Projektbeschreibung
Menschen helfen, das Verhalten von KI-Agenten zu verstehen
Agenten der künstlichen Intelligenz (KI) stehen hinter verschiedenen Technologien, die beispielsweise in selbstfahrenden Autos oder bei medizinischen Behandlungsempfehlungen zum Einsatz kommen. Sie sind immer häufiger anzutreffen und können der Gesellschaft in Bereichen wie Bildung, Gesundheitswesen und Verkehr zugute kommen. Da sie jedoch mit Menschen arbeiten und interagieren, ist es wichtig, das Bewusstsein und das Verständnis für diese Art von Intelligenz zu schärfen. In diesem Zusammenhang wird das vom Europäischen Forschungsrat finanzierte Projekt CONVEY adaptive und interaktive Methoden zur Vermittlung des Verhaltens von Agenten entwickeln. Dabei werden Erkenntnisse und Methoden aus den Bereichen KI und Mensch-Computer-Interaktion genutzt. Im Rahmen des Projekts werden auch Algorithmen und Schnittstellen entwickelt, mit denen die Nutzenden die Fähigkeiten der Agenten erkunden können.
Ziel
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.
Schlüsselbegriffe
Programm/Programme
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Thema/Themen
Aufforderung zur Vorschlagseinreichung
(öffnet in neuem Fenster) ERC-2022-STG
Andere Projekte für diesen Aufruf anzeigenFinanzierungsplan
HORIZON-ERC -Gastgebende Einrichtung
32000 Haifa
Israel