"Meet My Sidekick!": Effects of Separate Identities and Control of a Single Robot in HRI

2026-02-07

AI Summary

This study investigates how attributing distinct identities to physically separated control domains—such as the head and gripper—on a single robotic platform influences human perception of its capabilities and implicit trust. Using a mixed experimental design, the research compares three presentation conditions (single robot, co-controlled dual agents, and separately controlled dual agents) across supportive, fault-isolation, and collaborative tasks. Results demonstrate that users reliably perceive the distinct control domains as independent agents and accurately attribute faults to the corresponding identity. This work provides the first empirical validation that “disembodied representation” on a unified robotic platform can yield the cognitive benefits of multi-agent collaboration, significantly enhancing attributional clarity and enabling more nuanced trust calibration in human–robot interaction.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Multiagent Systems: Adversarial Agents

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

The presentation of a robot's capability and identity directly influences a human collaborator's perception and implicit trust in the robot. Unlike humans, a physical robot can simultaneously present different identities and have them reside and control different parts of the robot. This paper presents a novel study that investigates how users perceive a robot where different robot control domains (head and gripper) are presented as independent robots. We conducted a mixed design study where participants experienced one of three presentations: a single robot, two agents with shared full control (co-embodiment), or two agents with split control across robot control domains (split-embodiment). Participants underwent three distinct tasks -- a mundane data entry task where the robot provides motivational support, an individual sorting task with isolated robot failures, and a collaborative arrangement task where the robot causes a failure that directly affects the human participant. Participants perceived the robot as residing in the different control domains and were able to associate robot failure with different identities. This work signals how future robots can leverage different embodiment configurations to obtain the benefit of multiple robots within a single body.

Problem

• human-robot interaction
• robot identity
• embodiment
• control allocation
• trust

Innovation

• split-embodiment
• robot identity
• human-robot interaction
• co-embodiment
• implicit trust