go back

To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions

Daniel Tanneberg, Felix Ocker, Stephan Hasler, Jörg Deigmöller, Anna Belardinelli, Chao Wang, Heiko Wersing, Bernhard Sendhoff, Michael Gienger, "To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions", Arxiv, no. arXiv:2403.12533, 2024.

Abstract

How can a robot support a group of humans in physical group activities? We present \textit{Attentive Support}, a novel interaction concept for robots to support a group of humans. It combines scene perception, dialogue acquisition, situation understanding, and behavior generation with the common-sense reasoning capabilities of Large Language Models (LLMs). In addition to following user instructions, \textit{Attentive Support} is capable to decide when and how to support the users, and when to remain silent. With a diverse set of scenarios, we show and evaluate the robot's attentive behavior, which should support and help the humans when required, while not disturbing if no help is required.



Download Bibtex file Per Mail Request

Search