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.

Virtualization of Wiring Harness Manipulation Tasks through the PyChrono Simulation Engine

The purpose of this thesis work is the study and creation of a harness modelling system. The model needs to simulate faithfully the physical behaviour of the harness, without any instability or incorrect movements. Since there are various simulation engines that try to model wiring's systems, this thesis work focused on the creation and test of a 3D environment with wiring and other objects through the PyChrono Simulation Engine. Fine-tuning of the simulation parameters were done during the test to achieve the most stable and correct simulation possible, but tests showed the intrinsic limits of the Engine regarding the collisions' detection between the various part of the cables, while collisions between cables and other physical objects such as pavement, walls and others are well managed by the simulator. Finally, the main purpose of the model is to be used to train Artificial Intelligence through Reinforcement Learnings techniques, so we designed, using OpenAI Gym APIs, the general structure of the learning environment, defining its basic functions and an initial framework.

Tuning automatico di parametri in un sistema di controllo semaforico auto-organizzante

L'elaborato di tesi tratta dei vantaggi ottenibili dall'uso di tecniche di automatic parameter tuning, applicando un'implementazione di iterated racing su di un innovativo sistema di controllo semaforico auto-organizzante ispirato da concetti di swarm intelligence.

Studio e ottimizzazione di un sistema automatico per il cambiamento del setup in un motoveicolo sportivo

In the racing field the possibility to change the suspension settings can improve the overall performance of motorcycles, adapting to any type of circuit, any driving style and any weather condition, increasing the feeling of the rider with the vehicle. The present study investigated the pressure and forces related to changes in the oil level inside of the front fork. Seeing the importance of the change of the oil level have been developed an automated device, to be installed in the forks of original sports motorcycles, with the function to vary the level of oil in an automatic way. This system, having the possibility to continuously change the partial setup, could allow the optimization of the forks in each sector of the track, through a unit that automates the change. The project of the system has been presented to teams and riders of national championships and they showed interest on it.

Design and implementation of a synchronous interleaved boost converter for fuel cell-powered catamaran

The present work describes the different stages of design, implementation, and validation procedures for an interleaved DC-DC boost converter intended for the 2022 Futura, a fuel cell-powered racing catamaran developed by the UniBoAT team. The main goal of the entire design has been the significant reduction of the weight of the converter by removing heat sinks and reducing component size while increasing its efficiency by adopting high-end power switches and the interleaved architecture operated with a synchronous control strategy. The obtained converter has been integrated into the structure containing the fuel cell stack obtaining a fully integrated system. The realized device has been based on an interleaved architecture with six phases controlled digitally through the average current mode control. The design has been validated through simulations carried out using the software LT-Spice, whereas experimental validations have been performed by means of laboratory bench tests and on-field tests. Detailed thermal and efficiency analyses are provided with the bench tests under the two synchronous and non-synchronous operating modes and with the adoption of the phase shedding technique. The prototype implementation and its performance in real operating conditions are also discussed. Eventually, it is underlined as the designed converter can be used in other applications requiring a voltage-controlled boost converter.

Rilevazione ottica delle dimensioni della camera di combustione per la stima del rapporto di compressione reale

La ricerca di un'ottima qualità costruttiva è diventata, per ogni fornitore o produttore legato all’ambito automotive/motoristico, l’aspetto principale nella produzione di un veicolo, soprattutto nel caso specifico di un motore: per garantire, dunque, una buona qualità generale lungo tutta la gamma di produzione, è necessario avere una buona “ripetibilità” di costruzione, ossia, è fondamentale poter assemblare un alto numero di motori che siano il più possibile identici tra loro; considerando tutte le variabili che intervengono lungo la catena di produzione, a partire dalla banale lavorazione meccanica delle parti, fino all’assemblaggio stesso del motore. E' facilmente intuibile, pertanto, come non sia così raro avere delle leggere imperfezioni tra motore e motore che possono poi andare ad impattare sulla vita e sulle performance stesse del mezzo. Questo discorso è ancora più valido se si parla dell’ambito racing, in cui la qualità costruttiva, e, quindi, le performance, giocano un ruolo fondamentale nella progettazione di un motore, nonostante il volume produttivo sia tutto sommato piccolo. L’obiettivo dell'elaborato è quello di creare un metodo di controllo e di confronto della qualità/precisione costruttiva, intesa sia come qualità di produzione delle parti che di assemblaggio del motore finito. A partire da una scansione laser tridimensionale, sotto forma di una nuvola di punti, si è creato un software di elaborazione dati che permettesse di arrivare a calcolare il rapporto di compressione reale del motore in analisi e la mappa di squish tramite la sovrapposizione virtuale delle due scansioni relative ai cilindri/pistoni del blocco motore e la testa del motore stesso.