Embedded Files
RePAIR
RePAIR
RePAIR project – an acronym for Reconstructing the Past: Artificial Intelligence and Robotics meet Cultural Heritage. State-of-the-art technology will, for the first time, be employed in the physical reconstruction of archaeological artefacts, which are mostly fragmentary and difficult to reassemble.
The main goal of the RePAIR project is to develop innovative technology to virtually eliminate one of the most laborious and frustrating steps in archaeological research, namely the physical reconstruction of shattered works of art. In fact, countless vases, amphorae, frescoes and other ancient artifacts, around the world, have not survived intact and have been extracted from excavation sites as large collections of fragments, many of which are damaged, worn out or entirely missing.
Funding Programme: H2020 - FET Open
Total Fund: 3.5M €
Role: Coordinator
Dates: 09/2021 - 11/2025
Easy Walk
Easy Walk
In the last decade, several studies have proposed solutions to prototype a smart walker. Several approaches may vary from user-guided walkers with an intelligent braking system to autonomous platforms featured by people detection modules and remote teleoperations. However, despite the technological and scientific efforts, to date the translational impact of the current smart walkers is still limited. We identify three main reasons for that: i) current approaches lack reliability and robustness—especially in daily life operations and in natural scenarios; ii) the coupling between humans and machines is underestimated. The user is guided or s/he autonomously drives the walker; in most cases the integration of the intentions of the two actors (user and machine) is minimal; iii) the cost of the platform is often prohibitive and this definitely jeopardizes the vast adoption of the technology, and especially, it prevents a continuous personal usage at home. As a direct consequence, users—and in particular older adults—do not trust the walker, and thus, they do not use it. In the EasyWalk project we hypothesize that such a trust can be achieved by providing a walker that is low-cost, easy-to-use, reliable and able to infer, to integrate and to contextualize the user's intentions according to the environment information.
Funding Programme: PRIN - PNRR
Total Fund: 260K €
Role: Partner
Dates: 11/2023 - 02/2026
Past Projects
Past Projects
MEMEX
MEMEX
MEMories and EXperiences for inclusive digital storytelling
MEMEX promotes Artificial Intelligence (AI) as assistive technology, helping humans through the use of machine learning, computer vision and augmented reality.
Funding Programme: H2020 - RIA
Total Fund:
Role: Third party
Dates: 12/2019 - 12/2022
AIDA
AIDA
ARTIFICIAL INTELLIGENCE ASSISTED PERFORMANCE AND ANOMALY DETECTION AND DIAGNOSTIC (AIDA)
The objective of the work is to define, design and validate a machine-learning-based method for the detection of Radio Frequency (RF) anomalies and the identification of the associated root causes, with the purpose of accelerating the RF equipment performance evaluation activity, supporting the domain experts in their analysis throughout the whole development, from design to qualification and assembly, integration and Test (AIT).
Funding Programme: ESA TENDER
Total Fund: 400k €
Role: Partner
Dates: 2020 - 2021
AI4EU
AI4EU
A European AI On Demand Platform and Ecosystem
Artificial Intelligence is a disruptive technology of our times with expected impacts rivalling those of electricity or printing. Resources for innovation are currently dominated by giant tech companies in North America and China. To ensure European independence and leadership, we must invest wisely by bundling, connecting and opening our AI resources. AI4EU will efficiently build a comprehensive European AI-ondemand platform to lower barriers to innovation, to boost technology transfer and catalyse the growth of start-ups and SMEs in all sectors through Open calls and other actions.
Funding Programme: H2020-ICT-2018-2020
Total Fund: 20.6M €
Role: Partner
Dates: 2019 - 2021
Hume-Nash Machines
Hume-Nash Machines
Hume-Nash Machines: Context-Aware Models of Learning and Recognition
Contrary to standard classification algorithms, which are based on the idea of assigning similar objects to the same class labels, thereby neglecting category-level similarities, our model will conform to the more general “Hume’s similarity principle” which prescribes that similar objects should be assigned to similar categories.
Funding Programme: Samsung - Global Research Outreach 2015
Total Fund: 160K €
Role: Coordinator
Dates: 2015 - 2017
REXlearn
REXlearn
RexLEARN: Reliable and Explainable Adversarial Machine Learning
Machine-learning technologies have become pervasive, and even able to outperform humans on specific tasks. However, it has been shown that they suffer from hallucinations known as adversarial examples, i.e., imperceptible, adversarial perturbations to images, text and audio that fool these systems into perceiving things that are not there. This has severely questioned their suitability for mission-critical applications, including self-driving cars and autonomous vehicles. The defense strategies proposed to overcome this issue have been shown to be ineffective against more sophisticated attacks carefully crafted to bypass them, highlighting the challenging nature of this problem. In this project, we formulate three main challenges that demand for novel learning paradigms, able to take reliable and explainable decisions, to assess and mitigate the security risks associated to such potential misuses of machine learning. This project will pave the way towards the design of reliable and explainable machines that are also useful beyond adversarial settings. We will indeed develop tools and prototypes that can face the challenges posed not only by cybersecurity applications with a clear adversarial nature, but also by recent computer-vision and deep-learning technologies.
Funding Programme: PRIN 2017
Role: Partner
Dates: 2019 - 2023
SIMBAD
SIMBAD
SIMBAD: (Beyond Features) Similarity-Based Pattern Analysis and Recognition
Traditional pattern recognition techniques are centered around the notion of “feature”. According to this view, the objects to be classified are represented in terms of properties that are intrinsic to the object itself. Hence, a typical pattern recognition system makes its decisions by simply looking at one or more feature vectors provided as input. The strength of this approach is that it can leverage a wide range of mathematical tools ranging from statistics, to geometry, to optimization. However, in many real-world applications a feasible feature-based description of objects might be difficult to obtain or inefficient for learning purposes. In these cases, it is often possible to obtain a measure of the (dis)similarity of the objects to be classified, and in some applications the use of dissimilarities (rather than features) makes the problem more viable.
Funding Programme: FP7 - FET ICT
Total Fund: 1.6M €
Role: Coordinator
Dates: 2008 - 2011
Page updated
Google Sites
Report abuse