M.Sc. & Ph.D.
Courses

Learning outcomes (students should be able to)

Use information and communication technologies in a complex way within intelligent robotic systems;

Select methods on their own, that are based on applying diverse artificial intelligence techniques and biologically inspired algorithms, with the aim to find the optimal solution during the development and machine learning of intelligent robotic systems;

Understand the interaction of software and hardware subsystems of the mobile robot in decision making, during the exploration of the manufacturing environment, through reconfiguring its physical structure and programming intelligent behavior in the MATLAB environment;

Capability for team work.

Learning outcomes (students should be able to)

Design cyber-physical systems through the implementation of communication and computational capabilities to mechanical devices;

Implement smart and conventional sensors and actuators in various systems;

Design dedicated control systems based on microcontrollers;

Understand the basic principles of motion control and implement motion control in various tasks.

Learning outcomes (students should be able to)

Use of information and communication technologies for scheduling of systems and processes;

Make the formulation, presentation and mathematical modeling of the scheduling optimization problem, with the adoption of appropriate optimization criteria and definition of the fitness function;

Select and implement advanced biologically-inspired strategies and optimization methods on their own, with the aim of finding the optimal solution of the scheduling plan by minimizing/maximizing the appropriate fitness function depending on the set of constraints;

Develop original software solutions on their own, for scheduling of systems and processes in the MATLAB software, with comparative analysis, discussion, and presentation of achieved results.

Learning outcomes (students should be able to)

Use different computer networks in an industrial environment;

Design and implement the industrial control systems distributed to smart devices;

Model the distributed control systems in accordance with IEC 61499;

Verify the performance of smart device network;

Understand the issues related to reliability and security in the industrial Internet of Things.

Learning outcomes (students should be able to)

Demonstrate knowledge and understanding of variable, reconfigurable and flexible manufacturing concepts;

Demonstrate knowledge of the parallel development of products and manufacturing systems;

Demonstrate knowledge of design support methods and tools for reconfigurability.

Demonstrate the ability to lead the development of changing manufacturing solutions.

Demonstrate the ability to assess the current state of implementation and reconfigurable manufacturing systems.

Learning outcomes (students should be able to)

Implementation of the developed software tools (e.g. TRIZ, Flexy) for modelling and analysis of intelligent manufacturing systems and processes;

Selection of methods based on the application of artificial neural networks (by using software packages MATLAB, BPnet, ART Simulator) and other computational intelligence techniques in designing and building intelligence of artefacts (autonomous mobile robots can thus be observed interacting with their manufacturing environment) as well as scheduling of manufacturing entities;

Advanced utilization of the software for discrete event simulation (AnyLogic, Flexy) with analysis and presentation of the experimental results obtained;

Understanding the interaction of soft and hard real-time subsystems of autonomous mobile robot through reconfiguration and advanced programming in MATLAB.

Learning outcomes (students should be able to)

Starting from the fundamental concepts, this subject includes scientific multidisciplinary in accordance with biological inspired bases through perspective development realization in the fields of intelligent control, artificial life and application of autonomous systems in robotized production technologies of the 21st century. The outcome of this subject is oriented towards scientific progress of PhD students, especially through intensive scientific experimental research work in domain of hardware-software integration of AS within advanced technologies of the 21st century based on development of machine intelligence and learning (computational intelligence; machine Q-learning; advanced artificial intelligence techniques; Biological Manufacturing Systems (BMS), etc.).

Learning outcomes (students should be able to)

AI and ML is a comprehensive course on the subject, covering topics not usually included in introductory machine learning. It discusses AI methods based in different fields, including artificial neural networks and genetic algorithms, signal and image processing, intelligent control, and data mining, in order to present a unified treatment of machine learning problems and solutions. All basic learning algorithms are explained so that the PhD student can easily move from the equations to a computer program, such as BPnet or Matlab.

Learning outcomes (students should be able to)

Selection of methods based on the application of artificial neural networks and other computational intelligence AI techniques in designing and building intelligence of cognitive robots;

Implementation of developed algorithms in order to enable autonomous behaviour of mobile robots in laboratory model of manufacturing environment;

Advanced programming in MATLAB® environment;

Experimental verification of autonomous robot behaviour with analysis of experimental results and comparison with other existing methods;

Building ability to analyze related work in the field of cognitive robotics.

Learning outcomes (students should be able to)

Formulate and mathematically model the optimization problem;

Understand all the phases necessary for algorithm implementation;

Implement the algorithm (the objective is to minimize/maximize the fitness function according to optimization criteria);

Develop their own codes in MATLAB environment and experimentally evaluate the performance of the algorithm;

Carry out scientific research work and apply biologically inspired algorithms to solve real optimization problems.

Learning outcomes (students should be able to)

Understand fundament theories, learning methods and advanced issues of neural network and fuzzy systems;

Apply the learned knowledge of neural and fuzzy systems to solve various research problems.