Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Survey on Dialogue Management in Human-Robot Interaction

Merle M. Reimann, Florian A. Kunneman, Catharine Oertel, Koen V. Hindriks

TL;DR

This paper conducts a PRISMA-guided systematic review of dialogue management (DM) in human-robot interaction (HRI), focusing on spoken DM in physically embodied robots. It analyzes 68 papers across 949+504+209 initial results, classifying DM approaches into handcrafted, probabilistic, and hybrid, and documents how robot appearance, modalities, and environments shape DM design. The review reveals a persistent dominance of handcrafted DM in task-based HRI, a recent shift toward hybrid systems, and diverse evaluation practices, highlighting challenges in grounding, memory, data collection, and cross-domain generalization. The findings offer practical guidance for researchers choosing DM approaches, emphasize the need for standardized evaluation metrics and datasets, and advocate integrating multimodal grounding and environment-aware reasoning to improve robustness and user experience in social robots.

Abstract

As social robots see increasing deployment within the general public, improving the interaction with those robots is essential. Spoken language offers an intuitive interface for the human-robot interaction (HRI), with dialogue management (DM) being a key component in those interactive systems. Yet, to overcome current challenges and manage smooth, informative and engaging interaction a more structural approach to combining HRI and DM is needed. In this systematic review, we analyse the current use of DM in HRI and focus on the type of dialogue manager used, its capabilities, evaluation methods and the challenges specific to DM in HRI. We identify the challenges and current scientific frontier related to the DM approach, interaction domain, robot appearance, physical situatedness and multimodality.

A Survey on Dialogue Management in Human-Robot Interaction

TL;DR

This paper conducts a PRISMA-guided systematic review of dialogue management (DM) in human-robot interaction (HRI), focusing on spoken DM in physically embodied robots. It analyzes 68 papers across 949+504+209 initial results, classifying DM approaches into handcrafted, probabilistic, and hybrid, and documents how robot appearance, modalities, and environments shape DM design. The review reveals a persistent dominance of handcrafted DM in task-based HRI, a recent shift toward hybrid systems, and diverse evaluation practices, highlighting challenges in grounding, memory, data collection, and cross-domain generalization. The findings offer practical guidance for researchers choosing DM approaches, emphasize the need for standardized evaluation metrics and datasets, and advocate integrating multimodal grounding and environment-aware reasoning to improve robustness and user experience in social robots.

Abstract

As social robots see increasing deployment within the general public, improving the interaction with those robots is essential. Spoken language offers an intuitive interface for the human-robot interaction (HRI), with dialogue management (DM) being a key component in those interactive systems. Yet, to overcome current challenges and manage smooth, informative and engaging interaction a more structural approach to combining HRI and DM is needed. In this systematic review, we analyse the current use of DM in HRI and focus on the type of dialogue manager used, its capabilities, evaluation methods and the challenges specific to DM in HRI. We identify the challenges and current scientific frontier related to the DM approach, interaction domain, robot appearance, physical situatedness and multimodality.
Paper Structure (17 sections, 4 figures, 2 tables)

This paper contains 17 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Review
  3. Robot appearance
  4. Types of DM in HRI
  5. Handcrafted approaches
  6. Probabilistic approaches
  7. Hybrid approaches
  8. Communication capabilities in HRI
  9. Confirm
  10. Ask for confirmation
  11. Ask for repetition/rephrasing
  12. Ask clarification questions
  13. Reference resolution/spatial grounding
  14. Acquire knowledge
  15. Evaluation methods of DM in HRI
  16. ...and 2 more sections

Figures (4)

  • Figure 1: The integration of the dialogue manager into a spoken dialogue system.
  • Figure 2: Dialogue management in human-robot interaction is influenced by multiple factors that show high variability. Different robot appearances can be combined with varying modalities, interaction domains and environments. Some examples are given for each factor to illustrate it.
  • Figure 3: Appearance of the robots used in the surveyed papers.
  • Figure 4: The dialogue management approaches over the years used in the surveyed papers.