Project EVOSOS successfully concluded!

Within the project EVOSOS, we investigated how evolutionary computation can be applied to find the appropriate local rules that provide the desired emergent global behavior for a given system. In particular, we propose a design methodology built on meta-heuristic search that can guides the designer throughout the whole engineering process. Additionally, we investigate the evolvability of self-organizing technical systems via several case studies focusing on the effects of certain design decisions explained in the proposed methodology. First, a self-organizing cellular automata model is described that is evolved to present a desired 2D structure. Using this example the connection between problem complexity and evolvability is discussed.
Two further studies focus on evolutionary swarm robotics. In the first one, we discuss the effects of various interaction interfaces and their effects on the quality of the evolved solutions. We find that seemingly identical interfaces can produce significantly different group behavior. The second experiment investigates how a self-organizing team of soccer robots can be evolved. Here, we study the effects of different agent controller structures and interface interpretation models.
A further outcome of the project is the evolutionary software framework FREVO, which implements the proposed design methodology and thus aids engineers and researchers working with self-organizing systems.

Publications (with link to fulltexts):

• I. Fehervari and W. Elmenreich. Evolution as a tool to design self-organizing systems. In Self-Organizing Systems, volume LNCS 8221, pages 139–144. Springer Verlag, 2014.
• István Fehérvári, On Evolving Self-organizing Technical Systems, PhD Dissertation, Alpen-Adria-Universität Klagenfurt, 2013.
• I. Fehérvári, V. Trianni, and W. Elmenreich. On the effects of the robot configuration on evolving coordinated motion behaviors. In Proceedings of the IEEE Congress on Evolutionary Computation. IEEE, June 2013.
• I. Fehérvári, A. Sobe, and W. Elmenreich. Biologically sound neural networks for embedded systems using OpenCL. In Proceedings of the International Conference on NETworked sYStems (NETYS 2013). Springer Verlag, May 2013.
• R. M. W. Masood, J.Klinglmayr, I. Fehervari, W. Watzl, C. Bettstetter: Demo Abstract: Synchronization using Inhibitory and Excitatory Coupling: From Theory to Practice, in: The 32nd IEEE International Conference on Computer Communications, IEEE, Piscataway (NJ), April 2013.
• I. Fehérvári, W. Elmenreich, and E. Yanmaz. Evolving a team of self-organizing UAVs to address spatial coverage problems. In R. M. Bichler, S. Blachfellner, and W. Hofkirchner, editors, European Meeting on Cybernetics and Systems Research Book of Abstracts, pages 201–204, Vienna, Austria, April 2012.
• A. Sobe, I. Fehérvári, and W. Elmenreich. FREVO: A tool for evolving and evaluating self-organizing systems. In Proceedings of the 1st International Workshop on Evaluation for Self-Adaptive and Self-Organizing Systems, Lyon, France, September 2012.
• W. Elmenreich and I. Fehérvári. Evolving self-organizing cellular automata based on neural network genotypes. In Proceedings of the Fifth International Workshop on Self-Organizing Systems, volume LNCS 6557, pages 16–25. Springer Verlag, 2011.
• I. Fehervari, B. Lenart: Using an Adaptive Neuro-Fuzzy Inference System for Adaptive Inventory Control, in: Proceedings of the International Conference on Innovative Technologies (IN-TECH) 2011, Czech Technical University, Faculty of mechanical engineering, Department of manufacturing technology, Prague, 2011, S. 43 - 48.
• O. Maurhart, W. Elmenreich, I. Fehervari, A. Bouchachia: Evaluation of Robustness and Performance of Environmental Influences on Evolutionary Algorithms compared to Ant Colony Systems, in: European Conference on Complex Systems (ECCS'11 Vienna), Löcker Verlag, Wien, 2011, S. 98 - 99.

Complexity on the workbench

Today’s technical systems contain more and more components which are typically networked and interacting with each other. So, these systems become very complex, which makes it difficult to engineer and maintain the system using traditional, hierarchical approaches.
Looking into complex systems in nature, we see that they are controlled by distributed self-organizing mechanisms that are simple, scalable, robust, and adaptive. However, putting a self-organizing approach into technical systems is not straightforward, because such complex systems are typically hard to predict. A particular change in an interaction mechanism might even have counter-intuitive effects.
In nature, the driving mechanism behind building self-organizing behavior is evolution - why not use the very same method in form of an evolutionary algorithm?
However, there is a need to integrate different tools and models like neural networks, mutation and recombination, and problem-specific simulations. With our tool FREVO we provide a unifying framework to reduce this problem to basically three components: a problem representation, an agent representation and an evolutionary algorithm.
FREVO has been used to solve quite different problems and is available as open source to everyone. It is a very flexible framework open to new components and simulations, thus, we are looking forward to see you testing your ideas with it :-)



This talk was originally given by István Fehérvári at FET 2011 in the science café. This work was supported in part by the Lakeside Labs project MESON (Modeling and Engineering of Self-Organizing Networks) and the Lakeside Labs GmbH.

On Evolving Self-organizing Technical Systems

The trend toward pervasive computing and networked systems has led to increased complexity and dynamics of today’s technical systems. Thus, future systems are expected to be even more complex requiring novel ways to handle such complex networked systems. One approach to solve this problem is to increase the level of self-organization in those systems. Self-organizing systems offer numerous advantages over traditional ones like robustness against a failure of a component and scalability but due to the distributed structure there is no straightforward way to design a self-organizing system.

Within the project EVOSOS, we investigated how evolutionary computation can be applied to find the appropriate local rules that provide the desired emergent global behavior for a given system. In particular, we propose a design methodology built on meta-heuristic search that can guides the designer throughout the whole engineering process. Additionally, we investigate the evolvability of self-organizing technical systems via several case studies focusing on the effects of certain design decisions explained in the proposed methodology. First, a self-organizing cellular automata model is described that is evolved to present a desired 2D structure. Using this example the connection between problem complexity and evolvability is discussed.

Two further studies focus on evolutionary swarm robotics. In the first one, we discuss the effects of various interaction interfaces and their effects on the quality of the evolved solutions. We find that seemingly identical interfaces can produce significantly different group behavior. The second experiment investigates how a self-organizing team of soccer robots can be evolved. Here, we study the effects of different agent controller structures and interface interpretation models.

István Fehérvári, On Evolving Self-organizing Technical Systems, PhD Dissertation, Alpen-Adria-Universität Klagenfurt, 2013. (fulltext-pdf)

FREVO presented at SASO'12, Lyon

Anita Sobe and Istvan Fehervari are currently at the SASO 2012 in Lyon, the main conference on self-organizing and self-adaptive systems, with approximately 100 attendees. The topics of the talks are very wide spread and therefore the attendees and speakers come from different fields where they apply and analyze various SASO systems.

The first day we attendted the Workshop EVAL4SASO, a special session dedicated for the problem of evaluating such complex SASO systems. Here, we presented our paper:

A. Sobe, I. Fehervari, W. Elmenreich

FREVO: A Tool for Evolving and Evaluating Self-organizing Systems

In IEEE SASO Workshop Eval4SASO, Lyon, France, September 2012

It presents a generic evolutionary framework for rapid prototyping and evaluating research ideas on the design and behavior of evolved complex systems. To illustrate its capabilities, we demonstrated a short demo on a sample problem of dynamic pricing in smart microgrids. FREVO is easy to use and we hope it will assist many researchers and engineers. For further details and downloads, see:

http://frevo.sourceforge.net/

The initial feedback we obtained on the conference was very promising, opening many new possibilities for further joint work in this field. 

To see what is possible with this tool, please check this interesting video on evolving a team of robots playing soccer:

Evolving a team of self-organizing UAVs to address spatial coverage problems

An example for engineering a distributed algorithm using evolutionary methods was presented at the European Meeting on Cybernetics and Systems Research (EMCSR 2012). The task was to evolve a distributed control algorithm for flying UAV drones to cover an area. The problem of having multiple mobile agents covering (or as we say in robotics, "sweeping") an area is relevant for many applications like lawn mowing, snow removal, floor cleaning, environmental monitoring, communication assistance and several military and security applications. The work by Istvan Fehervari, Wilfried Elmenreich and Evsen Yanmaz describes a simple grid-based abstraction of the problem which was used to test two evolved and one handcrafted control algorithm in comparison to reference algorithms like random walk and random direction.

 Slides (via slideshare):

I. Fehérvári, W. Elmenreich, and E. Yanmaz. Evolving a team of self-organizing UAVs to address spatial coverage problems. In R. M. Bichler, S. Blachfellner, and W. Hofkirchner, editors, European Meeting on Cybernetics and Systems Research Book of Abstracts (ISSN: 2227-7803), Vienna, Austria, April 2012.

Evolving self-organizing systems - complexity on the workbench

This talk was given by István Fehérvári at FET 2011 in the science café. The tool presented in the talk, FREVO , is a flexible framework open to new components and simulations. It is available as open source at http://www.frevotool.tk.

Heading for the European Conference on Complex Systems (ECCS 2012) in Vienna

The European Conference on Complex Systems (ECCS 2012) is an event bringing together 600 researchers in the area of complex and self-organizing systems. Two of them are István and me, presenting our poster on a comparison of evolutionary and ant colonization algorithms.

We are looking forward to an interesting conference, see the program at ECCS'12 website.
The conference runs from September 12 to 16. Our presentation is on Friday, by the way :-)