DinoCompanion: An Attachment-Theory Informed Multimodal Robot for Emotionally Responsive Child-AI Interaction
Authors:
- Boyang WangBWBoyang Wang
- Yuhao SongYSYuhao Song
- Jinyuan CaoJCJinyuan Cao
- Peng YuPYPeng Yu
- Hongcheng GuoHGHongcheng Guo
- Zhoujun LiZLZhoujun Li
Preprint
Abstract
Children's emotional development fundamentally relies on secure attachment relationships, yet current AI companions lack the theoretical foundation to provide developmentally appropriate emotional support. We introduce DinoCompanion, the first attachment-theory-grounded multimodal robot for emotionally responsive child-AI interaction. We address three critical challenges in child-AI systems: the absence of developmentally-informed AI architectures, the need to balance engagement with safety, and the lack of standardized evaluation frameworks for attachment-based capabilities. Our contributions include: (i) a multimodal dataset of 128 caregiver-child dyads containing 125,382 annotated clips with paired preference-risk labels, (ii) CARPO (Child-Aware Risk-calibrated Preference Optimization), a novel training objective that maximizes engagement while applying epistemic-uncertainty-weighted risk penalties, and (iii) AttachSecure-Bench, a comprehensive evaluation benchmark covering ten attachment-centric competencies with strong expert consensus (\k{appa}=0.81). DinoCompanion achieves state-of-the-art performance (57.15%), outperforming GPT-4o (50.29%) and Claude-3.7-Sonnet (53.43%), with exceptional secure base behaviors (72.99%, approaching human expert levels of 78.4%) and superior attachment risk detection (69.73%). Ablations validate the critical importance of multimodal fusion, uncertainty-aware risk modeling, and hierarchical memory for coherent, emotionally attuned interactions.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Parental Involvement in Adolescent Psychological Interventions: A Meta-analysisClinical Child and Family Psychology Review, 2024
- Effects of AI understanding-training on AI literacy, usage, self-determined interactions, and anthropomorphization with voice assistantsComputers and Education Open, 2024
- Effectiveness of AI-assisted game-based learning on science learning outcomes, intrinsic motivation, cognitive load, and learning behaviorEducation and Information Technologies, 2024
- Screen Time, Sociodemographic Factors, and Psychological Well-Being Among Young ChildrenJAMA Network Open, 2024
- Are screen media the new pacifiers? The role of parenting stress and parental attitudes for children's screen time in early childhoodComputers in Human Behavior, 2023
- A Scoping Review of the Use of Robotics Technologies for Supporting Social-Emotional Learning in Children with AutismJournal of Autism and Developmental Disorders, 2023
- Is the screen time duration affecting children's language development? - A scoping reviewClinical Epidemiology and Global Health, 2023
- Body stakes: an existential ethics of care in living with biometrics and AIAI & SOCIETY, 2022
- Can communication with social robots influence how children develop empathy? Best-evidence synthesisAI & SOCIETY, 2021
- Facilitating the Child–Robot Interaction by Endowing the Robot with the Capability of Understanding the Child Engagement: The Case of Mio Amico RobotInternational Journal of Social Robotics, 2020