Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 244-249 |
| Seitenumfang | 6 |
| Fachzeitschrift | IFAC-PapersOnLine |
| Jahrgang | 58 |
| Ausgabenummer | 27 |
| Frühes Online-Datum | 27 Nov. 2024 |
| Publikationsstatus | Veröffentlicht - 2024 |
| Veranstaltung | 18th IFAC Workshop on Time Delay Systems, TDS 2024 - Udine, Italien Dauer: 2 Okt. 2023 → 5 Okt. 2023 |
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.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Steuerungs- und Systemtechnik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: IFAC-PapersOnLine, Jahrgang 58, Nr. 27, 2024, S. 244-249.
Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
TY - JOUR
T1 - Large Language Model for Assisted Robot Programming in Micro-Assembly
AU - Wiemann, Rolf
AU - Terei, Niklas
AU - Raatz, Annika
N1 - Publisher Copyright: © 2024 The Authors.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Intuitive Robot Programming
KW - Large Language Models
KW - Micro-Assembly
KW - ROS2
UR - http://www.scopus.com/inward/record.url?scp=85213022950&partnerID=8YFLogxK
U2 - 10.1016/j.procir.2024.10.083
DO - 10.1016/j.procir.2024.10.083
M3 - Conference article
AN - SCOPUS:85213022950
VL - 58
SP - 244
EP - 249
JO - IFAC-PapersOnLine
JF - IFAC-PapersOnLine
SN - 2405-8971
IS - 27
T2 - 18th IFAC Workshop on Time Delay Systems, TDS 2024
Y2 - 2 October 2023 through 5 October 2023
ER -