INTEGRATION OF A PHYSICAL SYSTEM, MACHINE LEARNING, SIMULATION,
VALIDATION AND CONTROL SYSTEMS TOWARDS SYMBIOTIC MODEL
ENGINEERING
Sebastian Bohlmann
Institute of Applied Mathematics
Gottfried Wilhelm Leibniz University Hannover
Welfengarten 1
D-30167 Hannover, Germany
bohlmann@ifam.uni-hannover.de
Volkhard Klinger
Department of Embedded Systems
and Information Engineering
FHDW Hannover
Freundallee 15
D-30173 Hannover, Germany
volkhard.klinger@fhdw.de
Helena Szczerbicka
Department of Simulation and Modelling
Gottfried Wilhelm Leibniz University Hannover
Welfengarten 1
D-30167 Hannover, Germany
hsz@sim.uni-hannover.de
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.
Keywords: symbiotic simulation, symbiotic circle, system identification, agent-based evolutionary compu-
tation, memetic optimization algorithms.
SpringSim-MSCIAAS 2017, April 23-26, Virginia Beach, VA, USA
©2017 Society for Modeling & Simulation International (SCS)