Skip to main content
Vai all'homepage della Commissione europea (si apre in una nuova finestra)
italiano it
CORDIS - Risultati della ricerca dell’UE
CORDIS

Intelligence-Oriented Verification&Controller Synthesis

Descrizione del progetto

Affidabilità per i sistemi intelligenti

Dalle automobili a guida autonoma ai dispositivi medici robotizzati, il software sta prendendo decisioni sempre più decisive e di carattere vitale; ciononostante, man mano che i sistemi diventano più elaborati, l’apprendimento automatico introduce nuove sfide, in quanto i modelli sono potenti, ma difficili da verificare e spiegare, ovvero «a scatola nera». In questo contesto, il progetto InOVationCS, finanziato dal CER, combinerà le innovazioni in materia di verifica con approcci basati sull’apprendimento con l’obiettivo di fornire controller scalabili, affidabili, corretti sin dalla progettazione e sufficientemente trasparenti da essere considerati sicuri. Il risultato offerto da InOVationCS potrebbe rappresentare una pietra miliare verso la realizzazione di sistemi intelligenti basati sui dati, sicuri da applicare nel mondo reale.

Obiettivo

Software making decisions or controlling cyber-physical systems is ubiquitous, hence its correctness is of paramount importance. While the increasing complexity makes manual implementation extremely error-prone, verification can provide formal guarantees on correctness. Verification of hardware and software has seen many successes and industrialization, making systems safe and reliable and their development more efficient. Controller synthesis goes one step further and avoids the manual implementation, providing a correct-by-construction controller directly. Despite considerable advances, scalable solutions remain elusive here.

Artificial intelligence and machine learning (AI/ML) provide scalable solutions to decision making, but at the cost of their reliability, making their verification even more pressing. Besides, the use of AI/ML gives rise to fundamentally new challeges since models, properties and controllers are now often based on data rather than design. Due to their “black-box” nature, the resulting systems are (i) even harder to verify, and (ii) not explainable enough to be responsibly deployed.

The PI has been pioneering the use of learning in verification to bring together the best of both worlds, scalability and reliability. The main objective of InOVation&CS is to utilize the power of learning in verification and controller-synthesis to overcome both the traditional scalability challenges as well as the recent, data-driven ones. The key to bringing the two closer than ever is a paradigm shift towards explainability and utilizing structure stemming from the presence of intelligence (human or artificial) in the definition, analysis and solution of real problems, thus providing more information to the learning parts. InOVation&CS shall provide new, more applicable and more scalable methodology for producing guaranteed reliable controllers.

Keywords: verification, model checking, Markov decision processes, stochastic games, temporal logics

Campo scientifico (EuroSciVoc)

Parole chiave

Programma(i)

Argomento(i)

Meccanismo di finanziamento

HORIZON-ERC - HORIZON ERC Grants

Vedi tutti i progetti finanziati nell’ambito di questo schema di finanziamento

Invito a presentare proposte

(si apre in una nuova finestra) ERC-2024-COG

Vedi tutti i progetti finanziati nell’ambito del bando

Istituzione ospitante

Masarykova univerzita
Contributo netto dell'UE
€ 1 995 000,00
Indirizzo
Zerotinovo namesti 9
601 77 Brno
Cechia
Regione
Česko Jihovýchod Jihomoravský kraj
Tipo di attività
Higher or Secondary Education Establishments
Collegamenti
Costo totale
€ 1 995 000,00

Beneficiari (1)