Reseach topics 2019

We actively seek for a cooperation with students at all levels of their studies. Come and join us to work on challenging, real-life oriented problems. We offer to students various research topics for their thesis and projects. Some of them are more industry orientated (i.e. working on a task required by some of our industry partners, solving their real-life problem), others are more theoretical (i.e. focusing on developing new fundamental algorithms and theory).

In the list below you can see a short description and motivation for solving the problem/project. After the student chooses the area of his/her work, the topic is more deeply specified. If you still hesitate, just make an appointment with sojkam1atfel [dot] cvut [dot] cz (Michal Sojka) (@wentasah) or Přemysl Šůcha (suchapatfel [dot] cvut [dot] cz) and come to see what we are working on.

EATON Lab projects

EATON offers a large number of industrial projects related to embeded devices that will be applied to modern manufacturing facilities. Find out more here.

Mixed-reality with Microsoft Hololens

Join us on a project for developing new applications for mixed-reality headset Microsoft Hololens. Applications (interactive holograms) are programmed in Unity 3D engine that runs an on-board computer. The target application will help human operators to interact with production machines and HMI panels manufactured by EATON company. The work is done in cooperation with EATON Lab.

Machine learning for energy consumption analysis

Noninvasive sensors such as a sensor of the electrical current is an elegant way how to improve observability in a production environment. However, signals from these sensors may be difficult to understand and analyze. To address this, we work on machine learning algorithms to compute uptime of the machines, their mode and time needed to perform the given operations. We collect a large stream of data from the production shopfloor into our data cluster that needs to be automatically labeled and processed by advance machine learning algorithms.

Energy consumption optimization of robotic cells

The fourth industrial revolution is a term for a new way of designing, realizing and controlling modern (smart) factories. One of the principles of this “revolution” is virtualization of plants which is supposed to allow efficiently design future smart factories. The aim of the thesis is to design and implement an algorithm for optimizing energy consumption of robotic cells (see the figure) using a virtual model constructed in Siemens Process Simulate.

Autonomous model car F1/10

Self-driving cars are future of public transportation and a lot of skilled engineers will be needed to make this technology safe and reliable. This topic could be your entry to this future world. The goal is to improve the algorithms in our current car and participate in F1/10 challenge with that car. In addition to that, we collaborate with industrial partners on the development of real autonomous cars and the techniques developed here may be ported into real cars.

Use of deep learning techniques for solving combinatorial problems

The Deep Neural Networks (DNNs) are powerful models used mostly in the machine learning domain. Nevertheless, a recent research done by Google has shown that DNNs can also help to solve combinatorial problems. The aim of this thesis is to propose an exact algorithm for solving a simple scheduling, i.e. a combinatorial problem where a deep neural network is helping to search the solution space of the scheduling problem.

Integrate project and manpower scheduling

In a collaboration with Gent University in Belgium, we propose a topic addressing scheduling of complex projects (e.g. construction of building complexes). This problem assumes not only allocation of the project activities but also scheduling of human resources necessary to realize the project. The objective is to develop a scheduling algorithm for this bilevel optimization problem.

Production scheduling

Would you like to solve practical and challenging problems faced by companies such as SKODA, Proctor&Gamble and EATON? Then production scheduling is a right topic for you. The task is to study a given production scheduling problem and implement an efficient algorithm for it. Depending on the specific setting, different objectives and constraints have to be considered, e.g. smoothing of the energy consumption, rescheduling due to unexpected disturbances, etc. To evaluate the proposed algorithms, we use an industry-proven simulation and visualization tool Plant Simulation which is developed by Siemens.

Parallel algorithm for combinatorial problems

Combinatorial optimization is not only a mathematical domain but it also plays an important role in many applied areas like logistics, project management, production, communication, etc. However, for many real-world combinatorial problems, the solution search trees become unmanageably large. One way how to mitigate this problem is to use of parallel algorithms. Therefore, the topic addresses development an efficient parallel (GPU) algorithm for solving a real-world combinatorial problem.

Fundamental research in scheduling & open problems

Sometimes, even the fastest computers are not able to solve the given combinatorial problems in a reasonable time. This does not necessarily mean that these problems are impossible to solve, but a deeper theoretical understanding of the problem is required to implement efficient algorithms. The task of this topic is to study fundamental properties of the given scheduling problem and implement efficient algorithms that exploit these properties (we recommend this topic to more mathematically-inclined students).

Reliable hardware for autonomous cars

Future self-driving cars will require not only tremendous computational power for processing data in real-time but also increased reliability and fault-tolerance. While sufficient performance is easily provided by modern hardware, the reliability of such hardware is not considered in "automotive-grade". This topic addresses the challenge of increasing the reliability and determinism of Xilinx UltraSCALE platform, used by our industrial partners in their autonomous cars, by implementing so-called "Predictable Execution Model" on this platform and improving it by using new hardware features of the platform.

Scheduling of the Time-Triggered communication on Deterministic Ethernet

The Ethernet technology is one of the most widespread technology in the world. Nowadays, the network has the usage even in the areas where it was not intended. It becomes more and more common even in highly critical applications, where any failure can cause jeopardy of life, because of the increasing bandwidth demands of e.g. autonomous driving systems. The car or airplane manufacturers endeavor to modify the Ethernet protocol to be also capable of the deterministic and hard real-time communication - TTEthernet, 802.1Qbv, 802.1Qbu and 802.3br. In such a time-triggered Ethernet standards, the communication follows a schedule known in advance. Design and development of an algorithm, which is able to create efficient schedules, is the main objective of this diploma thesis topic.



Industrial Informatics Research Center leads the Computer Engineering study branch of popular study program Open Informatics at the Faculty of Electrical Engineering of CTU in Prague. For more information check out the site for Computer Engineering [in Czech]

IIRC secures a number of undergraduate and graduate courses. See the links below.