Understanding Large-Language Model (LLM)-powered Human-Robot Interaction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Callie Y., Lee, Christine P., Mutlu, Bilge
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916081952620544
author Kim, Callie Y.
Lee, Christine P.
Mutlu, Bilge
author_facet Kim, Callie Y.
Lee, Christine P.
Mutlu, Bilge
contents Large-language models (LLMs) hold significant promise in improving human-robot interaction, offering advanced conversational skills and versatility in managing diverse, open-ended user requests in various tasks and domains. Despite the potential to transform human-robot interaction, very little is known about the distinctive design requirements for utilizing LLMs in robots, which may differ from text and voice interaction and vary by task and context. To better understand these requirements, we conducted a user study (n = 32) comparing an LLM-powered social robot against text- and voice-based agents, analyzing task-based requirements in conversational tasks, including choose, generate, execute, and negotiate. Our findings show that LLM-powered robots elevate expectations for sophisticated non-verbal cues and excel in connection-building and deliberation, but fall short in logical communication and may induce anxiety. We provide design implications both for robots integrating LLMs and for fine-tuning LLMs for use with robots.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03217
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Understanding Large-Language Model (LLM)-powered Human-Robot Interaction
Kim, Callie Y.
Lee, Christine P.
Mutlu, Bilge
Robotics
Human-Computer Interaction
Large-language models (LLMs) hold significant promise in improving human-robot interaction, offering advanced conversational skills and versatility in managing diverse, open-ended user requests in various tasks and domains. Despite the potential to transform human-robot interaction, very little is known about the distinctive design requirements for utilizing LLMs in robots, which may differ from text and voice interaction and vary by task and context. To better understand these requirements, we conducted a user study (n = 32) comparing an LLM-powered social robot against text- and voice-based agents, analyzing task-based requirements in conversational tasks, including choose, generate, execute, and negotiate. Our findings show that LLM-powered robots elevate expectations for sophisticated non-verbal cues and excel in connection-building and deliberation, but fall short in logical communication and may induce anxiety. We provide design implications both for robots integrating LLMs and for fine-tuning LLMs for use with robots.
title Understanding Large-Language Model (LLM)-powered Human-Robot Interaction
topic Robotics
Human-Computer Interaction
url https://arxiv.org/abs/2401.03217