CHATBOX: A Lightweight, Cost-Efficient Social Companion Robot for Mental Health Support via Emotion-Aware RAG Interaction

Abstract

We present CHATBOX, a lightweight, costefficient Socially Assistive Robot (SAR) for mental health conversations with young users. Built from 3D-printed components and low-cost servo motors, CHATBOX delivers a deployable 12-DOF expressive platform costing under USD 300. An interchangeable animal-mask system gives users agency over companion morphology and support user engagement. The system adopts an edge-to-server architecture in which a Jetson Nano communicates with a local server running a customised EfficientNet V2-S Facial Emotion Recognition (FER) model (CHATBOX V1), achieving 81% validation accuracy across seven emotion classes. We integrate Retrieval-Augmented Generation (RAG) as an emotionally grounded continuity layer: session logs and emotional states are embedded after each interaction and retrieved in later sessions, enabling contextaware responses perceived as attentive rather than scripted. A pilot in-lab study with $N=10$ participants (ages 10-16) provides preliminary indications of comfort, friendliness, and perceived continuity.