Version 1
: Received: 23 April 2023 / Approved: 24 April 2023 / Online: 24 April 2023 (05:24:27 CEST)
Version 2
: Received: 24 April 2023 / Approved: 25 April 2023 / Online: 25 April 2023 (03:42:52 CEST)
Version 3
: Received: 25 April 2023 / Approved: 26 April 2023 / Online: 26 April 2023 (03:54:36 CEST)
How to cite:
Koubaa, A. ROSGPT: Next-Generation Human-Robot Interaction with ChatGPT and ROS. Preprints2023, 2023040827. https://doi.org/10.20944/preprints202304.0827.v3
Koubaa, A. ROSGPT: Next-Generation Human-Robot Interaction with ChatGPT and ROS. Preprints 2023, 2023040827. https://doi.org/10.20944/preprints202304.0827.v3
Koubaa, A. ROSGPT: Next-Generation Human-Robot Interaction with ChatGPT and ROS. Preprints2023, 2023040827. https://doi.org/10.20944/preprints202304.0827.v3
APA Style
Koubaa, A. (2023). ROSGPT: Next-Generation Human-Robot Interaction with ChatGPT and ROS. Preprints. https://doi.org/10.20944/preprints202304.0827.v3
Chicago/Turabian Style
Koubaa, A. 2023 "ROSGPT: Next-Generation Human-Robot Interaction with ChatGPT and ROS" Preprints. https://doi.org/10.20944/preprints202304.0827.v3
Abstract
This paper presents ROSGPT, an innovative concept that harnesses the capabilities of large language models (LLMs) to significantly advance human-robot interaction. We develop ROSGPT as a ROS2 package that seamlessly integrates ChatGPT with ROS2-based robotic systems. The core idea is to leverage prompt engineering with LLMs, specifically ChatGPT, utilizing its unique properties such as ability eliciting, chain-of-thought, and instruction tuning. The concept employs ontology development to convert unstructured natural language commands into structured robotic instructions specific to the application context through prompt engineering. We capitalize on LLMs' zero-shots and few-shots learning capabilities by eliciting \textit{structured} robotic commands from \textit{unstructured} human language inputs. To demonstrate the feasibility of this concept, we implemented a proof-of-concept that integrates ChatGPT with ROS2, showcasing the transformation of human language instructions into spatial navigation commands for a ROS2-enabled robot. This versatile concept can be easily adapted to various other robotic missions. ROSGPT serves as a new stride towards Artificial General Intelligence (AGI) and paves the way for the robotics and natural language processing communities to collaborate in creating novel, intuitive human-robot interactions. The open-source implementation of ROSGPT on ROS 2 is available on GitHub.
Keywords
Human-Robot Interaction; ROS; ROS2; ChatGPT; Large Language Model; Robot Operating System
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Commenter: Anis Koubaa
Commenter's Conflict of Interests: Author
Fixed typos