Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

What Can You Say to a Robot? Capability Communication Leads to More Natural Conversations

Merle M. Reimann, Koen V. Hindriks, Florian A. Kunneman, Catharine Oertel, Gabriel Skantze, Iolanda Leite

TL;DR

This work addresses how a robot can convey its capabilities to users to improve transparency and interaction quality. It compares Baseline, Reactive, and Proactive capability communication strategies in a three-interaction restaurant setting with 120 participants, using questionnaires, dialogue logs, and video analysis. Results show that Proactive capability communication increases enjoyment and willingness to reuse and fosters a more conversational user style, while Reactive communication is hampered by speech recognition issues; Baseline provides minimal transparency. The study demonstrates the practicality of proactive transparency in HRI and suggests tailoring capability communication to user experience to enhance long-term human-robot collaboration.

Abstract

When encountering a robot in the wild, it is not inherently clear to human users what the robot's capabilities are. When encountering misunderstandings or problems in spoken interaction, robots often just apologize and move on, without additional effort to make sure the user understands what happened. We set out to compare the effect of two speech based capability communication strategies (proactive, reactive) to a robot without such a strategy, in regard to the user's rating of and their behavior during the interaction. For this, we conducted an in-person user study with 120 participants who had three speech-based interactions with a social robot in a restaurant setting. Our results suggest that users preferred the robot communicating its capabilities proactively and adjusted their behavior in those interactions, using a more conversational interaction style while also enjoying the interaction more.

What Can You Say to a Robot? Capability Communication Leads to More Natural Conversations

TL;DR

This work addresses how a robot can convey its capabilities to users to improve transparency and interaction quality. It compares Baseline, Reactive, and Proactive capability communication strategies in a three-interaction restaurant setting with 120 participants, using questionnaires, dialogue logs, and video analysis. Results show that Proactive capability communication increases enjoyment and willingness to reuse and fosters a more conversational user style, while Reactive communication is hampered by speech recognition issues; Baseline provides minimal transparency. The study demonstrates the practicality of proactive transparency in HRI and suggests tailoring capability communication to user experience to enhance long-term human-robot collaboration.

Abstract

When encountering a robot in the wild, it is not inherently clear to human users what the robot's capabilities are. When encountering misunderstandings or problems in spoken interaction, robots often just apologize and move on, without additional effort to make sure the user understands what happened. We set out to compare the effect of two speech based capability communication strategies (proactive, reactive) to a robot without such a strategy, in regard to the user's rating of and their behavior during the interaction. For this, we conducted an in-person user study with 120 participants who had three speech-based interactions with a social robot in a restaurant setting. Our results suggest that users preferred the robot communicating its capabilities proactively and adjusted their behavior in those interactions, using a more conversational interaction style while also enjoying the interaction more.

Paper Structure

This paper contains 36 sections, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Spoken human-robot interaction
  4. Transparency in human-robot interaction
  5. The robots' capability communication strategies
  6. Baseline
  7. Reactive
  8. Proactive
  9. Dialogue examples
  10. Baseline condition
  11. Reactive condition
  12. Procative condition
  13. Hypotheses
  14. Methods
  15. Participants
  16. ...and 21 more sections

Figures (4)

  • Figure 1: The setup of the experiment. ARI greets the participant and then leads them to the high table at the left.
  • Figure 2: The scores for the different scales for the three conditions. Enjoyment, ease of use and willingness to use the robot again are measured on a 5-point Likert scale, while the performance trust uses a 7-point Likert scale.
  • Figure 3: The overall scores of the three conditions in regard to the self-reported expertise with social robots (1 = Not familiar at all, 5 = Extremely familiar).
  • Figure 4: The average number of user words per utterance per interaction.