Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings - ACM/IEEE 25th International Conference on Model Driven Engineering Languages and Systems, MODELS 2022 |
| Untertitel | Companion Proceedings |
| Seiten | 37-41 |
| Seitenumfang | 5 |
| ISBN (elektronisch) | 9781450394673 |
| Publikationsstatus | Veröffentlicht - 9 Nov. 2022 |
| Veranstaltung | 25th ACM/IEEE International Conference on Model Driven Engineering Languages and Systems, MODELS 2022 - Montreal, Kanada Dauer: 23 Okt. 2022 → 28 Okt. 2022 |
Abstract
In the automotive industry, the design, modeling, and planning of multi-robot cells are manual error-prone, and time-expensive tasks. A recent work investigated, using reactive synthesis, approaches to automate robot task planning, and execution. In this paper, we present a tool that realizes a model-At-runtime approach. The tool is integrated with a robot simulation tool, to automate efficient multi-robot choreography planning, and execution. We illustrate the tool using a multi-robot spot welding cell, inspired from an industrial case. Given a virtual model of the production cell, and user constraints definition, the tool can derive a specification for the reactive synthesis. The tool integrates the synthesized controller with the production cell execution, and in real time, optimizes the strategies by considering the uncertainties. The system can select among several correct, and safe actions, the optimal action using AI-based planning techniques, such as the Monte Carlo Tree Search (MCTS) algorithm. We showcase our tool, illustrate its implementation architecture, including how it can support robot experts for automated planning and execution of production cells.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Ingenieurwesen (sonstige)
- Informatik (insg.)
- Software
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings - ACM/IEEE 25th International Conference on Model Driven Engineering Languages and Systems, MODELS 2022: Companion Proceedings. 2022. S. 37-41.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - A tool for the automation of efficient multi-robot choreography planning and execution
AU - Wete, Eric
AU - Greenyer, Joel
AU - Kudenko, Daniel
AU - Nejdl, Wolfgang
AU - Flegel, Oliver
AU - Eisner, Dennes
PY - 2022/11/9
Y1 - 2022/11/9
N2 - In the automotive industry, the design, modeling, and planning of multi-robot cells are manual error-prone, and time-expensive tasks. A recent work investigated, using reactive synthesis, approaches to automate robot task planning, and execution. In this paper, we present a tool that realizes a model-At-runtime approach. The tool is integrated with a robot simulation tool, to automate efficient multi-robot choreography planning, and execution. We illustrate the tool using a multi-robot spot welding cell, inspired from an industrial case. Given a virtual model of the production cell, and user constraints definition, the tool can derive a specification for the reactive synthesis. The tool integrates the synthesized controller with the production cell execution, and in real time, optimizes the strategies by considering the uncertainties. The system can select among several correct, and safe actions, the optimal action using AI-based planning techniques, such as the Monte Carlo Tree Search (MCTS) algorithm. We showcase our tool, illustrate its implementation architecture, including how it can support robot experts for automated planning and execution of production cells.
AB - In the automotive industry, the design, modeling, and planning of multi-robot cells are manual error-prone, and time-expensive tasks. A recent work investigated, using reactive synthesis, approaches to automate robot task planning, and execution. In this paper, we present a tool that realizes a model-At-runtime approach. The tool is integrated with a robot simulation tool, to automate efficient multi-robot choreography planning, and execution. We illustrate the tool using a multi-robot spot welding cell, inspired from an industrial case. Given a virtual model of the production cell, and user constraints definition, the tool can derive a specification for the reactive synthesis. The tool integrates the synthesized controller with the production cell execution, and in real time, optimizes the strategies by considering the uncertainties. The system can select among several correct, and safe actions, the optimal action using AI-based planning techniques, such as the Monte Carlo Tree Search (MCTS) algorithm. We showcase our tool, illustrate its implementation architecture, including how it can support robot experts for automated planning and execution of production cells.
KW - AI-based optimization
KW - Model-driven engineering
KW - Multi-robot motion planning
KW - Reactive synthesis
KW - Task scheduling
UR - http://www.scopus.com/inward/record.url?scp=85142926314&partnerID=8YFLogxK
U2 - 10.1145/3550356.3559090
DO - 10.1145/3550356.3559090
M3 - Conference contribution
AN - SCOPUS:85142926314
SP - 37
EP - 41
BT - Proceedings - ACM/IEEE 25th International Conference on Model Driven Engineering Languages and Systems, MODELS 2022
T2 - 25th ACM/IEEE International Conference on Model Driven Engineering Languages and Systems, MODELS 2022
Y2 - 23 October 2022 through 28 October 2022
ER -