apply it, one should identify which constraints can help and which can hinder the solving process. So far this has been performed by hand, for example in MiniZinc, or automatically with manually designed heuristics, in Savile Row. Though, it has been shown that the performances of these heuristics differ across problems and solvers, in some cases helping and in others hindering the solving procedure. However, recent works in the field of combinatorial optimization have shown that Machine Learning (ML) can be increasingly useful in the model reformulation steps. This thesis aims to design a ML approach to identify the instances for which Savile Row’s heuristics should be activated. Additionally, it is possible that the heuristics miss some good tabulation opportunities, so we perform an exploratory analysis for the creation of a ML classifier able to predict whether or not a constraint should be tabulated. The results reached towards the first goal show that a random forest classifier leads to an increase in the performances of 4 different solvers. The experimental results in the second task show that a ML approach could improve the performance of a solver for some problem classes.