Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Social Group Human-Robot Interaction: A Scoping Review of Computational Challenges

Massimiliano Nigro, Emmanuel Akinrintoyo, Nicole Salomons, Micol Spitale

TL;DR

This scoping review addresses the computational challenges of social group HRI by analyzing 44 representative papers from 2015–2024, focusing on perception and behaviour generation. It maps how input factors like group size, robot capabilities, and environment shape challenges in detecting groups and engagement, as well as generating appropriate conversational and approaching behaviours. The study reveals a predominance of rule-based methods, with limited use of reinforcement learning, and highlights gaps such as subgroup detection, interpersonal relationship modeling, and personalization based on group entitativity. By outlining these gaps and offering concrete recommendations, the paper provides a roadmap for advancing robust, scalable group HRI in real-world settings.

Abstract

Group interactions are a natural part of our daily life, and as robots become more integrated into society, they must be able to socially interact with multiple people at the same time. However, group human-robot interaction (HRI) poses unique computational challenges often overlooked in the current HRI literature. We conducted a scoping review including 44 group HRI papers from the last decade (2015-2024). From these papers, we extracted variables related to perception and behaviour generation challenges, as well as factors related to the environment, group, and robot capabilities that influence these challenges. Our findings show that key computational challenges in perception included detection of groups, engagement, and conversation information, while challenges in behaviour generation involved developing approaching and conversational behaviours. We also identified research gaps, such as improving detection of subgroups and interpersonal relationships, and recommended future work in group HRI to help researchers address these computational challenges

Social Group Human-Robot Interaction: A Scoping Review of Computational Challenges

TL;DR

This scoping review addresses the computational challenges of social group HRI by analyzing 44 representative papers from 2015–2024, focusing on perception and behaviour generation. It maps how input factors like group size, robot capabilities, and environment shape challenges in detecting groups and engagement, as well as generating appropriate conversational and approaching behaviours. The study reveals a predominance of rule-based methods, with limited use of reinforcement learning, and highlights gaps such as subgroup detection, interpersonal relationship modeling, and personalization based on group entitativity. By outlining these gaps and offering concrete recommendations, the paper provides a roadmap for advancing robust, scalable group HRI in real-world settings.

Abstract

Group interactions are a natural part of our daily life, and as robots become more integrated into society, they must be able to socially interact with multiple people at the same time. However, group human-robot interaction (HRI) poses unique computational challenges often overlooked in the current HRI literature. We conducted a scoping review including 44 group HRI papers from the last decade (2015-2024). From these papers, we extracted variables related to perception and behaviour generation challenges, as well as factors related to the environment, group, and robot capabilities that influence these challenges. Our findings show that key computational challenges in perception included detection of groups, engagement, and conversation information, while challenges in behaviour generation involved developing approaching and conversational behaviours. We also identified research gaps, such as improving detection of subgroups and interpersonal relationships, and recommended future work in group HRI to help researchers address these computational challenges

Paper Structure

This paper contains 22 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Previous Reviews on Group HRI
  4. Perception
  5. Behaviour Generation
  6. Methodology
  7. Findings
  8. Input
  9. Group
  10. Robot
  11. Environment
  12. Perception
  13. Group and F-Formation Detection
  14. Engagement Detection
  15. Conversational Information Detection
  16. ...and 7 more sections

Figures (3)

  • Figure 1: Extended IPO Framework illustrating perception and behaviour generation as part of group interaction processes.In bold and with asterisks the variables treated in this review. Note that this work does not take into account the output aspects of this framework as in sebo2020robots.
  • Figure 2: Group size for studies involving a physical robot (robot excluded)
  • Figure 3: Overview of key computational challenges in perception and behaviour generation and their interrelationships