Skip to main content
European Commission logo
TRIMIS

Conveying Agent Behavior to People: A User-Centered Approach to Explainable AI

PROJECTS
Funding
European
European Union
Duration
-
Geo-spatial type
Infrastructure Node
Total project cost
€1 470 250
EU Contribution
€1 470 250
Project Acronym
CONVEY
STRIA Roadmaps
Connected and automated transport (CAT)
Transport mode
Road icon
Transport policies
Deployment planning/Financing/Market roll-out,
Digitalisation
Transport sectors
Passenger transport,
Freight transport

Overview

Call for proposal
ERC-2022-STG
Link to CORDIS
Background & Policy context

Artificial intelligence (AI) agents are behind diverse technologies like those used in self-driving cars and medical treatment recommendations. They are becoming increasingly prevalent and can benefit society in areas like education, healthcare and transportation. However, since they operate and interact with humans, it’s important to raise awareness and understanding of this type of intelligence. In this context, the European Research Council-funded CONVEY project will develop adaptive and interactive methods for conveying the behaviour of agents. It will draw on insights and methodologies from AI and human-computer interaction. The project will also develop algorithms and interfaces for users to explore agent capabilities.

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 vacuum—people 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 patient’s 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.

Objectives

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.

Funding

Specific funding programme
HORIZON.1.1 - European Research Council (ERC)
Other Programme
ERC-2022-STG ERC STARTING GRANTS

Partners

Lead Organisation
EU Contribution
€1 470 250

Technologies

Technology Theme
Connected and automated vehicles
Technology
Autonomous vehicle technologies
Development phase
Research/Invention

Contribute! Submit your project

Do you wish to submit a project or a programme? Head over to the Contribute page, login and follow the process!

Submit