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

TL;DR

This paper presents EMOTION, a novel framework using in-context learning of large language models to generate expressive, humanlike motion sequences for humanoid robots, improving non-verbal communication in human-robot interactions.

Contribution

It introduces EMOTION, a new method leveraging LLMs for dynamic, context-aware gesture generation, surpassing prior approaches in diversity and subtlety of robotic non-verbal cues.

Findings

Generated gestures are often rated as natural and understandable.

EMOTION matches or exceeds human performance in user studies.

Provides design guidelines for future expressive gesture generation.

Abstract

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.