Projects

The creation-diffusion of fake multimedia content, whether entirely computer-synthesized or obtained by manipulating original content, can be considered a danger to many aspects of our society. The overall phenomenon has reached unprecedented levels, thanks to the availability of artificial intelligence tools dedicated to generating fake content almost indistinguishable from real ones in a relatively simple way. Fighting so-called deepfakes, videos, images and audio clips, generated with deep learning techniques, requires the development of appropriate countermeasures. The project aims to develop theoretical and practical tools to detect fake or counterfeited content, trace back to its origin, and limit its diffusion, through passive analysis techniques operating when the content is used or diffused, and active protection methods to be adopted at the time of content creation, to facilitate subsequent authentication.

Partners: Scuola IMT Alti Studi Lucca, Università degli Studi di Cagliari, Sapienza Università di Roma, CNIT, ENI

SERICS (PE00000014) under the MUR National Recovery and Resilience Plan funded by the European Union - NextGenerationEU 

Il progetto ha l’ambizione di studiare e realizzare applicazioni cooperative, su piattaforma C-ITS ETSI che riescano a ridurre le situazioni di rischio durante la mobilità.

La piattaforma offrirà, attraverso tecnologie di intelligenza artificiale, data analytics, video & audio processing per l’object detection, l’edge computing, il routing intelligente degli eventi:

1- Strumenti real & near-real-time per il monitoraggio dinamico e predittivo della mobilità e degli elementi infrastrutturali ad essa collegati sulla base dei dati provenienti dal territorio, inclusi quelli della segnaletica statica digitalizzata, utilizzando flussi GNSS e di sistemi video eterogenei (fonti video tradizionali e sensori mmwave).

2- Strumenti di real & near-real-time detection e notifica di situazioni quali guida pericolosa, comportamento anomalo del veicolo sulla base traiettoria, insieme con la gestione di eventi quali  incidenti, infrastrutture non disponibili causa eventi naturali.

3- Strumenti di simulazione in grado di fornire supporto alla pianificazione di interventi finalizzati a preservare e migliorare aspetti quantitativi e qualitativi della mobilità e per la programmazione e gestione del trasporto multimodale integrato.

Soggetto CAPOFILA: VODAFONE AUTOMOTIVE ITALIA SPA

Soggetti co-proponenti: SAPIENZA UNIVERSITA' DI ROMA, POLITECNICO DI MILANO, SMART-I SRL

Fondo per la Crescita Sostenibile - Accordi per l'innovazione nel settore automotive - D.M. 31 dicembre 2021 e D.D. 10 ottobre 2022, Ministero delle Imprese e del Made in Italy (MIMIT)

The project aims at the design and prototyping of a visual detection system of the varroa mite, which exploits energy-aware resource management and application algorithms based on the cloud-to-IoT continuum paradigm, tailored and extended to run on cooperating energy-constrained devices. This innovative automatic detection system of the level of infestation uses visual deep learning algorithms that dramatically reduce the state-of-the-art detection time of the varroa infestation level.

Link to Project Page

Development of a Sandbox for security and robustness assessment of DL models that enables :

• Validation by calculating the robustness of the model through security level assessment (DL network tested with increasing levels of perturbation of the adversarial attacks)

• Investigation of model vulnerabilities

• Mitigation through measures to be taken to harden the analyzed model

PNRM Project funded by NAVARM, partner Telsy SpA

The goal of Artemisia is to analyze visitors interest in museums and archaeological areas. Through innovative sensors able to capture position and orientation we can reconstruct visitors trajectories, and through artificial intelligence we can investigate  the most crowded areas of a museum and visitors behaviour.

Link to Project Page

Il progetto prevede la realizzazione di un ambiente integrato denominato Social Museum and Smart Tourism con funzionalità specialistiche finalizzate ad offrire al visitatore di una città o territorio d’arte servizi di smart community innovativi rispetto allo scenario attuale.

The goal of SecondHands was to design a robot that can offer help to a maintenance technician in a pro-active manner. We seen this robot as a second pair of hands that can assist the technician when he/she was in need of help.

Link to Project Page

TRADR is an integrated european research project funded by the EU FP7 Programme, ICT: Cognitive systems, interaction, robotics (Project Nr. 609763) in the area of robot-assisted disaster response (disaster robotics; robot search and rescue).

Using a proven-in-practice user-centric design methodology, TRADR develops novel science and technology for human-robot teams to assist in urban search and rescue disaster response efforts, which stretch over multiple sorties in missions that may take several days or weeks.

Link to Project Page

While today’s robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize. This is a severe limitation: any robot will inevitably face novel situations in unconstrained settings, and thus will always have knowledge gaps. This calls for robots able to learn continuously about objects by themselves.

Link to Project Page

Cognitive Systems and Robotics Working together to assess real-life urban disaster sites NIFTi investigates how natural behavior in human-robot cooperation can arise. The project operationalizes natural cooperation as balancing operational and cooperation demands in a cognitive architecture (CA), to minimize human cognitive task load and optimize joint workflow.

Link 1 to Project Page

Link 2 to Project Page

The goal of ALOOF is to enable robots to tap into the ever-growing amount of knowledge available on the Web, by learning from there about the meaning of previously unseen objects, expressed in a form that makes them applicable when acting in situated environments. By searching the Web, robots will be able to learn about new objects, their specific properties, where they might be stored and so forth. 

Link to Project Page

The goal of the ‘View Finder’ project is to develop innovative algorithms for control and navigation of mobile robots, particularly autonomous control systems.

Implementation timeframe: 12/2006 – 11/2009

Link to Project Page

Lo scopo principale del progetto è quello di sviluppare un sistema adattivo per la valutazione automatica delle condizioni di suscettibilità e l’identificazione di aree a rischio incendio, come l’FWI, fornito dall’European Forest Fire Information System, da altri studi come SIGRI, e da altre fonti. L’obiettivo della ricerca è di fornire agli addetti ai lavori un modello dinamico ed adattivo che integri clima, condizioni meteorologiche, condizioni del terreno e orografia, valutando il grado di vulnerabilità da incendi di aree specifiche. 

Link to Project Page