Domain-Specific Fine-Tuning of Large Language Models for Interactive Robot Programming

Benjamin Alt; Urs Keßner; Aleksandar Taranovic; Darko Katic; Andreas Hermann; Rainer Jäkel; Gerhard Neumann

Domain-Specific Fine-Tuning of Large Language Models for Interactive Robot Programming

Robotics 2024-04-23 v2 Artificial Intelligence Computation and Language Human-Computer Interaction Machine Learning

Authors: Benjamin Alt , Urs Keßner , Aleksandar Taranovic , Darko Katic , Andreas Hermann , Rainer Jäkel , Gerhard Neumann

View on arXiv ↗ PDF ↗

Abstract

Industrial robots are applied in a widening range of industries, but robot programming mostly remains a task limited to programming experts. We propose a natural language-based assistant for programming of advanced, industrial robotic applications and investigate strategies for domain-specific fine-tuning of foundation models with limited data and compute.

Keywords

robot learning programming languages robotics

Cite

@article{arxiv.2312.13905,
  title  = {Domain-Specific Fine-Tuning of Large Language Models for Interactive Robot Programming},
  author = {Benjamin Alt and Urs Keßner and Aleksandar Taranovic and Darko Katic and Andreas Hermann and Rainer Jäkel and Gerhard Neumann},
  journal= {arXiv preprint arXiv:2312.13905},
  year   = {2024}
}

Comments

5 pages, 1 figure, presented at the 2024 European Robotics Forum in Rimini, Italy

Domain-Specific Fine-Tuning of Large Language Models for Interactive Robot Programming

Abstract

Keywords

Cite

Comments

Related papers