Can you pass that tool?: Implications of Indirect Speech in Physical Human-Robot Collaboration

2025-02-17

AI Summary

This study addresses the lack of empirical research on indirect speech acts (ISAs) in physical human–robot collaboration (HRC), where the impact mechanisms of ISAs remain unclear and no principled strategies exist for coordinating direct versus indirect requests. We conducted a 36-participant Wizard-of-Oz experiment integrating natural language interaction with multidimensional evaluation—assessing anthropomorphism perception, trust, and team performance. Results demonstrate, for the first time empirically, that robotic ISA comprehension significantly enhances human anthropomorphism perception (+32%), task performance (+24%), and trust (+28%). Crucially, we identify task-context sensitivity as a key moderating factor: ISA effectiveness varies systematically with task type and collaborative demands. Building on this insight, we propose the first task-driven coordination strategy for direct and indirect requests in HRC. This work establishes both theoretical foundations and practical design guidelines for developing more natural, interpretable, and trustworthy human–robot interaction paradigms.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Indirect speech acts (ISAs) are a natural pragmatic feature of human communication, allowing requests to be conveyed implicitly while maintaining subtlety and flexibility. Although advancements in speech recognition have enabled natural language interactions with robots through direct, explicit commands--providing clarity in communication--the rise of large language models presents the potential for robots to interpret ISAs. However, empirical evidence on the effects of ISAs on human-robot collaboration (HRC) remains limited. To address this, we conducted a Wizard-of-Oz study (N=36), engaging a participant and a robot in collaborative physical tasks. Our findings indicate that robots capable of understanding ISAs significantly improve human's perceived robot anthropomorphism, team performance, and trust. However, the effectiveness of ISAs is task- and context-dependent, thus requiring careful use. These results highlight the importance of appropriately integrating direct and indirect requests in HRC to enhance collaborative experiences and task performance.

Problem

• Understanding indirect speech in robots
• Impact on human-robot collaboration
• Task-dependent effectiveness of ISAs

Innovation

• Indirect speech acts interpretation
• Wizard-of-Oz study methodology
• Task-dependent ISA effectiveness analysis