Research Retreat 2023

17.04.2023 -

Our research retreat took place from 17 to 18 April in Thale. 





more ...

Best Paper Award at EvoStar 2023

13.04.2023 -

Our paper 

  • Julia Reuter, Hani Elmestikawy, Sanaz Mostaghim, Fabien Evrard and Berend van Wachem
  • Graph Networks as Inductive Bias for Genetic Programming: Symbolic Models for Particle-Laden Flows
  • In: Pappa, G., Giacobini, M., Vasicek, Z. (eds) Genetic Programming. EuroGP 2023. Lecture Notes in Computer Science, vol 13986. Springer, Cham.

received the best paper award at the EuroGP conference, which took place in Brno, Czech Republic, 12-14 April 2023. 


Tobias also received the best student poster award at the same conference: 



more ...

Simon's PhD Defense

28.03.2023 -

Simon Anderer successfully defended his PhD with the title:

Role Mining for Industrial-strength ERP Systems Using Evolutionary Algorithms




more ...

New DFG Project

01.03.2023 -

 A new DFG project which is jointly financed by the Austrian Science Fund (FWF) has been approved. We will collaborate with the Johannes Kepler University in Linz and the German Aerospace Center (DLR) in Oberpfaffenhofen. The goal of the project is the use of autonomous drone swarms for rescue applications. Here, drones can imitate the swarming behavior of birds to always have an optimal view for rescue purposes. 

Considering the current high level of attention that is being paid to drones, it is easy to overlook the enormous potential that they bring with them in civilian areas. Drone groups are establishing themselves worldwide in blue light organizations such as the police, fire brigade and mountain rescue to use this technology to save human lives. Search and rescue operations benefit, among other things, from the flexible, fast and - compared to helicopters - inexpensive and safe use of drones. They are also used in the inspection of disaster areas, for the early detection of forest fires, for border security, or wildlife observation. The problem with all these applications is always the occlusion caused by vegetation, such as forest, which usually makes it impossible to find, detect, and track people, animals or vehicles in single aerial photographs. This project is based on the "Airborne Optical Sectioning" (AOS) imaging method developed at the Johannes Kepler University and will study further potentials of the swarms. 


more ...

PhD Defense Jens Weise

06.02.2023 -

On 6th February, Jens Weise successfully defended his PhD with the title "Evolutionary Many-Objective Optimisation for Pathfinding Problems":


more ...

Keynote talk of Prof. Deb

06.02.2023 -

On Monday 6th February, Prof. Kalyanmoy Deb from Michigan State University gave a University Guest lecture with the Title "Evolutionary Multi-Criterion Optimization: An Emerging Computational Problem-Solving Tool". Over 100 participants attended the talk.



Picture Left to right: Prof. Sanaz Mostaghim, Prof. Jens Strackeljan (President of the University), Prof. Kalyanmoy Deb, Prof. Hans-Knud Arndt (Dean of the Faculty of Computer Science), Prof. Pascal Kerschke (TU Dresden). 

Abstract: Most problems in science, engineering and commerce involve more than one conflicting criteria to be simultaneously optimized. Despite the vast literature on scalarizing multiple criteria into one, evolutionary optimization methods of treating them as truly multi-criterion problems in a Pareto sense produce a number of additional benefits to the users. Their ability to find and maintain multiple trade-off solutions with a flexible and customizable framework provides vital knowledge about the problem in addition to the optimal solutions themselves. In this lecture, we shall present a few popular and state-of-the-art algorithms, demonstrate their advantages on a number of real-world practical problems from engineering and society, and introduce some recent research topics. Additionally, the use of machine learning algorithms and human knowledge in enhancing their performance, and the use of multi-criterion algorithms in enhancing performance of machine learning methods will be discussed.


Bio-sketch: Kalyanmoy Deb is University Distinguished Professor and Koenig Endowed Chair Professor at Department of Electrical and Computer Engineering in Michigan State University, USA. Prof. Deb's research interests are in evolutionary optimization and their application in multi-criterion optimization, modeling, and machine learning. He is and has been a visiting professor at various universities across the world including University of Skövde in Sweden, Aalto University in Finland, Nanyang Technological University in Singapore, and IITs in India. He was awarded IEEE Evolutionary Computation Pioneer Award for his sustained work in multi-objective optimization, Infosys Prize, TWAS Prize in Engineering Sciences, CajAstur Mamdani Prize, Distinguished Alumni Award from IIT Kharagpur, Edgeworth-Pareto award, Bhatnagar Prize in Engineering Sciences, and Bessel Research award from Germany. He is fellow of ACM, IEEE, and ASME. He has published over 600 research papers with Google Scholar citation of almost 180,000 with h-index 129. More information about his research contribution can be found from


more ...

Xenija's PhD

06.02.2023 -

Xenija Neufeld had successfully defended her PhD in December 2020. Due to COVID we could not give her PhD hat, which we finally did 2 years later :-)





more ...

SDW visits SwarmLab

17.01.2023 -

On 17th January, the students and the trusties (VertrauendozentInnen) of the SDW (Stiftung der Deutschen Wirtschaft) visited SwarmLab. Sanaz is acting as a trusty (Vertrauendozentin) of SDW since 2018. 




more ...

Hall of Femmes

04.10.2022 -

Delighted to be part of the "Hall of Femmes" at the Paderborn University:


more ...

New Project AULA-KI

01.10.2022 -


Adaptive Umgebungsabhängige Lokalisierung von autonomen Fahrzeugen durch Methoden der künstlichen Intelligenz.

On first of October, the project associated with our AI young scientist group founded by the BMBF started.


The project aims to create the foundation towards a new AI-group composed of researches at the OvGU and the ifak e.V. focussing on developing, extending and applying AI-Methods for industrial scenarios. This first project aims to solve the problem of degraded sensor quality in autonomous cars in harsh weather conditions. To this end, methods will be developed to detect these weather events, communicate them to specialized decision components and mitigate them. This will provide means towards a more robust localization information and thus more robust behavior of autonomous cars.

more ...

Sanaz as a member of DigitalRat

19.05.2022 -

Sanaz has been appointed as a member of the Digitalization advisory board "DigitalRat" of the state of Saxony-Anhalt:



MID/Foto: Viktoria Kühne


more ...

Guest Lecture

19.09.2022 -

Finally the first in person lecture took place at our chair. Professor Sperduti (Padova University, Italy) gave a talk on "An Introduction to Graph Neural Networks".

2022-09-20-Vortrag-Sperduti copy


more ...

RoboCup Team got the 2nd Place at WorldCup in Thailand

01.08.2022 -

RoboCup Team got the second place at the worldcup in Bangkok, Thailand:



Diesjährige Wettkampferfolge des Team robOTTO der Otto-von Guericke-Universität Magdeburg

Am 28. und 29.07.2022 fanden neben den MINT Mach-Aktionstage der Landeshauptstadt Magdeburg in der Festung Mark die GermanOpen (Europameisterschaft) der RoboCup@Work-Liga statt. Sieben RoboCup-Teams u.a. aus Deutschland und Österreich ließen ihre Roboter im freundschaftlichen Wettkampf gegeneinander antreten. Organisiert wurde die Veranstaltung in diesem Jahr vom Team robOTTO der Otto-von Guericke-Universität Magdeburg. Besonderes Highlight stellte das Veranstaltungsformat dar, welches in diesem Jahr sowohl in Präsenz als auch in digitaler Form durchgeführt wurde. So nahm zum Beispiel das griechische RoboCup-Team DIR digital an der Veranstaltung teil, indem Sie ihre Läufe in einer eigenen Wettkampfarena streamten. Die Schiedsrichter bewerteten sodann aus der Fern die erledigten Aufgaben. Innerhalb der fünf anwesenden Teams erreichte das Team robOTTO den dritten Platz.

Die GermanOpen stellten auch in diesem Jahr für viele europäischen Teams eine Generalprobe für die einige Wochen später stattfindende Weltmeisterschaft – dem RoboCup dar. In diesem Jahr fand dieser bereits zwei Wochen nach den GermanOpen vom 11. – 17.07. 2022 in Bangkok (Thailand) statt. 

Das Team der Otto-von-Guericke-Universität reiste mit insgesamt sieben Teammitglieder:innen und ihrem Roboter „Euler“ nach Bangkok. Die Zeit zwischen den Wettkämpfen wurde vom Team intensiv genutzt um Soft- und Hardware-Bugs zu fixen. Die harte Vorbereitung sollte sich in einem spannenden Kopf-an-Kopf-Rennen im Finale in Bangkok auszahlen. So errang das Team stolz den Vizeweltmeister-Titel und setzte seine Erfolge der letzten Jahre fort. Es zweigte sich deutlich, dass sich das Team vor allem softwaretechnisch gegen die Konkurrenz durchsetzen konnte. Ziel für die nächste Wettkampfsaison ist die Optimierung der Hardware des Roboters, um, so hoffte das Team, bei der Weltmeisterschaft 2023 in Bordeaux (Frankreich) den Weltmeistertitel mit nach Hause zu bringen.

Neben der jahrelangen erfolgreichen Teilnahme am RoboCup, hat das Team robOTTO eine tragende Rolle in der RoboCup@Work-Liga. So sind die Teammitglieder:innen in verschieden Rollen sowohl auf nationaler als auch internationaler Ebene an der Organisation der RoboCup-Wettkämpfe beteiligt, vertreten die Co-Leitung der Liga und sind darüber hinaus auch an der Weiterentwicklung der Regeln und der Liga selbst beteiligt.

Das Team robOTTO ist interdisziplinär aufgestellt und gibt den Studierenden aller Fakultäten die Möglichkeit an und mit Robotern zu arbeiten. Ziel ist es dabei die Leidenschaft für die Robotik aufleben zu lassen und für Skills auf- und auszubauen, die in der Arbeitswelt gefragt sind. In diesem Rahmen bietet das Team den Studierenden der Otto-von-Guericke-Universität Magdeburg an nachhaltige Forschungs-, Bachelor- und Masterarbeiten sowie Softwareprojekte umzusetzen.

Interessenten können gern über Kontakt mit dem Team aufnehmen.



more ...

New DFG Project

23.08.2022 -

We will start a new DFG project "Optimization of Gas-Solid Fluidized Beds Operation using Machine Learning" in collaboration with Prof. Berend vam Wachem Chair of Mechanical Process Engineering at OVGU.

Fluidized beds are the basis for scores of applications in which fast mixing, heat and mass transfer of gas and solid particles are essential. Their performance largely relies on the bubble dynamics: rising bubbles drive the solids circulation and significantly enhance gas-solids contact, improving mixing, reactions, and transport properties. So far, almost all fluidized beds are operated with a uniform gas flow. However, some recent academic work shows that operating a fluidized bed with an alternating gas flow (e.g. sinusoidal gas fluidisation velocity) leads to different bubble patterns and dynamics. In this project, we aim to control the bubbles in a fluidized bed, by application of computational intelligence (CI) methodologies such as evolutionary algorithms and genetic programming. We will use our lab-scale fluidized bed with camera system and our model developments in the Eulerian-Eulerian and Eulerian-Lagrangian frameworks to capture the dynamics of bubbles in the fluidized bed as the fluidizing gas velocity is spatio-temporally varied. Firstly, these results will be used to find the optimal inflow-pattern for given target functions. The challenge for the CI algorithm is to find the right balance between the computationally and timely intensive experimental data and the simulation data to efficiently deliver the required fluidization velocity profile. In addition, we aim to address multiple conflicting target functions using multi-objective optimization algorithms. Secondly, the CI algorithm will be used to steer and control the velocity profile, to obtain a specified bubble size and dynamics. Being able to control the behavior of the bubbles in a fluidized bed will significantly improve the desired outcome, such as product quality, efficiency and selectivity of the process, to name a few.

more ...

New BMBF Project

01.07.2022 -

On first of July, we started a new project funded by BMBF: 

6G-ANNA: 6G Access, Network of Networks, Automation

In 6G-ANNA-MOEVE werden wir multi-kriterielle Optimierung und Entscheidungsfindungsalgorithmen sowie Methoden für verteiltes Lernen entwickeln. Die multi-kriteriellen Optimierungsprobleme haben mehrere Zielfunktionen, die gleichzeitig optimiert werden müssen. Ein Beispiel für solche hochkomplexe Probleme ist die Minimierung des Energieverbrauchs im Netz bei gleichzeitiger Sicherstellung von Ende- zu-Ende Performanz (Durchsatz, Latenz und Zuverlässigkeit). Die Lösung solcher Probleme ist eine Menge optimaler Alternativen, auf dieser Entscheidungsgrundlage kann der Anwender gemäß seinen Präferenzen die für ihn beste Lösung auswählen. Das gibt dem Anwender ein hohes Maß an Flexibilität in der Entscheidung, was zur Nachhaltigkeit der Lösungen beiträgt.

Für eine Echtzeitoptimierung werden wir digitale Zwillinge (Simulationen) entwickeln. Allerdings spiegeln Simulationen die Realität nicht perfekt wider. Daher sollen hier Methoden entwickelt werden, die eine effiziente Kombination von Offline- (Simulationsbasierte-) und Echtzeitoptimierung bieten. Eine mögliche Lösung für Echtzeitoptimierung kann durch verteilte Optimierung auf lokaler Ebene stattfinden. Parallelisierung bzw. die dezentrale Ausführung von Optimierungsalgorithmen ist ein komplexes Problem und hat viele Herausforderungen, u.a. Konvergenz zu lokalem Optimum und Mobilität der Knoten.

Bei der Entwicklung der Entscheidungsfindungsalgorithmen werden wir den Anwender in den Vordergrund stellen und dabei eine technische Unterstützung durch KI-Algorithmen anbieten. Ein Ziel des Projekts ist, dass durch die Interaktion zwischen Menschen und Maschine die nicht maschinenlesbaren Präferenzen der Anwender von Algorithmen verstanden werden, was wir „reverse explainability“ von Entscheidungsfindung nennen. Diese findet in „Collaborative Spaces“ Anwendung, die sich auf die Mensch-Maschine Interaktion, z.B. die Zusammenarbeit von Robotern und Menschen in der industriellen Produktion, fokussieren.


more ...

CI-Organized RoboCup @Work German Open


Start of German Open 2022 at Festung Mark


The AG CI organized this year's German Open of the @Work League. The setup day ended today and there was already some action going on. The next two days are filled with competition runs. For more information, please visit the Instagram of the robOTTO Team.

more ...

RoboCup Team Recogtion at the City Hall

27.04.2022 -

Our RoboCup Team got the third place at the WorldCup 2021. This was recognized by the Mayor of the City Magdeburg, Dr. Trümper, who asked the team to sign in the golden book of the city. 





more ...

New Edition of the Computational Intelligence Textbook

06.04.2022 -

The third edition of the Computational Intelligence Textbook is published: 

More information can be found on Springer:

Or here:




more ...

Sanaz as a new member of Saxon Academy of Sciences


Sanaz has been appointed to be a new member of Saxon Academy of Sciences (Sächsische Akademie der Wissenschaften - SAW). More information about SAW taken from the webpage of SAW "It is founded in 1846 under the name of Royal Saxon Society for the Sciences, the Saxon Academy of Sciences and Humanities. ... More than 200 scientists of all disciplines meet regularly to exchange views, examine methods and results of specialist studies in interdisciplinary discussion and engage in long-term basic research."


more ...

Last Modification: 07.12.2023 - Contact Person: Webmaster