Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

"See You Later, Alligator": Impacts of Robot Small Talk on Task, Rapport, and Interaction Dynamics in Human-Robot Collaboration

Kaitlynn Taylor Pineda, Ethan Brown, Chien-Ming Huang

TL;DR

This work examines whether small talk by a non-anthropomorphic industrial robot can improve human-robot collaboration. By building a GPT-4o–driven system that recognizes social intent and generates conversational responses, the authors compare a task-only robot to one that also engages in small talk during PVC pipe assembly (N=58). They find that social small talk significantly boosts perceived rapport and elicits active social engagement, but also increases overall task duration due to idle time and novelty effects, underscoring a trade-off between social richness and productivity. The study offers design guidance for balancing frequency and timing of robot small talk and highlights ethical considerations around deception, social pressure, and transparency when deploying LLM-enabled interactions in work settings.

Abstract

Small talk can foster rapport building in human-human teamwork; yet how non-anthropomorphic robots, such as collaborative manipulators commonly used in industry, may capitalize on these social communications remains unclear. This work investigates how robot-initiated small talk influences task performance, rapport, and interaction dynamics in human-robot collaboration. We developed an autonomous robot system that assists a human in an assembly task while initiating and engaging in small talk. A user study ($N = 58$) was conducted in which participants worked with either a functional robot, which engaged in only task-oriented speech, or a social robot, which also initiated small talk. Our study found that participants in the social condition reported significantly higher levels of rapport with the robot. Moreover, all participants in the social condition responded to the robot's small talk attempts; 59% initiated questions to the robot, and 73% engaged in lingering conversations after requesting the final task item. Although active working times were similar across conditions, participants in the social condition recorded longer task durations than those in the functional condition. We discuss the design and implications of robot small talk in shaping human-robot collaboration.

"See You Later, Alligator": Impacts of Robot Small Talk on Task, Rapport, and Interaction Dynamics in Human-Robot Collaboration

TL;DR

This work examines whether small talk by a non-anthropomorphic industrial robot can improve human-robot collaboration. By building a GPT-4o–driven system that recognizes social intent and generates conversational responses, the authors compare a task-only robot to one that also engages in small talk during PVC pipe assembly (N=58). They find that social small talk significantly boosts perceived rapport and elicits active social engagement, but also increases overall task duration due to idle time and novelty effects, underscoring a trade-off between social richness and productivity. The study offers design guidance for balancing frequency and timing of robot small talk and highlights ethical considerations around deception, social pressure, and transparency when deploying LLM-enabled interactions in work settings.

Abstract

Small talk can foster rapport building in human-human teamwork; yet how non-anthropomorphic robots, such as collaborative manipulators commonly used in industry, may capitalize on these social communications remains unclear. This work investigates how robot-initiated small talk influences task performance, rapport, and interaction dynamics in human-robot collaboration. We developed an autonomous robot system that assists a human in an assembly task while initiating and engaging in small talk. A user study () was conducted in which participants worked with either a functional robot, which engaged in only task-oriented speech, or a social robot, which also initiated small talk. Our study found that participants in the social condition reported significantly higher levels of rapport with the robot. Moreover, all participants in the social condition responded to the robot's small talk attempts; 59% initiated questions to the robot, and 73% engaged in lingering conversations after requesting the final task item. Although active working times were similar across conditions, participants in the social condition recorded longer task durations than those in the functional condition. We discuss the design and implications of robot small talk in shaping human-robot collaboration.
Paper Structure (30 sections, 3 figures, 1 table)

This paper contains 30 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background and Related Works
  3. Small Talk in Humans
  4. Human-Machine Small Talk
  5. Leveraging LLMs for Robot Small Talk
  6. Engineering a Robot to Engage in Small Talk
  7. Speech Listener: Continuous Speech Processing
  8. Phase 1: Intent Recognition
  9. Phase 2: Robot Behavior Generation
  10. Methods
  11. Experimental Conditions and Task
  12. Hypotheses
  13. Procedure
  14. Measures
  15. Primary Metrics
  16. ...and 15 more sections

Figures (3)

  • Figure 1: System Overview. The blue circles in Phase 2 denote robot behaviors.
  • Figure 2: We investigated four primary metrics; a significant difference was found between conditions for (a) task duration and (b) perceived rapport.
  • Figure 3: We plot task time breakdown results by condition in Fig. \ref{['fig:task-time-expressions']}a-\ref{['fig:task-time-expressions']}d. Significant differences were found for (c) human idle time and (d) robot idle time. We also plot the significant differences between conditions for individual and overall emotional expressiveness in Fig. \ref{['fig:task-time-expressions']}e-\ref{['fig:task-time-expressions']}g.