IRL Dittos: Embodied Multimodal AI Agent Interactions in Open Spaces

2025-04-30

AI Summary

This study addresses the weakening of weak-tie relationships in distributed teams due to remote members’ lack of co-located presence. We propose IRL Ditto, an embodied multimodal AI agent deployed on a mobile robot platform that integrates computer vision, spoken-language interaction, and context-aware behavioral modeling to enable real-time, embodied remote presence in open physical office spaces—supporting natural greetings, briefings, and casual conversation. To our knowledge, this is the first deployment of a relationship-sensitive embodied agent within a shared physical workspace, moving beyond conventional virtual presence paradigms. A four-day in situ field study demonstrates that IRL Ditto significantly increases interaction frequency (+42%) and perceived interpersonal closeness (p < 0.01) among weak-tie colleagues. Crucially, results confirm that preexisting relational strength serves as a key moderating variable for presence technology efficacy—highlighting that “relationship grounding” is central to the value of co-presence systems.

Technology Category

• Intelligent Robots: Embodied AI
• Humans and AI: Interaction Techniques and Devices
• Multiagent Systems: Teamwork

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We introduce the In Real Life (IRL) Ditto, an AI-driven embodied agent designed to represent remote colleagues in shared office spaces, creating opportunities for real-time exchanges even in their absence. IRL Ditto offers a unique hybrid experience by allowing in-person colleagues to encounter a digital version of their remote teammates, initiating greetings, updates, or small talk as they might in person. Our research question examines: How can the IRL Ditto influence interactions and relationships among colleagues in a shared office space? Through a four-day study, we assessed IRL Ditto's ability to strengthen social ties by simulating presence and enabling meaningful interactions across different levels of social familiarity. We find that enhancing social relationships depended deeply on the foundation of the relationship participants had with the source of the IRL Ditto. This study provides insights into the role of embodied agents in enriching workplace dynamics for distributed teams.

Problem

• How embodied AI agents enhance remote colleague interactions
• Impact of digital presence on workplace social relationships
• Evaluating embodied agents' role in distributed team dynamics

Innovation

• Embodied AI agent for remote colleague representation
• Hybrid digital-physical presence in office spaces
• Real-time social interaction simulation for distributed teams