Descrizione del progetto
Aiutare gli esseri umani a comprendere il comportamento degli agenti di intelligenza artificiale
Gli agenti di IA sono alla base di varie tecnologie, quali quelle utilizzate nelle auto a guida autonoma e per le raccomandazioni terapeutiche. Sono sempre più diffusi e possono apportare benefici alla società in settori come l’istruzione, l’assistenza sanitaria e i trasporti. Tuttavia, dal momento che operano e interagiscono con gli esseri umani, è importante aumentare la consapevolezza e la comprensione di questo tipo di intelligenza. In questo contesto, il progetto CONVEY, finanziato dal Consiglio europeo della ricerca, svilupperà metodi adattivi e interattivi per trasmettere il comportamento degli agenti e si avvarrà a tal fine delle informazioni e delle metodologie dell’IA e dell’interazione uomo-computer. Il progetto svilupperà inoltre algoritmi e interfacce per consentire agli utenti di esplorare le capacità di questi agenti.
Obiettivo
From self-driving cars to agents recommending medical treatment, Artificial Intelligence (AI) agents are becoming increasingly prevalent. These agents have the potential to benefit society in areas such as transportation, healthcare and education. Importantly, they do not operate in a vacuumpeople interact with agents in a wide range of settings. To effectively interact with agents, people need to be able to anticipate and understand their behavior. For example, a driver of an autonomous vehicle will need to anticipate situations in which the carfails and hands over control, while a clinician will need to understand the treatment regime recommended by an agent to determine whether it aligns with the patients preferences.
Explainable AI methods aim to support users by making the behavior of AI systems more transparent. However, the state-of-the-art in explainable AI is lacking in several key aspects. First, the majority of existing methods focus on providing local explanations to one-shot decisions of machine learning models. They are not adequate for conveying the behavior of agents that act over an extended time duration in large state spaces. Second, most existing methods do not consider the context in which explanations are deployed, including to the specific needs and characteristics of users. Finally, most methods are not interactive, limiting users ability to gain a thorough understanding of the agents.
The overarching objective of this proposal is to develop adaptive and interactive methods for conveying the behavior of agents and multi-agent teams operating in sequential decision-making settings. To tackle this challenge, the proposed research will draw on insights and methodologies from AI and human-computer interaction. It will develop algorithms that determine what information about agents behavior to share with users, tailored to users needs and characteristics, and interfaces that allow users to proactively explore agents capabilities.
Parole chiave
Programma(i)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Argomento(i)
Invito a presentare proposte
(si apre in una nuova finestra) ERC-2022-STG
Vedi altri progetti per questo bandoMeccanismo di finanziamento
HORIZON-ERC -Istituzione ospitante
32000 Haifa
Israele