Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Simulation Series |
| Herausgeber/-innen | Saurabh Mittal, Jose Luis Risco Martin |
| Seiten | 13-24 |
| Seitenumfang | 12 |
| Auflage | 8 |
| ISBN (elektronisch) | 9781510840300 |
| Publikationsstatus | Veröffentlicht - Apr. 2017 |
| Veranstaltung | 2nd Symposium on Modeling and Simulation of Complexity in Intelligent, Adaptive and Autonomous Systems 2017, MSCIAAS 2017, Part of the 2017 Spring Simulation Multi-Conference, SpringSim 2017 - Virginia Beach, USA / Vereinigte Staaten Dauer: 23 Apr. 2017 → 26 Apr. 2017 |
Publikationsreihe
| Name | Simulation Series |
|---|---|
| Nummer | 8 |
| Band | 49 |
| ISSN (Print) | 0735-9276 |
Abstract
System simulation without detailed prior knowledge or data of the system is a complex challenge. In this paper we present an approach to automatically generate a model on the fly in a symbiotic way. Basically the data based model generation system introduced is an agent based evolutionary optimization system creating continuous differential equations from simple predefined operators. The well known paradigm of symbiotic simulation is then enhanced with this agent based machine learning system. Here we focus on the emergent behavior of the model generation system resulting from the interaction of multiple agents optimizing a common model and the effects arising from the direct coupling and steering of the connected physical system. Different emergent mechanisms and effects can be observed speeding up the model generation process. To measure and evaluate this effects multiple experiments with a robotic system are discussed.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Computernetzwerke und -kommunikation
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Simulation Series. Hrsg. / Saurabh Mittal; Jose Luis Risco Martin. 8. Aufl. 2017. S. 13-24 2 (Simulation Series; Band 49, Nr. 8).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Integration of a physical system, machine learning, simulation, validation and control systems towards symbiotic model engineering
AU - Bohlmann, Sebastian
AU - Klinger, Volkhard
AU - Szczerbicka, Helena
PY - 2017/4
Y1 - 2017/4
N2 - System simulation without detailed prior knowledge or data of the system is a complex challenge. In this paper we present an approach to automatically generate a model on the fly in a symbiotic way. Basically the data based model generation system introduced is an agent based evolutionary optimization system creating continuous differential equations from simple predefined operators. The well known paradigm of symbiotic simulation is then enhanced with this agent based machine learning system. Here we focus on the emergent behavior of the model generation system resulting from the interaction of multiple agents optimizing a common model and the effects arising from the direct coupling and steering of the connected physical system. Different emergent mechanisms and effects can be observed speeding up the model generation process. To measure and evaluate this effects multiple experiments with a robotic system are discussed.
AB - System simulation without detailed prior knowledge or data of the system is a complex challenge. In this paper we present an approach to automatically generate a model on the fly in a symbiotic way. Basically the data based model generation system introduced is an agent based evolutionary optimization system creating continuous differential equations from simple predefined operators. The well known paradigm of symbiotic simulation is then enhanced with this agent based machine learning system. Here we focus on the emergent behavior of the model generation system resulting from the interaction of multiple agents optimizing a common model and the effects arising from the direct coupling and steering of the connected physical system. Different emergent mechanisms and effects can be observed speeding up the model generation process. To measure and evaluate this effects multiple experiments with a robotic system are discussed.
KW - Agent-based evolutionary computation
KW - Memetic optimization algorithms
KW - Symbiotic circle
KW - Symbiotic simulation
KW - System identification
UR - http://www.scopus.com/inward/record.url?scp=85020620054&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85020620054
T3 - Simulation Series
SP - 13
EP - 24
BT - Simulation Series
A2 - Mittal, Saurabh
A2 - Martin, Jose Luis Risco
T2 - 2nd Symposium on Modeling and Simulation of Complexity in Intelligent, Adaptive and Autonomous Systems 2017, MSCIAAS 2017, Part of the 2017 Spring Simulation Multi-Conference, SpringSim 2017
Y2 - 23 April 2017 through 26 April 2017
ER -