Data-driven and data-oriented methods for materials science and technologies

The discovery of new materials and their functions has always been a fundamental component of technological progress. Nowadays, the quest for new materials is stronger than ever: sustainability, medicine, robotics and electronics are all key assets which depend on the ability to create specifically tailored materials. However, designing materials with desired properties is a difficult task, and the complexity of the discipline makes it difficult to identify general criteria. While scientists developed a set of best practices (often based on experience and expertise), this is still a trial-and-error process. This becomes even more complex when dealing with advanced functional materials. Their properties depend on structural and morphological features, which in turn depend on fabrication procedures and environment, and subtle alterations leads to dramatically different results. Because of this, materials modeling and design is one of the most prolific research fields. Many techniques and instruments are continuously developed to enable new possibilities, both in the experimental and computational realms. Scientists strive to enforce cutting-edge technologies in order to make progress. However, the field is strongly affected by unorganized file management, proliferation of custom data formats and storage procedures, both in experimental and computational research. Results are difficult to find, interpret and re-use, and a huge amount of time is spent interpreting and re-organizing data. This also strongly limit the application of data-driven and machine learning techniques. This work introduces possible solutions to the problems described above. Specifically, it talks about developing features for specific classes of advanced materials and use them to train machine learning models and accelerate computational predictions for molecular compounds; developing method for organizing non homogeneous materials data; automate the process of using devices simulations to train machine learning models; dealing with scattered experimental data and use them to discover new patterns.

Innovative photoresponsive materials & supramolecular structures

This thesis focuses on two main topics: photoresponsive azobenzene-based polymers and supramolecular systems generated by the self-assembly of lipophilic guanosines. In the first chapters describe innovative photoresponsive devices and materials capable of performing multiple roles in the field of soft robotics and energy conversion. Chapter 2 describes a device obtained by coupling a photoresponsive liquid-crystalline network and a piezoelectric polymer to convert visible light into electricity. Chapter 3 deals with a material that can assume different shapes when triggered by three different stimuli in different environments. Chapter 4 reports a highly performing artificial muscle that contracts when irradiated. The last two chapters report on supramolecular structures generated from functionalized guanosines dissolved in organic solvents. Chapter 6 illustrates the self-assembly into G-quadruplexes of 8- and 5’-functionalized guanosines in the absence of templating ions. Chapter 7 describes the supramolecular structure generated by the assembly of a lipophilic guanosine in the presence of silver cations. Chapter 6 is reproduced from an already published paper, while the other chapters are going to be submitted to different journals in a couple of months.

An Image Recognition Software for Identification of Vehicle Homologation Tags

In recent years, we have witnessed great changes in the industrial environment as a result of the innovations introduced by Industry 4.0, especially in the integration of Internet of Things, Automation and Robotics in the manufacturing field. The project presented in this thesis lies within this innovation context and describes the implementation of an Image Recognition application focused on the automotive field. The project aims at helping the supply chain operator to perform an effective and efficient check of the homologation tags present on vehicles. The user contribution consists in taking a picture of the tag and the application will automatically, exploiting Amazon Web Services, return the result of the control about the correctness of the tag, the correct positioning within the vehicle and the presence of faults or defects on the tag. To implement this application we ombined two IoT platforms widely used in industrial field: Amazon Web Services(AWS) and ThingWorx. AWS exploits Convolutional Neural Networks to perform Text Detection and Image Recognition, while PTC ThingWorx manages the user interface and the data manipulation.

Caratterizzazione e progettazione di un attuatore differenziale elastico compatto per la robotica collaborativa

Lo sviluppo della robotica collaborativa, in particolare nelle applicazioni di processi industriali in cui sono richieste la flessibilità decisionale di un utilizzatore umano e le prestazioni di forza e precisione garantite dal robot, pone continue sfide per il miglioramento della capacità di progettare e controllare al meglio questi apparati, rendendoli sempre più accessibili in termini economici e di fruibilità. Questo cambio di paradigma rispetto ai tradizionali robot industriali, verso la condivisone attiva degli ambienti di lavoro tra uomo e macchina, ha accelerato lo sviluppo di nuove soluzioni per rendere possibile l’impiego di robot che possano interagire con un ambiente in continua mutazione, in piena sicurezza. Una possibile soluzione, ancora non diffusa commercialmente, ma largamente presente in letteratura, è rappresentata dagli attuatori elastici. Tra gli attuatori elastici, l’architettura che ad oggi ha destato maggior interesse è quella seriale, in cui l’elemento cedevole viene posto tra l’uscita del riduttore ed il carico. La bibliografia mostra come alcuni limiti della architettura seriale possano essere superati a parità di proprietà dinamiche. La soluzione più promettente è l’architettura differenziale, che si caratterizza per l’utilizzo di riduttori ad un ingresso e due uscite. I vantaggi mostrati dai primi risultati scientifici evidenziano l’ottenimento di modelli dinamici ideali paragonabili alla più nota architettura seriale, superandola in compattezza ed in particolare semplificando l’installazione dei sensori necessari al controllo. In questa tesi viene effettuata un’analisi dinamica preliminare ed uno studio dell’attitudine del dispositivo ad essere utilizzato in contesto collaborativo. Una volta terminata questa fase, si presenta il design e la progettazione di un prototipo, con particolare enfasi sulla scelta di componenti commerciali ed il loro dimensionamento, oltre alla definizione della architettura costruttiva complessiva.

Enhanced switchgear connection testing through augmented reality: early developments

Augmented reality is an emerging field of interactive design in which virtual material is seamlessly blended with displays of real world environments. The tremendous potential of augmented reality has begun to be explored with the emergence of personal mobile devices capable of constructing engaging augmented reality experiences. This work is part of a project aiming at using augmented reality goggles to bring advance information to the user interacting with switch-gear during automation cabling. In particular we will be focusing on the recognition and definition of the figures of the component on the AR device. In this part we are using standard camera that allows us to get real images and helps us to localize the gearbox in space through ARUCO marker and we can exploit in order to re-project the actual shape of the component that are currently interested in manipulation by exploiting the data provided by the database. The experiments are carried out using the camera to get the images of the real world switch-gear and re-project those images with the component superimposed on it. Using transforms of the database we did localization to re-project the rendered image of component exactly on the real world component, which can be further integrated in AR goggles to see the component superimposed in real-time.

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.

Motor Unit Spike Trains Recontruction from sEMG Signals for Gesture Classification on a Low-Power Processing Platform

Hand gesture recognition based on surface electromyography (sEMG) signals is a promising approach for the development of intuitive human-machine interfaces (HMIs) in domains such as robotics and prosthetics. The sEMG signal arises from the muscles' electrical activity, and can thus be used to recognize hand gestures. The decoding from sEMG signals to actual control signals is non-trivial; typically, control systems map sEMG patterns into a set of gestures using machine learning, failing to incorporate any physiological insight. This master thesis aims at developing a bio-inspired hand gesture recognition system based on neuromuscular spike extraction rather than on simple pattern recognition. The system relies on a decomposition algorithm based on independent component analysis (ICA) that decomposes the sEMG signal into its constituent motor unit spike trains, which are then forwarded to a machine learning classifier. Since ICA does not guarantee a consistent motor unit ordering across different sessions, 3 approaches are proposed: 2 ordering criteria based on firing rate and negative entropy, and a re-calibration approach that allows the decomposition model to retain information about previous sessions. Using a multilayer perceptron (MLP), the latter approach results in an accuracy up to 99.4% in a 1-subject, 1-degree of freedom scenario. Afterwards, the decomposition and classification pipeline for inference is parallelized and profiled on the PULP platform, achieving a latency < 50 ms and an energy consumption < 1 mJ. Both the classification models tested (a support vector machine and a lightweight MLP) yielded an accuracy > 92% in a 1-subject, 5-classes (4 gestures and rest) scenario. These results prove that the proposed system is suitable for real-time execution on embedded platforms and also capable of matching the accuracy of state-of-the-art approaches, while also giving some physiological insight on the neuromuscular spikes underlying the sEMG.

Distributed collision-free traffic management via vertex cover for multi-vehicle systems

In this thesis, we state the collision avoidance problem as a vertex covering problem, then we consider a distributed framework in which a team of cooperating Unmanned Vehicles (UVs) aim to solve this optimization problem cooperatively to guarantee collision avoidance between group members. For this purpose, we implement a distributed control scheme based on a robust Set-Theoretic Model Predictive Control ( ST-MPC) strategy, where the problem involves vehicles with independent dynamics but with coupled constraints, to capture required cooperative behavior.

Development of a Robotic Wires Storage System for Switchgear Manufacturing Automation

Considering the great development of robotics in industrial automation, the Remodel project aims to reproduce, through the use of Cobots, the wiring activity typical of a human operator and to realize an autonomous storage work. My researches focused on this second topic. In this paper, we will see how to realize a gripper compatible with an Omron TM5X-900, able to perform a pick and place of different types of cables, but also how to compute possible trajectories. In particular, what I needed, was a trajectory going from the Komax, the cables production machine, to a Warehouse taking into account the possible entangles of cables with the robot during its motion. The last part has been dedicated to the synchronization between robot and main machine work.

A comprehensive study on robotic manipulation of deformable linear objects

There are many deformable objects such as papers, clothes, ropes in a person’s living space. To have a robot working in automating the daily tasks it is important that the robot works with these deformable objects. Manipulation of deformable objects is a challenging task for robots because these objects have an infinite-dimensional configuration space and are expensive to model, making real-time monitoring, planning and control difficult. It forms a particularly important field of robotics with relevant applications in different sectors such as medicine, food handling, manufacturing, and household chores. In this report, there is a clear review of the approaches used and are currently in use along with future developments to achieve this task. My research is more focused on the last 10 years, where I have systematically reviewed many articles to have a clear understanding of developments in this field. The main contribution is to show the whole landscape of this concept and provide a broad view of how it has evolved. I also explained my research methodology by following my analysis from the past to the present along with my thoughts for the future.

Robotic grasping: State of the art and modular real-world implementation

Robotic Grasping is an important research topic in robotics since for robots to attain more general-purpose utility, grasping is a necessary skill, but very challenging to master. In general the robots may use their perception abilities like an image from a camera to identify grasps for a given object usually unknown. A grasp describes how a robotic end-effector need to be positioned to securely grab an object and successfully lift it without lost it, at the moment state of the arts solutions are still far behind humans. In the last 5–10 years, deep learning methods take the scene to overcome classical problem like the arduous and time-consuming approach to form a task-specific algorithm analytically. In this thesis are present the progress and the approaches in the robotic grasping field and the potential of the deep learning methods in robotic grasping. Based on that, an implementation of a Convolutional Neural Network (CNN) as a starting point for generation of a grasp pose from camera view has been implemented inside a ROS environment. The developed technologies have been integrated into a pick-and-place application for a Panda robot from Franka Emika. The application includes various features related to object detection and selection. Additionally, the features have been kept as generic as possible to allow for easy replacement or removal if needed, without losing time for improvement or new testing.