Signal or'Noise': Human Reactions to Robot Errors in the Wild

2026-02-04

AI Summary

This study investigates the consistency and utility of human social responses to errors made by non-social robots during repeated and group interactions in real-world settings. Deploying a coffee-serving robot in a public space, the research conducted in-situ observations and social signal analysis of natural interactions with 49 participants, offering the first systematic examination of human reactions to non-social robot failures outside controlled laboratory environments. Findings reveal that participants consistently exhibited rich and diverse social signals, particularly in group contexts where they proactively provided interaction-relevant information; however, these signals also contained substantial noise. The work underscores the complexity of social signaling in authentic human–robot interaction and provides an empirical foundation for designing fault-tolerant behaviors in non-social robots.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Humans and AI: Interaction Techniques and Devices

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Social Networks and Social Media: Analysis of web-mediated communications, communities, and crowds

Abstract

In the real world, robots frequently make errors, yet little is known about people's social responses to errors outside of lab settings. Prior work has shown that social signals are reliable and useful for error management in constrained interactions, but it is unclear if this holds in the real world - especially with a non-social robot in repeated and group interactions with successive or propagated errors. To explore this, we built a coffee robot and conducted a public field deployment ($N = 49$). We found that participants consistently expressed varied social signals in response to errors and other stimuli, particularly during group interactions. Our findings suggest that social signals in the wild are rich (with participants volunteering information about the interaction), but"noisy."We discuss lessons, benefits, and challenges for using social signals in real-world HRI.

Problem

• human-robot interaction
• robot errors
• social signals
• field study
• group interaction

Innovation

• social signals
• robot errors
• field study
• human-robot interaction
• real-world HRI