Physics-Informed Machine Learning for Trustworthy Control of Autonomous Robots, (2022-2023) - Responsabile Scientifico
Non-EU international research
PE7_10 - Robotics
Obiettivo 9. Costruire un'infrastruttura resiliente e promuovere l'innovazione ed una industrializzazione equa, responsabile e sostenibile
Trustworthy and long-term operations of autonomous robots in populated environments require the design of robust and interpretable control strategies. Two main kinds of controllers currently exist, on which the state of the art largely rests. On the one hand, data-driven controllers use machine learning in a black-box fashion, to provide robustness and generalization capabilities, thanks to the availability of large empirical data sets and the potentiality of Artificial Neural Networks (ANNs). At the other side of the spectrum, model-based controllers leverage the physical knowledge of the system, offering a more interpretable control action at the expense of typically high-dimensional models with limited granularity and adaptation capabilities. In this proposal, we devise a novel, robust and trustworthy control framework for autonomous robots, which seamlessly integrates the benefits of both data-driven and model-based approaches. Inspired to the emerging paradigm of Physics-Informed Machine Learning (PIML), the proposed control framework aims at attaining system robustness, as well as generalization capability and interpretability of learning-based models, with mathematically proved performance guarantees. The framework consists of three components: (i) a physics-informed surrogate model trained with an ad-hoc loss function to ensure physical consistency in the learning of the dynamical model of the robot, (ii) a residual Deep Neural Network (DNN) to provide real-time robustness and adaptability to unknown dynamics, and (iii) a nonlinear predictive controller with performance guarantees, which uses the predictions offered by the previous two models. The successful realization of this project will not only ensure trustworthy operations for safe-critical robotic systems (such as UAVs operating in densely populated areas), but will also attain the broader goal of advancing the state of the art in robust control of highly nonlinear and uncertain dynamical systems.
Mac2Mic - Macro to Micro: uncovering the hidden mechanisms driving network dynamics , (2018-2020) - Responsabile Scientifico
Il progetto di ricerca si propone di inferire delle tecniche “universali” per inferire il modello di sistemi modellabili da una rete complessa, a partire da dati “grezzi”. Per garantire la validazione dei risultati della ricerca verrà sistematizzata la raccolta e l’organizzazione di un’ampia base di dati sperimentali, con particolare riferimento a sistemi epidemici, biologici, neuronali, finanziari. Uno dei prodotti della ricerca sarà la produzione di un software “open source” e gratuito per l’inferenza della dinamica di sistemi complessi a partire da dati sperimentali
Multi-modal crowd sensing to monitor buildings in smart cities, (2017-2018) - Responsabile Scientifico
Non-EU international research
In this project, we will put forward a monitoring system for urban areas using TIR, based on the synergic useof UAVs and cars, to minimize the downsides of both approaches and improving the quality and reliability ofmeasurements. Cars will be used as ground measurement and processing units, as well as ground stationsand relays for UAVs. UAVs collaborative clusters will be used to perform agile and accurate measurementsat the highest levels above the ground. The collected multi-rate, multi-resolution measurement sets will beinterpreted and fused on board of the cars in order to produce accurate analyses of the urban area,especially energetic analyses. This approach leverages the research team skillset, i.e., multi-agent modelingand control, networked control systems, robust optimization, development and testing of guidance,navigation and control systems of UAVs, multi-modal sensing and visualization, thermal analysis of builtenvironment, and smart cities analytics and design.