RecipeMasterLLM: Revisiting RoboEarth in the Era of Large Language Models

TL;DR

RecipeMasterLLM leverages fine-tuned large language models and retrieval-augmented generation to automate the creation of OWL action ontologies in cloud robotics, enhancing knowledge sharing and updating processes.

Contribution

The paper introduces RecipeMasterLLM, a novel approach that automates knowledge acquisition for RoboEarth using LLMs and RAG, reducing manual effort and improving accuracy.

Findings

Automated generation of OWL action ontologies from user prompts.

Enhanced contextual understanding through retrieval-augmented generation.

Improved accuracy and efficiency in updating robot knowledge bases.

Abstract

RoboEarth was a pioneering initiative in cloud robotics, establishing a foundational framework for robots to share and exchange knowledge about actions, objects, and environments through a standardized knowledge graph. Initially, this knowledge was predominantly hand-crafted by engineers using RDF triples within OWL Ontologies, with updates, such as changes in an object's pose, being asserted by the robot's control and perception routines. However, with the advent and rapid development of Large Language Models (LLMs), we believe that the process of knowledge acquisition can be significantly automated. To this end, we propose RecipeMasterLLM, a high-level planner, that generates OWL action ontologies based on a standardized knowledge graph in response to user prompts. This architecture leverages a fine-tuned LLM specifically trained to understand and produce action descriptions consistent with the RoboEarth standardized knowledge graph. Moreover, during the Retrieval-Augmented Generation (RAG) phase, environmental knowledge is supplied to the LLM to enhance its contextual understanding and improve the accuracy of the generated action descriptions.