Influence-Based Reward Modulation for Implicit Communication in Human–Robot Interaction
ACM Transactions on Human-Robot Interaction · 31.05.2026 · 15 (3) · 1-33
DOI: 10.1145/3800955 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Human-Robot Interaction, online erschienen am 18.04.2026. Verfasst von Haoyang Jiang und 2 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben.
Abstract (Originalsprache)
Communication is essential for successful interaction. In Human–Robot Interaction (HRI), implicit communication holds the potential to enhance robots’ understanding of human needs, emotions and intentions. This article introduces a method to foster implicit communication in HRI without explicitly modelling human intentions or relying on pre-existing knowledge. Leveraging Transfer Entropy, we modulate influence between agents in social interactions in scenarios involving either collaboration or competition. By integrating influence into agents’ rewards within a partially observable Markov decision process, we demonstrate that boosting influence enhances collaboration and interaction, while resisting influence promotes social independence and diminishes performance in certain scenarios. Our findings are validated through simulations and real-world experiments with human participants in social navigation and autonomous driving settings.
Zitieren
APA
Jiang, H., Croft, E., & Burke, M. (2026). Influence-Based Reward Modulation for Implicit Communication in Human–Robot Interaction. ACM Transactions on Human-Robot Interaction, 15(3), 1-33. https://doi.org/10.1145/3800955
Vancouver
Jiang H, Croft E, Burke M. Influence-Based Reward Modulation for Implicit Communication in Human–Robot Interaction. ACM Transactions on Human-Robot Interaction. 2026;15(3):1-33. doi:10.1145/3800955
BibTeX
@article{Jiang2026,
author = {Jiang, Haoyang and Croft, Elizabeth and Burke, Michael},
title = {Influence-Based Reward Modulation for Implicit Communication in Human–Robot Interaction},
journal = {ACM Transactions on Human-Robot Interaction},
year = {2026},
volume = {15},
number = {3},
pages = {1--33},
doi = {10.1145/3800955}
}
EUVIMED