A Social Robot with Inner Speech for Dietary Guidance

2025-05-13

AI Summary

This study addresses the low transparency of dietary recommendations and consequent lack of user trust in social robots deployed in healthcare settings. We propose an explainable interaction method grounded in the cognitive mechanism of inner speech—marking the first application of human introspective verbalization to dietary guidance robots. Our approach introduces a multi-layer introspective reasoning architecture that integrates large language models (for semantic understanding) with a dietary knowledge graph (for structured nutritional inference), enabling robots to explicitly articulate their decision rationale. Experimental results demonstrate significant improvements in users’ trust and comprehension of dietary advice. A small-scale user study confirms explanation reliability at 89%, with acceptable inference latency. The core contribution lies in formalizing introspective speech—a well-established concept in cognitive science—as a computationally tractable, empirically verifiable, and anthropomorphic paradigm for explainable AI. This work establishes a novel foundation for trustworthy human–robot collaboration in health care.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We explore the use of inner speech as a mechanism to enhance transparency and trust in social robots for dietary advice. In humans, inner speech structures thought processes and decision-making; in robotics, it improves explainability by making reasoning explicit. This is crucial in healthcare scenarios, where trust in robotic assistants depends on both accurate recommendations and human-like dialogue, which make interactions more natural and engaging. Building on this, we developed a social robot that provides dietary advice, and we provided the architecture with inner speech capabilities to validate user input, refine reasoning, and generate clear justifications. The system integrates large language models for natural language understanding and a knowledge graph for structured dietary information. By making decisions more transparent, our approach strengthens trust and improves human-robot interaction in healthcare. We validated this by measuring the computational efficiency of our architecture and conducting a small user study, which assessed the reliability of inner speech in explaining the robot's behavior.

Problem

• Enhancing transparency and trust in dietary advice robots
• Integrating inner speech for explainable robot decision-making
• Improving human-robot interaction in healthcare through natural dialogue

Innovation

• Inner speech enhances robot transparency and trust.
• Large language models improve natural language understanding.
• Knowledge graph structures dietary information effectively.