Senior Researcher
Lakeside Labs, Klagenfurt, Austria
Swarm Algorithms for CPS Applications
.
Dr. Dipl.-Ing. Melanie Schranz
Engineering Swarm Intelligence for CPS Applications
Lakeside Labs, Klagenfurt, Austria
Swarm Algorithms for CPS Applications
Senior Researcher at Lakeside Labs GmbH
Area of responsibility:
Scientific and administrative project management of national and international research projects
Grant applications (KWF, FFG, EU-level)
External Lecturer at University of Klagenfurt
Innovation Manager at UPPERCUT group GmbH
Area of responsibility:
Grant applications, supervision and execution (KWF, AWSG, FFG)
Project management for innovative in-house products
Implementation and establishment of internal innovation culture
PhD in Technical Sciences at University of Klagenfurt
Research and Teaching Staff Member at University of Klagenfurt
Area of responsibility:
Independent teaching at bachelor’s and master’s level
Future-oriented research in the field of intelligent camera systems
Administration, personnel management and organization
Information Technology (master study) at the Alpen-Adria-Universität Klagenfurt
Scientific Assistant at University of Klagenfurt
Area of responsibility:
Support in research and teaching in the field of digital circuits and intelligent camera systems
Successful secured third-party grants (local, national, EU-level)
Additional Trainings:
Swarm Intelligence for CPS Applications
Interconnected devices and the emergence of autonomous cyber-physical systems in dynamic environments show high dynamics that increase the overall system complexity. To handle this complex characteristics, natural systems can serve as inspiration: they have evolved over millennia to master NP-hard problems. In all swarm models, the swarm is made up of many individual, simple, and relatively homogeneous agents. They cooperate without any central control and act according to simple and local behavior. Only through their interactions a collective behavior emerges that is able to solve complex tasks. These characteristics lead to the main advantages of swarms: adaptability, robustness, and scalability.
Modeling and adapting existing swarm intelligence algorithms to cyber-physical systems is a key focus of my research. Therein, additional requirements come from real-world applications including swarms of drones for search and rescue, rovers for logistic, autonomous cars for smart traffic, and machines that need to be scheduled for a production plant.
Ongoing projects:
Successfully completed projects:
Coordination and Control
Algorithms for Sensor Networks
In wireless sensor networks (WSNs), cooperative control and distributed processing opened up a wide research field. WSNs are constituted of spatially distributed sensor nodes to retrieve information from the environment and react on it. The individual sensor nodes in such a network communicate wirelessly and their actions are also autonomous with respect to the received information. Furthermore, the individual sensor nodes in a WSN are able to learn from its environment especially through exchanging locally retrieved information among themselves. A typical characteristic of sensor nodes used in an adhoc WSN are the limited resources. They are usually battery powered, have a bounded communication range and limited on-board processing and storage capabilities. Throughout my research, I consider only networks consisting of visual sensors communicating wirelessly. Visual sensor networks (VSNs) with overlapping field of views consist of autonomous low-power image sensors with storage and communication capabilities as well as a processing unit on board. Thus, they have the ability to analyze and process the data locally. A typical task of a VSN is to identify and track objects for surveillance and identification applications.
In my research utilized by the market-based approach, I perform dynamic cluster management including cluster head election and handover. With evaluations in a simulation environment we show the advantages in terms of resource awareness of the proposed cluster-based protocol over the fully distributed approach. Different state estimation algorithm enrich both approaches. This research was done during my PhD and goes on in several papers appearing ongoingly.
Modeling and Simulation
Modeling and simulation of swarm intelligence for cyber-physical systems are the main key points to analyze and evaluate self-organization behavior and its properties. Therefore, we use different simulators that are able to abstract different levels of cyber-physical systems’ details, including Gazebo and ARGoS. Beside analysis they offer us the possibility to deploy the generated code in ROS directly on our hardware platforms.
For evaluating control and coordination aspects in autonomous VSNs no convenient simulation framework is available. We established a new simulator for the evaluation of control and coordination strategies using the game engine Unity. The VSNsim provides a user friendly 3D environment for evaluations before implementing the algorithms on a real camera network. The current version of the simulator models multiple cameras (static and mobile) with parallel execution behavior in a pseudo-realistic environment with multiple GUI elements (including moving objects to track). Such an evaluation environment motivates researchers to encourage their creativity in designing various scenarios and thus, analyzing different behavior of their algorithms.
Since 10/2016 Michael Gruber and me started to work further on module-based simulation of multi-sensor systems/ production plants. This was the initial step to found a company in 02/2018 by Michael Gruber (http://sensolligent.com/).
Journals, Conference Papers and Book Chapters
Melanie Schranz and Bernhard Rinner, Consensus in Visual Sensor Networks Consisting of Calibrated and Uncalibrated Cameras. In Proceedings of the 6th International Conference on Distributed Smart Cameras, pp. 1-2, Hong Kong, China, 2012.
Melanie Schranz und Wilfried Elmenreich, Approach for a Reliable Cooperative Relaying Process. In Proceedings of the Junior Scientist Conference, pp. 1-2, Technische Universität Wien, 2008.
videos and interviews
talks, panel discussions, interviews
bachelor and master program
Grundlagenlabor: Pervasive Computing (bachelor study
Informationstechnik, 2 SWS, Alpen-Adria-Universität Klagenfurt)
In-depth course for VHDL programming
ICT-Lab: Pervasive Computing (master study
Information Technology, 2 SWS, Alpen-Adria-Universität Klagenfurt)
In-depth course for VHDL programming
Entwurf digitaler Schaltungen (bachelor study Informationstechnik, 2 SWS, Alpen-Adria-Universität Klagenfurt)
Introductory course for Boolean algebra, design of digital circuits and VHDL programming
Digital Signal Processors (master study
Information Technology, 2 SWS, Alpen-Adria-Universität Klagenfurt)
In-depth course for handling digital signal processors applying C and assembler programming
Regular representative for the lectures Entwurf digitaler Schaltungen, Sensor Networks und Digital Signal Processors (bachelor and master studies Information Technology, Alpen-Adria-Universität Klagenfurt)
stay in contact
I am continuously searching for new contacts to industry and research! The high combination of both sectors paths the way to success stories!
For more information, please contact:
schranz@lakeside-labs.com