Deco: Extending Personal Physical Objects into Pervasive AI Companion through a Dual-Embodiment Framework

📅 2026-05-05
📈 Citations: 0
Influential: 0
📄 PDF

career value

226K/year
🤖 AI Summary
This study addresses the challenge that existing AI companions struggle to sustain emotional bonds users have already formed with physical attachment objects, such as plush toys. To bridge this gap, the authors propose a novel “dual-bodied companionship” framework that synchronizes users’ personal physical artifacts with digital avatars generated through multimodal large language models and augmented reality, enabling emotionally coherent and behaviorally aligned companionship via a mobile system. Emphasizing the extension of pre-existing emotional histories rather than the creation of new relationships, the framework articulates four design principles to guide affective AI development. User studies demonstrate that the implemented system, Deco, significantly outperforms baseline digital companions in perceived companionship and emotional connection (p<0.01), while a seven-day field deployment further confirms its capacity to enhance subjective well-being (p=0.040) and support sustained interaction.
📝 Abstract
Individuals frequently form deep attachments to physical objects (e.g., plush toys) that usually cannot sense or respond to their emotions. While AI companions offer responsiveness and personalization, they exist independently of these physical objects and lack an ongoing connection to them. To bridge this gap, we conducted a formative study (N=9) to explore how digital agents could inherit and extend the emotional bond, deriving four design principles (Faithful Identity, Calibrated Agency, Ambient Presence, and Reciprocal Memory). We then present the Dual-Embodiment Companion Framework, instantiated as Deco, a mobile system integrating multimodal Large Language Models (LLMs) and Augmented Reality to create synchronized digital embodiments of users' physical companions. A within-subjects study (N=25) showed Deco significantly outperformed a personalized LLM-empowered digital companion baseline on perceived companionship, emotional bond, and design-principle scales (all p<0.01). A seven-day field deployment (N=17) showed sustained engagement, subjective well-being improvement (p=.040), and three key relational patterns: digital activities retroactively vitalized physical objects, bond deepening was driven by emotional engagement depth rather than interaction frequency, and users sustained bonds while actively navigating digital companions' AI nature. This work highlights a promising alternative for designing digital companions: moving from creating new relationships to dual embodiment, where digital agents seamlessly extend the emotional history of physical objects.
Problem

Research questions and friction points this paper is trying to address.

AI companion
emotional bond
physical objects
dual embodiment
pervasive AI
Innovation

Methods, ideas, or system contributions that make the work stand out.

Dual-Embodiment
AI Companion
Multimodal LLMs
Augmented Reality
Emotional Bond
🔎 Similar Papers
2024-04-20ACM Symposium on User Interface Software and TechnologyCitations: 10
2024-07-09IEEE/ASME transactions on mechatronicsCitations: 94