Would you let a humanoid play storytelling with your child? A usability study on LLM-powered narrative Humanoid-Robot Interaction
🤖 AI Summary
This study addresses the lack of contextual awareness and natural interaction capabilities in social robots deployed for education, assistance, and rehabilitation—particularly with children. We propose a narrative-driven, socially aware humanoid robot interaction framework built on the iCub platform, integrating generative AI (e.g., ChatGPT), computer vision, and multimodal social behavior modeling. The system enables real-time recognition of social cues, turn-taking responsiveness, and dynamic adaptation to evolving narrative contexts during child-robot collaborative storytelling. Its key innovation lies in tightly coupling generative narrative generation with explicit social intent understanding, jointly optimizing semantic coherence and behavioral appropriateness. User studies demonstrate significant improvements in interaction naturalness, engagement, and quality of socially contingent responses. The framework establishes a scalable, embodied human-robot collaboration paradigm tailored for child-centered applications.
Application Category
📝 Abstract
A key challenge in human-robot interaction research lies in developing robotic systems that can effectively perceive and interpret social cues, facilitating natural and adaptive interactions. In this work, we present a novel framework for enhancing the attention of the iCub humanoid robot by integrating advanced perceptual abilities to recognise social cues, understand surroundings through generative models, such as ChatGPT, and respond with contextually appropriate social behaviour. Specifically, we propose an interaction task implementing a narrative protocol (storytelling task) in which the human and the robot create a short imaginary story together, exchanging in turn cubes with creative images placed on them. To validate the protocol and the framework, experiments were performed to quantify the degree of usability and the quality of experience perceived by participants interacting with the system. Such a system can be beneficial in promoting effective human robot collaborations, especially in assistance, education and rehabilitation scenarios where the social awareness and the robot responsiveness play a pivotal role.
Problem
Research questions and friction points this paper is trying to address.
Enhancing humanoid robot attention via social cue recognition
Implementing storytelling interaction for human-robot collaboration
Evaluating usability in education and rehabilitation scenarios
Innovation
Methods, ideas, or system contributions that make the work stand out.
Integrating ChatGPT for social cue understanding
Using storytelling to enhance human-robot interaction
Implementing image cubes for creative narrative exchange
🔎 Similar Papers
No similar papers found.
