Print Email Facebook Twitter Feasible Action-Space Reduction as a Metric of Causal Responsibility in Multi-Agent Spatial Interactions Title Feasible Action-Space Reduction as a Metric of Causal Responsibility in Multi-Agent Spatial Interactions Author George, A. (TU Delft Human-Robot Interaction) Cavalcante Siebert, L. (TU Delft Interactive Intelligence) Abbink, D.A. (TU Delft Human-Robot Interaction) Zgonnikov, A. (TU Delft Human-Robot Interaction) Contributor Gal, Kobi (editor) Nowe, Ann (editor) Nalepa, Grzegorz J. (editor) Fairstein, Roy (editor) Radulescu, Roxana (editor) Date 2023 Abstract Modelling causal responsibility in multi-agent spatial interactions is crucial for safety and efficiency of interactions of humans with autonomous agents. However, current formal metrics and models of responsibility either lack grounding in ethical and philosophical concepts of responsibility, or cannot be applied to spatial interactions. In this work we propose a metric of causal responsibility which is tailored to multi-agent spatial interactions, for instance interactions in traffic. In such interactions, a given agent can, by reducing another agent's feasible action space, influence the latter. Therefore, we propose feasible action space reduction (FeAR) as a metric of causal responsibility among agents. Specifically, we look at ex-post causal responsibility for simultaneous actions. We propose the use of Moves de Rigueur (MdR) - a consistent set of prescribed actions for agents - to model the effect of norms on responsibility allocation. We apply the metric in a grid world simulation for spatial interactions and show how the actions, contexts, and norms affect the causal responsibility ascribed to agents. Finally, we demonstrate the application of this metric in complex multi-agent interactions. We argue that the FeAR metric is a step towards an interdisciplinary framework for quantifying responsibility that is needed to ensure safety and meaningful human control in human-AI systems. To reference this document use: http://resolver.tudelft.nl/uuid:b45eabb1-c894-448f-b698-17b0da35b89b DOI https://doi.org/10.3233/FAIA230349 Publisher IOS Press ISBN 978-1-64368-436-9 Source ECAI 2023 - 26th European Conference on Artificial Intelligence, including 12th Conference on Prestigious Applications of Intelligent Systems, PAIS 2023 - Proceedings Event 26th European Conference on Artificial Intelligence, ECAI 2023, 2023-09-30 → 2023-10-04, Krakow, Poland Series Frontiers in Artificial Intelligence and Applications, 0922-6389, 372 Part of collection Institutional Repository Document type conference paper Rights © 2023 A. George, L. Cavalcante Siebert, D.A. Abbink, A. Zgonnikov Files PDF FAIA_372_FAIA230349.pdf 659.72 KB Close viewer /islandora/object/uuid:b45eabb1-c894-448f-b698-17b0da35b89b/datastream/OBJ/view