RoboButler: frustration-aware assistive user localisation for social robots in office environments

Abstract

In human-robot interactions (HRI), it is crucial for robots to be accepted by users and that they find robotic assistance attempts helpful rather than frustrating. Working towards this goal, we investigate the problem of frustration-aware robot behaviour planning in human-robot interaction contexts without continuous user contact or live feedback. Specifically, we address the question of how social robots can efficiently localise users and assist them with errands of various importance in office environments, while minimizing the frustration experienced by their human colleagues to enhance the overall interaction experience. Doing so, we design a frustration-aware decision-making and learning framework building on multiarmed bandit approaches and knapsack algorithms, in addition to developing a Psychology-based model of frustration tailored for HRI settings with limited user contact. Then we evaluate our approach on realistic user behaviour datasets, simulating the interactions’ robotic components in Gazebo with a TIAGo robot, and perform further scalability analysis in graph-based simulations. The experimental results demonstrate that the proposed framework achieves localisation success rates and travel times that converge towards oracle values (outperforming other structured learning benchmarks) while yielding an estimated up to 75% less frustration – indicating the proposed framework’s suitability for advancing to user studies and deployment in real-world scenarios.

More information

Identifiers

ORCID for Tan Viet Tuyen Nguyen: orcid.org/0000-0001-8000-6485

ORCID for Bing Chu: orcid.org/0000-0002-2711-8717

ORCID for Danesh Tarapore: orcid.org/0000-0002-3226-6861

Catalogue record

Export record