Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Egocentric Robots in a Human-Centric World? Exploring Group-Robot-Interaction in Public Spaces

Ana Müller, Anja Richert

TL;DR

This paper addresses the gap in understanding how social norms operate in group-robot-interactions (GRI) in public spaces, where robots often fail to interpret social dynamics. The authors conduct an in-the-wild field study with a Furhat robot at a university cafeteria, using ego-network analysis (ENA) to assess perceived extraversion (ext.) across egos, robot alteri, and human alteri in dyadic and triadic groups (N=40; 24 dyadic, 16 GRI). They measured ext. via a 12-item Big Five Inventory scale and evaluated self, robot, and alteri ext., reporting reliability metrics and comparing interaction conditions. The results reveal no significant differences in ego self-extraversion or robot extraversion between dyadic and GRI, with alteri ext varying and GRIs showing slightly lower system satisfaction, suggesting moderate ext. across the interaction types. The study demonstrates the feasibility of ENA for HRI in-the-wild and highlights the need for adaptive turn-taking and dialogue design, potentially leveraging generative AI to improve group interactions and broader real-world deployment.

Abstract

The deployment of social robots in real-world scenarios is increasing, supporting humans in various contexts. However, they still struggle to grasp social dynamics, especially in public spaces, sometimes resulting in violations of social norms, such as interrupting human conversations. This behavior, originating from a limited processing of social norms, might be perceived as robot-centered. Understanding social dynamics, particularly in group-robot-interactions (GRI), underscores the need for further research and development in human-robot-interaction (HRI). Enhancing the interaction abilities of social robots, especially in GRIs, can improve their effectiveness in real-world applications on a micro-level, as group interactions lead to increased motivation and comfort. In this study, we assessed the influence of the interaction condition (dyadic vs. triadic) on the perceived extraversion (ext.) of social robots in public spaces. The research involved 40 HRIs, including 24 dyadic (i.e., one human and one robot) interactions and 16 triadic interactions, which involve at least three entities, including the robot.

Egocentric Robots in a Human-Centric World? Exploring Group-Robot-Interaction in Public Spaces

TL;DR

This paper addresses the gap in understanding how social norms operate in group-robot-interactions (GRI) in public spaces, where robots often fail to interpret social dynamics. The authors conduct an in-the-wild field study with a Furhat robot at a university cafeteria, using ego-network analysis (ENA) to assess perceived extraversion (ext.) across egos, robot alteri, and human alteri in dyadic and triadic groups (N=40; 24 dyadic, 16 GRI). They measured ext. via a 12-item Big Five Inventory scale and evaluated self, robot, and alteri ext., reporting reliability metrics and comparing interaction conditions. The results reveal no significant differences in ego self-extraversion or robot extraversion between dyadic and GRI, with alteri ext varying and GRIs showing slightly lower system satisfaction, suggesting moderate ext. across the interaction types. The study demonstrates the feasibility of ENA for HRI in-the-wild and highlights the need for adaptive turn-taking and dialogue design, potentially leveraging generative AI to improve group interactions and broader real-world deployment.

Abstract

The deployment of social robots in real-world scenarios is increasing, supporting humans in various contexts. However, they still struggle to grasp social dynamics, especially in public spaces, sometimes resulting in violations of social norms, such as interrupting human conversations. This behavior, originating from a limited processing of social norms, might be perceived as robot-centered. Understanding social dynamics, particularly in group-robot-interactions (GRI), underscores the need for further research and development in human-robot-interaction (HRI). Enhancing the interaction abilities of social robots, especially in GRIs, can improve their effectiveness in real-world applications on a micro-level, as group interactions lead to increased motivation and comfort. In this study, we assessed the influence of the interaction condition (dyadic vs. triadic) on the perceived extraversion (ext.) of social robots in public spaces. The research involved 40 HRIs, including 24 dyadic (i.e., one human and one robot) interactions and 16 triadic interactions, which involve at least three entities, including the robot.
Paper Structure (4 sections, 2 figures, 2 tables)

This paper contains 4 sections, 2 figures, 2 tables.

Table of Contents

  1. Motivation and Related Work
  2. Materials and Methods
  3. Results and Discussion
  4. Conclusion

Figures (2)

  • Figure 1: Interaction with Furhat at TH Köln. Showcasing research via ENA, involving one participant as the ego (survey respondent) and others, including the robot, as alteri. The interaction is described from the ego's viewpoint. The individuals depicted are not actual study participants to maintain privacy.
  • Figure 2: Research methodology using ENA to assess GRIs. Top part: interaction conditions. Bottom part: Questionnaire categories relevant to all interaction conditions (purple) and those specific to GRI (orange). The questionnaire transcript is available for download by scanning the QR code.