Ing. Tomáš Marada, Ph.D.
E-mail:   marada@fme.vutbr.cz  Dept.:   Institute of Production Machines, Systems and Robotics Dept. of Electrical Engineering Position:   Assistant Professor Room:   A1/1126

Supervised courses:

• Control of Machines and Drives (ERS)
• Control of Machines and Drives (ERS-K)
• Modelling and Simulation of Production Machines (GMS)
• Modelling and Simulation of Production Machines (GMS-K)

Publications:

• MATOUŠEK, R.; NĚMEC, Z.; MARADA, T.:
  Weighting of Goods by means of DC Motor,
  Advanced Materials Research, Vol.2012, (2012), No.463-464, pp.1427-1431, ISSN 1022-6680, Trans Tech Publications
  journal article - other
• MATOUŠEK, R.; NĚMEC, Z.; MARADA, T.:
  Weighting of Goods by means of DC Motor,
  Proceedings of the Fifth International Conference on Optimization of the Robots and Manipulators, pp.176-180, ISBN 978-981-08-5840-7, (2010), Research Publishing Servises
  conference paper
  akce: Fifth Internationa Conference on Optimization of the Robots and Manipulators, Calimanesti, 28.05.2010-30.05.2010
• MARADA, T.:
  Malý autonomní robot Micro-mouse I,
  Šedesát let kybernetiky, pp.9-15, ISBN 978-80-7204-662-1, (2009), Akademické nakladatelství CERM
  book chapter
• MARADA, T.:
  Malý autonomní robot micro-mouse I. Hardwarové řešení,
  Šedesát let kybernetiky, pp.145-151, ISBN 978-80-7204-662-1, (2009), Akademické nakladatelství CERM
  book chapter
• MARADA, T.:
  The Flood-Fill and the Modified Flood-Fill Algorithm for Micro-Mouse Robot,
  Proceedings of the 14th International Conference on Soft Computing MENDEL 2008, pp.192-197, ISBN 978-80-214-3675-6, (2008), FME BUT
  conference paper
  akce: MENDEL 2008 - 14th International Conference on Soft Computing, Brno University of Technology, 18.06.2008-20.06.2008
• MARADA, T.:
  The robot for practical verifying of artificial intelligence methods: Micro-mouse task,
  Recent Advances in Mechatronics, pp.102-106, ISBN 978-3-540-73955-5, (2007), Springer
  conference paper
  akce: Mechatronics 2007, Warsaw, 19.09.2007-21.09.2007
• MARADA, T.:
  Control of asynchronous electric motor focused on Q-learning,
  Březina, T. (ed.), Simulation Modelling of Mechatronic Systems I, pp.155-159, ISBN 80-214-3144-X, (2005)
  book chapter

List of publications at Portal BUT

Abstracts of most important papers:

• MATOUŠEK, R.; NĚMEC, Z.; MARADA, T.:
  Weighting of Goods by means of DC Motor,
  Proceedings of the Fifth International Conference on Optimization of the Robots and Manipulators, pp.176-180, ISBN 978-981-08-5840-7, (2010), Research Publishing Servises
  conference paper
  akce: Fifth Internationa Conference on Optimization of the Robots and Manipulators, Calimanesti, 28.05.2010-30.05.2010
  The paper deals with the practical problem of the intelligent weighing and his real solution by means of unprecedented new progression. The project was concerned with handling and weighing goods with different weights of individual items. The basic part of the paper is a demonstration of automatic control of the intelligent process of weighing goods using mostly hardware and software resources by Phoenix Contact and standard DC motor platform.sually ranks among the difficult task in engineering practice.
• MATOUŠEK, R.; NĚMEC, Z.; MARADA, T.:
  Intelligent Weighing of Goods for Packing,
  Cybernetic Letters, Vol.6, (2008), No.II, pp.1-5, ISSN 1802-3525, Univerzita obrany
  journal article - other
  The paper deals with the practical problem of the intelligent weighing and his real solution by means of unprecedented new progression. The project was concerned with handling and weighing goods with different weights of individual items. The basic part of the project is a demonstration of automatic control of the intelligent process of weighing and sorting goods using mostly hardware and software resources by Phoenix Contact. The basic idea of an intelligent weighing is based on the fact that the movement dynamics depends on the weight of the goods handled. In the process of movement control, detailed position and motor current values are measured to calculate the desired weight of the goods to be transported (handled).
• MARADA, T.:
  The robot for practical verifying of artificial intelligence methods: Micro-mouse task,
  Recent Advances in Mechatronics, pp.102-106, ISBN 978-3-540-73955-5, (2007), Springer
  conference paper
  akce: Mechatronics 2007, Warsaw, 19.09.2007-21.09.2007
  Robot localization and path planning belong to actual problems in robotics. The paper is focused on design of small autonomous robot for practical verifying artificial intelligence methods concretely on Micro-mouse task. The physical model was designed with respect to its simple construction, unpretentious production and relatively little cost but suffi-cient capability for performing different experiments.
• MARADA, T.:
  Control of asynchronous electric motor focused on Q-learning,
  Březina, T. (ed.), Simulation Modelling of Mechatronic Systems I, pp.155-159, ISBN 80-214-3144-X, (2005)
  book chapter
  Presented work is focus on use of Q-learning method on asynchronous drive control. The learning process was dividing into two phases - pre-learning stage and tutorage stage. Pre-learning stage uses conventional q-learning procedure and requires the computation model of asynchronous electric motor. This phase is very effective. Second phase - tutorage stage already uses real motor for improvement of settings obtained in the first stage. Controller designed this way is use in scalar control.
• MARADA, T., BŘEZINA, T.:
  Q-learned Controller Performance of Asynchronous electromotor,
  Elektronika, Vol.2004, (2004), No.8-9, pp.14-18, ISSN 0033-2089
  journal article - other
  akce: 5th International Conference, Mechatronics 2004 , Warsaw, Poland, 23.09.2004-25.09.2004
  The contribution is focused on the application of Q-learning on asynchronous electromotor (AE) control. The learning process was divided into two phases – prelearning stage and tutorage stage. Tutorage stage uses conventional Q-learning procedure applied on Q function created during the prelearning stage. Tutorage is expected to be processed on real AE plant and its use for controller adaptation on possible system parameters changes is not excluded. Based on the tests the best grids of Q-function table for 2-D state and 3-D state were selected and obtained policies performance was compared with the performance of AE controlled by PID, which was tuned through Ziegler-Nichols methodology.