Large Language Model for Assisted Robot Programming in Micro-Assembly
- authored by
- Rolf Wiemann, Niklas Terei, Annika Raatz
- Abstract
In the context of the rapid development of micro-devices and photonics, the importance of efficient automation solutions is becoming increasingly important. The automation of assembly processes in particular is a decisive factor, as assembly is responsible for a large proportion of costs. The programming of robots, particularly in the field of micro-assembly, requires extensive specialist knowledge due to the complexity of the assembly systems and processes. Increasingly more powerful large language models (LLMs) enable their use in robot programming. These allow interaction through natural language, providing an intuitive user interface. In this work, we utilize a LLM to assist users in programming new micro-assembly processes. We develop an assistant that we integrate into a Robot Operating System 2 (ROS2) framework. This framework enables the control and programming of a micro-assembly robot via ROS2 services. The assistant has access to these services and information about the components. Based on user requests, the assistant can parameterize these services and arrange them sequentially according to the assembly task. The assembly sequence can subsequently be modified by the user, either by using the assistant again or manually. We test the performance of the developed assistant using example tasks and demonstrate that, particularly, shorter sequences can be reliably generated. Finally, we present potential improvements and extensions of the application.
- Organisation(s)
-
Institute for Assembly Technology and Robotics
PhoenixD: Photonics, Optics, and Engineering - Innovation Across Disciplines
- Type
- Conference article
- Journal
- IFAC-PapersOnLine
- Volume
- 58
- Pages
- 244-249
- No. of pages
- 6
- ISSN
- 2405-8971
- Publication date
- 2024
- Publication status
- Published
- Peer reviewed
- Yes
- ASJC Scopus subject areas
- Control and Systems Engineering
- Electronic version(s)
-
https://doi.org/10.1016/j.procir.2024.10.083 (Access:
Open)
