How can LLMs transform the robotic design process?

Francesco Stella; Cosimo Della Santina; Josie Hughes

doi:10.1038/s42256-023-00669-7

How can LLMs transform the robotic design process?

Francesco Stella^*, Cosimo Della Santina, Josie Hughes

^*Corresponding author for this work

Learning & Autonomous Control

Research output: Contribution to journal › Comment/Letter to the editor › Scientific › peer-review

4 Citations (Scopus)

102 Downloads (Pure)

Abstract

We show that large language models (LLMs), such as ChatGPT, can guide the robot design process, on both the conceptual and technical level, and we propose new human–AI co-design strategies and their societal implications.

Original language	English
Pages (from-to)	561-564
Journal	Nature Machine Intelligence
Volume	5
Issue number	6
DOIs	https://doi.org/10.1038/s42256-023-00669-7
Publication status	Published - 2023

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Access to Document

10.1038/s42256-023-00669-7

s42256-023-00669-7Final published version, 5.41 MB

Cite this

@article{4c136ce731a448c1982f587c51760242,

title = "How can LLMs transform the robotic design process?",

abstract = "We show that large language models (LLMs), such as ChatGPT, can guide the robot design process, on both the conceptual and technical level, and we propose new human–AI co-design strategies and their societal implications.",

author = "Francesco Stella and {Della Santina}, Cosimo and Josie Hughes",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.",

year = "2023",

doi = "10.1038/s42256-023-00669-7",

language = "English",

volume = "5",

pages = "561--564",

journal = "Nature Machine Intelligence",

issn = "2522-5839",