English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large-language models (LLMs) hold significant promise in improvinghuman-robot interaction, offering advanced conversational skills andversatility in managing diverse, open-ended user requests in various tasks anddomains. Despite the potential to transform human-robot interaction, verylittle is known about the distinctive design requirements for utilizing LLMs inrobots, which may differ from text and voice interaction and vary by task andcontext. To better understand these requirements, we conducted a user study (n= 32) comparing an LLM-powered social robot against text- and voice-basedagents, analyzing task-based requirements in conversational tasks, includingchoose, generate, execute, and negotiate. Our findings show that LLM-poweredrobots elevate expectations for sophisticated non-verbal cues and excel inconnection-building and deliberation, but fall short in logical communicationand may induce anxiety. We provide design implications both for robotsintegrating LLMs and for fine-tuning LLMs for use with robots.

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