Signaling Human Intentions to Service Robots: Understanding the Use of Social Cues during In-Person Conversations

TL;DR

This study investigates how people signal their intentions to service robots during social interactions, focusing on how robot morphology and primary-task roles influence cue choices. Using an AR-based elicitation study with 24 participants, four robot morphologies (anthropomorphic, zoomorphic, grounded technical, aerial technical) and 13 referents were examined in a coffee-chat scenario, analyzed through multimodal cue coding and ordinal regression, complemented by retrospective interviews. Key findings show distinct patterns in cue modalities (eye, gesture, verbal) and gesture features that depend on morphology and conversation role, with practical implications for robot approaching strategies, cue processing, and responsive behavior. The work provides design guidance for minimizing interruptions, aligning robot sensing with user expectations, and supporting robust perception of human intent in real-world social environments. It advances our understanding of human-robot social signaling and offers concrete recommendations for deploying service robots in professional, socially dynamic settings.

Abstract

As social service robots become commonplace, it is essential for them to effectively interpret human signals, such as verbal, gesture, and eye gaze, when people need to focus on their primary tasks to minimize interruptions and distractions. Toward such a socially acceptable Human-Robot Interaction, we conducted a study ($N=24$) in an AR-simulated context of a coffee chat. Participants elicited social cues to signal intentions to an anthropomorphic, zoomorphic, grounded technical, or aerial technical robot waiter when they were speakers or listeners. Our findings reveal common patterns of social cues over intentions, the effects of robot morphology on social cue position and conversational role on social cue complexity, and users' rationale in choosing social cues. We offer insights into understanding social cues concerning perceptions of robots, cognitive load, and social context. Additionally, we discuss design considerations on approaching, social cue recognition, and response strategies for future service robots.

Figures (4)

• Figure 1: Four Forms of Robots Used in Our Experiment
• Figure 2: Experiment scenes with four robot morphologies. First row: Scenario illustrations showing (a) anthropomorphic, (b) zoomorphic, (c) grounded technical, and (d) aerial technical robots. Second row: Corresponding first-person participant viewpoints captured.
• Figure 3: The figure illustrations of some common codes in the Gesture modality.
• Figure 4: Explicit (dark) and implicit (light) Modality usages by Referent.