prof. Ing. Ivan Křupka, Ph.D.

1. Analysis and prediction of local DNA structures.

   Working on a given topic represents DNA sequence analysis with focus on large volumes of data that will include required algorithms for prediction of structures like triplexes, quadruplexes and for protein motifs analyses with reporting and visualization tools. Proposed software will be implemented as a web service and will be used for characterization and evaluation of the local DNA structures in DNA sequences with the focus to possibility to analyse whole genomes and different local DNA structures.

   Tutor: Šťastný Jiří, prof. RNDr. Ing., CSc.

2. Analysis of local DNA structures

   The project assumes the design and implementation of original algorithms for the analysis of local DNA structures. The proposed algorithms will be implemented as a web service and will be available online for public use.

   Tutor: Šťastný Jiří, prof. RNDr. Ing., CSc.

3. Autonomous mobile platform for cooperative industrial robots

   The thesis presents complex development of autonomous omnidirectional mobile robotic platform designed for applications of cooperating industrial robots. The platform's autonomy and semi-autonomy will be based on the implementation of machine vision, artificial intelligence and security protocols. The primary focus will be for the cooperative robot UR3 and ABB IRB YuMi.

   Tutor: Matoušek Radomil, prof. Ing., Ph.D.

4. Distributed optimazation systems

   The distributed approach is the current trend in many areas of computer applications, in communications, databases, calculations, control applications, and many others. For all these areas, optimization is an important part of their implementation. Distributed Optimization Approach allows to customize the structure of solved optimization tasks to real-world conditions where sub-optimization can be performed at lower levels to interact with other sub-optimizations that will contribute to the overall result.

   Tutor: Roupec Jan, doc. Ing., Ph.D.

5. Modelling of population evacuation in risk zones

   With the development of industry and the construction of large units, the potential danger to the population from accidents increases. Linked to this is the need to develop plans to evacuate the population in disaster-stricken areas. In general, two cases can be distinguished where a sufficient number of means of transport must be available to evacuate all residents in the shortest possible time for evacuation; in a less critical case, the population can be gradually withdrawn with small amount of resources. The aim of this work is to model transport operations during evacuation and minimize its completion taking into account all restrictive conditions in relation to the area and the level of risk, such as population density, number and capacity of means of transport, distance of collection points etc.

   Tutor: Šeda Miloš, prof. RNDr. Ing., Ph.D.

6. Multiparametric diagnostics of traction components

   The topic of the dissertation thesis is focused on the introduction of modern methods of multiparametric diagnostics (vibrodiagnostics, electrodiagnostics, tribodiagnostics, thermodiagnostics, etc.) in the testing of traction components (bogies, engines, generators) for diesel-electric locomotives. Implementation of methods of multiparametric diagnostics and design of intelligent evaluation of traction equipment tests using machine and deep learning (artificial intelligence) within the Industrial Internet of Things (IoT) will provide an objective assessment of the technical state of individual traction components. The introduction of diagnostics in the test rooms will contribute to the detection of faults and the assessment of the condition prior to the installation of the components into the locomotive assembly and to the utilization stated during the lifetime of the locomotives. The main goal is to extend the service life and increase the reliability of locomotives. The dissertation will be practically verified in a selected company, which deals with testing of components and production of locomotives.

   Tutor: Hammer Miloš, doc. Ing., CSc.

7. Optimisation of Serviceability in Network Applications

   In applications that serve locations deployed in a large area for certain customer service, it is a typical task to minimise these locations so that each customer has at least one of the centers at the available distance. The problem of coverage for this task has O (2 ^ n) complexity, where n is the number of given places and it is necessary to solve it by heuristic methods for the "large" instances of the problem. However, the task has even more complex formulations considering service capacities and customer requirements. In the dissertation the aim is to apply a general problem solving in the problems of communication of 5G mobile networks and data storage in NoSQL databases.

   Tutor: Šeda Miloš, prof. RNDr. Ing., Ph.D.

8. Optimization metaheuristics and HPC implementation

   Many optimization problems linked to real problems exhibit nonlinearities, multimodality, complexity, and various complicated constraints. Metaheuristic optimization deals with optimization problems using selected artificial intelligence algorithms. The aim of the research is to study and design algorithms suitable for solving so-called NP difficult tasks, incl. HPC implementation.

   Tutor: Matoušek Radomil, prof. Ing., Ph.D.

9. Robot Motion Planning in a Scene with Obstacles

   Methods for robot motion planning have a number of applications, they can be used in production halls where the robotic device moves on a defined route, but also in situations where it is necessary to construct the track continuously, e.g., when searching for explosive areas, searching for persons in emergency situations (e.g. earthquakes). Traditional approaches include scene decomposition methods, potential field method, and roadmap methods. Within a group, a number of specific methods can be defined, which may vary, for example, according to the geometric structures used (visibility graphs, rapidly-exploring random trees, Voronoi diagrams). The task is to classify and compare main approaches and implement an algorithm to ensure that the robot path is smooth and safe from the point of view of the threat of collision with obstacles.

   Tutor: Šeda Miloš, prof. RNDr. Ing., Ph.D.

10. Robot Motion Planning in a Scene with Obstacles

    Methods for robot motion planning have a number of applications, they can be used in production halls where the robotic device moves on a defined route, but also in situations where it is necessary to construct the track continuously, e.g., when searching for explosive areas, searching for persons in emergency situations (e.g. earthquakes). Traditional approaches include scene decomposition methods, potential field method, and roadmap methods. Within a group, a number of specific methods can be defined, which may vary, for example, according to the geometric structures used (visibility graphs, rapidly-exploring random trees, Voronoi diagrams). The task is to classify and compare main approaches and implement an algorithm to ensure that the robot path is smooth and safe from the point of view of the threat of collision with obstacles.

    Tutor: Šeda Miloš, prof. RNDr. Ing., Ph.D.

11. Robotics and Bin Picking - The Search for the Holy Grail

    There are three main types of bin picking: structured, semi-structured, and random bin picking. Each presents an increasing level of application complexity, cost and cycle time. We can say that random bin picking is already approaching mainstream of robotics. Random bin picking requires a convergence of technologies, particularly three main components that raise the robot’s intelligence: sensors, software, and end-of-arm tooling. Development in all three areas is moving us ever closer to that elusive prize.

    Tutor: Matoušek Radomil, prof. Ing., Ph.D.

12. Simulation and control of biologically inspired robots

    The thesis is focused on complex solution of advanced control of mobile bio-inspired robotic snake robots. The movement and autonomy of n-link snake will be solved in theory and practice. Theoretically achieved results will be verified and analyzed by simulation modeling (Unity Real-Time Dev platform, PhysX). The design of snake locomotion is assumed to use artificial intelligence, respectively. strengthened learning.

    Tutor: Matoušek Radomil, prof. Ing., Ph.D.

13. Total productive maintenance (TPM) in non-series and small-series production

    At present, it is or is in the interest of many manufacturing engineering companies to achieve the modern TPM concept across their production and other company departments. It is common practice to find a number of such successfully established examples, but in series production. For industrial companies with the character of non-series and small-series production, the implementation of TPM comes with a number of obstacles, which require new and non-standard approaches. In addition to describing common and widespread procedures, the aim of the dissertation thesis is to find, name and solve the process of TPM implementation in non-series and small-series production. It is assumed that the obtained results will be verified in the selected engineering company.

    Tutor: Hammer Miloš, doc. Ing., CSc.