Andrea de Giorgio, PhD

Andrea de Giorgio, PhD

Luxembourg, Luxembourg, Luxembourg
23 k abonnés + de 500 relations

À propos

Nicola Luigi Bragazzi calls me a genius.

With Artificial Engineering, we empower…

Articles de Andrea

Activité

S’inscrire pour voir toute l’activité

Expérience

  • Graphique 5xUP Venture Builder
  • -

    Naples, Italy

  • -

  • -

    Luxembourg

  • -

    Stockholm, Sweden

  • -

  • -

  • -

  • -

  • -

  • -

    Stockholm, Stockholm County, Sweden

  • -

    Luxembourg

  • -

    Stockholm, Sweden

  • -

  • -

  • -

  • -

  • -

  • -

  • -

  • -

    Stockholm, Sweden

  • -

  • -

    Stockholm, Sweden

  • -

    Stockholm, Sweden

  • -

    Stockholm, Sweden

  • -

    Stockholm, Sweden

  • -

  • -

Formation

Licences et certifications

Publications

  • Artificial Intelligence Control in 4D Cylindrical Space for Industrial Robotic Applications

    IEEE Access

    This article argues that an efficient artificial intelligence control algorithm needs the built-in symmetries of an industrial robot manipulator to be further characterized and exploited. The product of this enhancement is a four-dimensional (4D) discrete cylindrical grid space that can directly replace complex robot models. A* is chosen for its wide use among such algorithms to study the advantages and disadvantages of steering the robot manipulator within the 4D cylindrical discrete grid. The…

    This article argues that an efficient artificial intelligence control algorithm needs the built-in symmetries of an industrial robot manipulator to be further characterized and exploited. The product of this enhancement is a four-dimensional (4D) discrete cylindrical grid space that can directly replace complex robot models. A* is chosen for its wide use among such algorithms to study the advantages and disadvantages of steering the robot manipulator within the 4D cylindrical discrete grid. The study shows that this approach makes it possible to control a robot without any specific knowledge of the robot kinematic and dynamic models at planning and execution time. In fact, the robot joint positions for each grid cell are pre-calculated and stored as knowledge, then quickly retrieved by the pathfinding algorithm when needed. The 4D cylindrical discrete space has both the advantages of the configuration space and the three-dimensional Cartesian workspace of the robot. Since path optimization is the core of any search algorithms, including A*, the 4D cylindrical grid provides for a search space that can embed further knowledge in form of cell properties, including the presence of obstacles and volumetric occupancy of the entire industrial robot body for obstacle avoidance applications. The main trade-off is between a limited capacity for pre-computed grid knowledge and the path search speed. This innovative approach encourages the use of search algorithms for industrial robotic applications, opens up to the study of other robot symmetries present in different robot models and lays a foundation for the application of dynamic obstacle avoidance algorithms.

    Autres auteurs
    • Lihui Wang
    Voir la publication
  • Procedural knowledge and function blocks for smart process planning

    Elsevier

    In the age of digital manufacturing there is a need to elicit and transfer procedural knowledge between humans and machines. Having proper knowledge is essential in decision-making. The more the knowledge, the better decisions are made. To capture experiences and turn them into knowledge is fundamental in learning processes and knowledge development. Knowledge engineering and knowledge management have been subject for research for decades and several concepts about knowledge and knowledge…

    In the age of digital manufacturing there is a need to elicit and transfer procedural knowledge between humans and machines. Having proper knowledge is essential in decision-making. The more the knowledge, the better decisions are made. To capture experiences and turn them into knowledge is fundamental in learning processes and knowledge development. Knowledge engineering and knowledge management have been subject for research for decades and several concepts about knowledge and knowledge transfer have been introduced, but a functional approach to exploit knowledge efficiently in manufacturing is still missing. In the era of Industry 4.0, humans and machines must be able to collaborate in such way that both can exploit the best abilities of each other in a manufacturing process. This paper introduces a procedural knowledge process (PKP) approach to capturing and defining unexpected events, while a process step is able to perform its required functions and transfer that information as machine-understandable knowledge about a failure mode. Function blocks (FBs), as per the IEC-61499 standard, have been proposed as a way to achieve distributed process planning in which the manufacturing process can adapt itself to runtime conditions. Continue reading on the paper.

    Autres auteurs
    Voir la publication
  • Human-machine Collaboration in Virtual Reality for Adaptive Production Engineering

    Procedia Manufacturing, Volume 11, Pages 1279-1287, Elsevier

    This paper outlines the main steps towards an open and adaptive simulation method for human-robot collaboration (HRC) in production engineering supported by virtual reality (VR). The work is based on the latest software developments in the gaming industry, in addition to the already commercially available hardware that is robust and reliable. This allows to overcome VR limitations of the industrial software provided by manufacturing machine producers and it is based on an open-source community…

    This paper outlines the main steps towards an open and adaptive simulation method for human-robot collaboration (HRC) in production engineering supported by virtual reality (VR). The work is based on the latest software developments in the gaming industry, in addition to the already commercially available hardware that is robust and reliable. This allows to overcome VR limitations of the industrial software provided by manufacturing machine producers and it is based on an open-source community programming approach and also leads to significant advantages such as interfacing with the latest developed hardware for realistic user experience in immersive VR, as well as the possibility to share adaptive algorithms. A practical implementation in Unity is provided as a functional prototype for feasibility tests. However, at the time of this paper, no controlled human-subject studies on the implementation have been noted, in fact, this is solely provided to show preliminary proof of concept. Future work will formally address the questions that are raised in this first run.

    Autres auteurs
    Voir la publication
  • Learning programs is better than learning dynamics: A programmable neural network hierarchical architecture in a multi-task scenario

    Adaptive Behavior

    Distributed and hierarchical models of control are nowadays popular in computational modeling and robotics. In the artificial neural network literature, complex behaviors can be produced by composing elementary building blocks or motor primitives, possibly organized in a layered structure. However, it is still unknown how the brain learns and encodes multiple motor primitives, and how it rapidly reassembles, sequences and switches them by exerting cognitive control. In this paper we advance a…

    Distributed and hierarchical models of control are nowadays popular in computational modeling and robotics. In the artificial neural network literature, complex behaviors can be produced by composing elementary building blocks or motor primitives, possibly organized in a layered structure. However, it is still unknown how the brain learns and encodes multiple motor primitives, and how it rapidly reassembles, sequences and switches them by exerting cognitive control. In this paper we advance a novel proposal, a hierarchical programmable neural network architecture, based on the notion of programmability and an interpreter-programmer computational scheme. In this approach, complex (and novel) behaviors can be acquired by embedding multiple modules (motor primitives) in a single, multi-purpose neural network. This is supported by recent theories of brain functioning in which skilled behaviors can be generated by combining functional different primitives embedded in “reusable” areas of “recycled” neurons. Such neuronal substrate supports flexible cognitive control, too. Modules are seen as interpreters of behaviors having controlling input parameters, or programs that encode structures of networks to be interpreted. Flexible cognitive control can be exerted by a programmer module feeding the interpreters with appropriate input parameters, without modifying connectivity. Our results in a multiple T -maze robotic scenario show how this computational framework provides a robust, scalable and flexible scheme that can be iterated at different hierarchical layers permitting to learn, encode and control multiple qualitatively different behaviors.

    Autres auteurs
    Voir la publication

Cours

  • Analog Electronics

    -

  • Applied Bioinformatics

    DD2404

  • Artificial Intelligence

    DD2380

  • Artificial Neural Networks and Other Learning Systems

    DD2432

  • Basic Dynamic Systems

    -

  • Basic Measurements

    -

  • Basic of Transmission of Heat

    -

  • Basics of informatics

    -

  • Calculus 1

    -

  • Calculus 2

    -

  • Chemistry

    -

  • Computational Photography

    DD2429

  • Computer Programming 1

    -

  • Degree Project in Computer Science, Second Cycle

    DD221X

  • Digital Electronics

    -

  • Economics and Organization of Enterprises

    -

  • Electromagnetic Fields 1

    -

  • Electronic Computers 1

    -

  • English Language

    -

  • English Language Second Level

    -

  • Experimental Designs

    FMG3904

  • Geometry and Algebra

    -

  • Image Analysis and Computer Vision

    DD2423

  • Image Based Recognition and Classification

    DD2427

  • Industrial Electrical Systems

    -

  • Integrated Digital Circuits

    -

  • Internship

    -

  • Introduction to Circuits

    -

  • Introduction to the Philosophy of Science and Research Methodology

    DA2205

  • Learning Machines

    FIK3616

  • Machine Learning

    DD2431

  • Machine Learning, Advanced Course

    DD2434

  • Mathematical Methods for Engineering

    -

  • Microwaves

    -

  • Multimodal Interaction and Interfaces

    DT2140

  • Numerical Transmission

    -

  • Operating Systems

    -

  • Optoelectronics

    -

  • Physics 1

    -

  • Physics 2

    -

  • Production Systems

    F4K5105

  • Programmable Electronic Systems

    -

  • Reinforcement Learning

    FDD3359

  • Shaped Propagation

    -

  • Speech and Speaker Recognition

    DT2118

  • Swedish A1

    LS1500

  • Swedish A2

    LS1510

  • Swedish B1/B2 for Engineers

    LS1532

  • Theory of Signals

    -

  • Thesis and final test

    -

Projets

  • COROMA

    -

    COROMA project proposes to develop a cognitively enhanced robot that can execute multiple tasks for the manufacturing of metal and composite parts. COROMA will therefore provide the flexibility that European metalworking and advanced material manufacturing companies require to compete in the rapidly evolving global market.

    The project approach makes an extensive use of modularity. Seven different modules will be developed to fully cover the project’s technical challenges and objectives…

    COROMA project proposes to develop a cognitively enhanced robot that can execute multiple tasks for the manufacturing of metal and composite parts. COROMA will therefore provide the flexibility that European metalworking and advanced material manufacturing companies require to compete in the rapidly evolving global market.

    The project approach makes an extensive use of modularity. Seven different modules will be developed to fully cover the project’s technical challenges and objectives. The modular approach will ease the integration of the project outputs in the European industry. Since manufacturing companies have different requirements some companies may only require certain capabilities from the COROMA robot; thus, they will be able to tailor their COROMA robot picking the strictly necessary modules.

    Voir le projet
  • SYMBIO-TIC

    -

    Project coordinator: prof. Lihui Wang (https://www.kth.se/profile/lihuiw/).

    The european manufacturing industry is facing challenges in terms of adaptability, flexibility and vertical integration. The SYMBIO-TIC project adresses these important issues towards a safe, dynamic, intuitive and cost effective working environment were inmersive and symbiotic collaboration between human workers and robots can take place and bring significant benefits to robot - reluctant industries, where…

    Project coordinator: prof. Lihui Wang (https://www.kth.se/profile/lihuiw/).

    The european manufacturing industry is facing challenges in terms of adaptability, flexibility and vertical integration. The SYMBIO-TIC project adresses these important issues towards a safe, dynamic, intuitive and cost effective working environment were inmersive and symbiotic collaboration between human workers and robots can take place and bring significant benefits to robot - reluctant industries, where current tasks and processes are thought too complex to be automated. The benefits that the project can bring about include lower costs, increased safety, better working conditions and higher profitability through improved adaptability, flexibility, performance and seamless integration.

    Project specific objectives are:

    Objective 1: To develop an active collision avoidance subsystem to safeguard human workers.
    Objective 2: To generate adaptive task plans appropriate to both robots and human workers.
    Objective 3: To adapt to dynamic changes with intuitive and multimodal programming.
    Objective 4: To provide human workers with in-situ assistance on what-to-do and how-to-do.
    Objective 5: To demonstrate and validate the project concept and solutions.

    Voir le projet
  • THS Operational Language Evaluation

    -

    A project-based committee with the purpose of evaluating English (instead of Swedish) as the operational language for THS, the student union at KTH, Royal Institute of Technology, and to propose the approval of this change in the Statement and By-Laws of the organization.
    The committee has done a thorough job by analyzing the language policy used at KTH, the workflow within THS and KTH itself, the opinions and ideas of (almost) all the representatives of the sub-units of THS, or rather about…

    A project-based committee with the purpose of evaluating English (instead of Swedish) as the operational language for THS, the student union at KTH, Royal Institute of Technology, and to propose the approval of this change in the Statement and By-Laws of the organization.
    The committee has done a thorough job by analyzing the language policy used at KTH, the workflow within THS and KTH itself, the opinions and ideas of (almost) all the representatives of the sub-units of THS, or rather about 20 groups operating at different levels.
    The outcome will largely affect KTH, because its best partner - when it comes to include and help more students – is the student union and all its student-members who become volunteers in service around KTH. At the time of the investigation, almost one third of the students at KTH didn’t speak Swedish at all, while a lot fewer couldn’t speak a good English. Therefore, having Swedish as the only operative language in the student union constitutes a higher barrier.

    Autres créateurs
  • Gesture-Based Password Recognition

    -

    Gesture-based password recognition is an unexplored field of research based on the influence of two main areas: human gesture recognition in Human-Computer Interaction and password management in computer science. My team for this course-based project took inspiration from new devices that will be soon commercialized and from latest publications in the field of human computer interaction to develop a sensor equipped glove for password generation through hand gestures. Our study shows that it is…

    Gesture-based password recognition is an unexplored field of research based on the influence of two main areas: human gesture recognition in Human-Computer Interaction and password management in computer science. My team for this course-based project took inspiration from new devices that will be soon commercialized and from latest publications in the field of human computer interaction to develop a sensor equipped glove for password generation through hand gestures. Our study shows that it is possible to store these passwords and to match them with an input password. The number of simultaneous changing variables within a single gesture is considerably high and the level of security of a password depends on both the accuracy and the number of sensors employed. Gesture based passwords do not provide a more secure way of password verification than alphanumeric passwords with our current setup. Although the encouraging results that my team obtained are based on a limited prototype, the professional input devices based on hand movements that have been advertised lately will bring more data to this research field.

    Autres créateurs
    Voir le projet
  • Bachelor Thesis on Learning and Neural Encoding of Multiple Behaviors

    -

    The purpose of my Bachelor thesis was to study how the concept of programmable neural circuits can make the learning of different behaviors in a single structure more efficient. For this purpose I compared two architectures, one programmable and one non-programmable, as part of a robotic scenery opportunely projected to test the possibility of learning and then exhibit multiple behaviors. More specifically, I supposed that a robot could reach one of the eight different endings of a labyrinth…

    The purpose of my Bachelor thesis was to study how the concept of programmable neural circuits can make the learning of different behaviors in a single structure more efficient. For this purpose I compared two architectures, one programmable and one non-programmable, as part of a robotic scenery opportunely projected to test the possibility of learning and then exhibit multiple behaviors. More specifically, I supposed that a robot could reach one of the eight different endings of a labyrinth, which was composed of a series of three turnings and variable dimensions. For this problem, it was fundamental that the controlling architecture could learn behaviors and not simple trajectories. In this way, I had been able to collect sufficient data to realize a thoroughly analysis.
    Artificial neural architectures, learning algorithms and functions for the simulations and the analysis of the data were entirely realized in Matlab programming language.
    My main contribute was about adapting an old framework by developing new algorithms for the simulation and the analysis of the specific problem stated in my thesis. Therefore I executed a job composed of different phases, such as problem analysis, experimental setting, code implementation, debugging, test, execution and data elaboration.
    The work is part of an exhaustive soon-to-be-published research by the ViNe Lab (http://vinelab.na.infn.it/) team in Naples, Italy.

Langues

  • Italian

    Bilingue ou langue natale

  • English

    Bilingue ou langue natale

  • Swedish

    Capacité professionnelle générale

  • Latin

    Notions

  • French

    Notions

Organisations

  • THS - Tekniska Högskolans Studentkår (KTH, Royal Institute of Technology's Student Union)

    Member of the Operational Language Evaluation Group (OLEG)

    -
  • Rotaract Club Napoli

    Club positions: President, Secretary, Past President (honorary board member), Internet Delegate, RYLA Delegate, By-Laws Committee President, Internal Action Committee President. District positions: Internet Delegate 2009/10, RYLA Delegate 2011/13

    -

Recommandations reçues

Plus d’activités de Andrea

Voir le profil complet de Andrea

  • Découvrir vos relations en commun
  • Être mis en relation
  • Contacter Andrea directement
Devenir membre pour voir le profil complet

Autres profils similaires

Ajoutez de nouvelles compétences en suivant ces cours