Description du projet
Aider les êtres humains à comprendre le comportement des agents d’IA
Les agents d’intelligence artificielle (IA) sont à la base de différentes technologies telles que celles utilisées dans les voitures autonomes et les recommandations de traitement médical. Ils sont de plus en plus courants et peuvent être utiles à la société dans des domaines comme l’éducation, les soins de santé et les transports. Toutefois, étant donné qu’ils opèrent et interagissent avec les humains, il est important de comprendre et de sensibiliser à ce type d’intelligence. Dans ce contexte, le projet CONVEY, financé par le Conseil européen de la recherche, élaborera des méthodes adaptatives et interactives pour traduire le comportement des agents. Il s’appuiera sur les connaissances et les méthodologies de l’IA et de l’interaction homme-machine. Le projet développera également des algorithmes et des interfaces permettant aux utilisateurs de comprendre les capacités des agents.
Objectif
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.
Programme(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Thème(s)
Appel à propositions
(s’ouvre dans une nouvelle fenêtre) ERC-2022-STG
Voir d’autres projets de cet appelRégime de financement
HORIZON-ERC - HORIZON ERC GrantsInstitution d’accueil
32000 Haifa
Israël