EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Peide, Hu, Yuhan, Nechyporenko, Nataliya, Kim, Daehwa, Talbott, Walter, Zhang, Jian
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910678522003456
author Huang, Peide
Hu, Yuhan
Nechyporenko, Nataliya
Kim, Daehwa
Talbott, Walter
Zhang, Jian
author_facet Huang, Peide
Hu, Yuhan
Nechyporenko, Nataliya
Kim, Daehwa
Talbott, Walter
Zhang, Jian
contents This paper introduces a framework, called EMOTION, for generating expressive motion sequences in humanoid robots, enhancing their ability to engage in humanlike non-verbal communication. Non-verbal cues such as facial expressions, gestures, and body movements play a crucial role in effective interpersonal interactions. Despite the advancements in robotic behaviors, existing methods often fall short in mimicking the diversity and subtlety of human non-verbal communication. To address this gap, our approach leverages the in-context learning capability of large language models (LLMs) to dynamically generate socially appropriate gesture motion sequences for human-robot interaction. We use this framework to generate 10 different expressive gestures and conduct online user studies comparing the naturalness and understandability of the motions generated by EMOTION and its human-feedback version, EMOTION++, against those by human operators. The results demonstrate that our approach either matches or surpasses human performance in generating understandable and natural robot motions under certain scenarios. We also provide design implications for future research to consider a set of variables when generating expressive robotic gestures.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23234
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning
Huang, Peide
Hu, Yuhan
Nechyporenko, Nataliya
Kim, Daehwa
Talbott, Walter
Zhang, Jian
Robotics
Artificial Intelligence
This paper introduces a framework, called EMOTION, for generating expressive motion sequences in humanoid robots, enhancing their ability to engage in humanlike non-verbal communication. Non-verbal cues such as facial expressions, gestures, and body movements play a crucial role in effective interpersonal interactions. Despite the advancements in robotic behaviors, existing methods often fall short in mimicking the diversity and subtlety of human non-verbal communication. To address this gap, our approach leverages the in-context learning capability of large language models (LLMs) to dynamically generate socially appropriate gesture motion sequences for human-robot interaction. We use this framework to generate 10 different expressive gestures and conduct online user studies comparing the naturalness and understandability of the motions generated by EMOTION and its human-feedback version, EMOTION++, against those by human operators. The results demonstrate that our approach either matches or surpasses human performance in generating understandable and natural robot motions under certain scenarios. We also provide design implications for future research to consider a set of variables when generating expressive robotic gestures.
title EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2410.23234