Paper Image

Fine-tuning language models for robot programming assistance

Published on:

21 December 2023

Primary Category:

Robotics

Paper Authors:

Benjamin Alt,

Urs Keßner,

Aleksandar Taranovic,

Darko Katic,

Andreas Hermann,

Rainer Jäkel,

Gerhard Neumann

Bullets

Key Details

Proposes natural language assistant for industrial robot programming

Investigates domain adaptation of large language models

Compares model variants trained with different strategies

Evaluates models quantitatively and via user survey

Alpaca-based models perform best but still have issues

AI generated summary

Fine-tuning language models for robot programming assistance

This paper proposes an interactive, natural language-based assistant to help users program advanced industrial robots. It investigates strategies to adapt large language models for this domain using limited data and compute resources typical of small and medium-sized enterprises.

Answers from this paper

Comments

No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up