Stud.IP Uni Oldenburg
University of Oldenburg
16.10.2021 03:43:51
inf303 - Fuzzy Control and Artificial Neural Networks in Robotics and Automation (Complete module description)
Original version English Download as PDF
Module label Fuzzy Control and Artificial Neural Networks in Robotics and Automation
Module code inf303
Credit points 6.0 KP
Workload 180 h
Institute directory Department of Computing Science
Applicability of the module
  • Master's Programme Computing Science (Master) > Angewandte Informatik
  • Master's Programme Computing Science (Master) > Technische Informatik
  • Master's Programme Embedded Systems and Microrobotics (Master) > Akzentsetzungsmodule
  • Master's Programme Engineering of Socio-Technical Systems (Master) > Embedded Brain Computer Interaction
  • Master's Programme Engineering of Socio-Technical Systems (Master) > Human-Computer Interaction
  • Master's Programme Engineering of Socio-Technical Systems (Master) > Systems Engineering
  • Master's Programme Engineering Physics (Master) > Schwerpunkt: Renewable Energies
Responsible persons
Fatikow, Sergej (Authorized examiners)
Lehrenden, Die im Modul (Authorized examiners)
Skills to be acquired in this module
Experts in different branches try to approach their application-specific control and information processing problems by using fuzzy logic and artificial neural networks (ANN). The experiences gathered up to now prove robotics and automation technology to be predestined fields of application of both these approaches. The major topics of the course are control problems in robotics and automation technology, principles of fuzzy logic and ANN and their practical appplications, comparison of conventional and advanced control methods, combination of fuzzy logic and ANN in control systems. The course gives a comprehensive treatment of these advanced approaches for interested students.

Professional competence
The students:
  • recognise control problems in robotics and automation technology,
  • name principles of fuzzy logic and ANN and their practical appplications,
  • compare conventional and advanced control methods,
  • characterise the combination of fuzzy logic and ANN in control systems

Methodological competence
The students:
  • will acquire knowledge of the tools, methods and applications in fuzzy logic and ANN
  • deepen their knowledge for the practical use of the given methods
  • can use common software tools for design and application of fuzzy logic and ANN

Social competence
The students:
  • gain experience in interdisciplinary work
  • are integrated into the recent research work
Objective of the module / skills:

The students:
  • are able to transfer the gained knowledge for later use in their theses or studies for AMiR
  • can Design (complex) fuzzy logic controller and ANN systems
  • reflect their (control) solutions by using methods learned in this course
Module contents
  • Control problems in robotics and automation technology
  • Basic ideas of fuzzy logic and ANN
  • Principles of fuzzy logic
  • Fuzzy logic of rule-based systems
  • ANN models
  • ANN learning rules
  • Multilayer perceptron networks and backpropagation
  • Associative networks
  • Self-organizing feature maps
  • PID design principles
  • Design of fuzzy control systems
  • Fuzzy logic application examples
  • Design of ANN control systems
  • ANN application examples
  • Fuzzy + Neuro: principles and applications
Reader's advisory
  • Lecture notes (available at the secretariat, A1-3-303) in book form

  • Bothe, H.-H.: Neuro-Fuzzy-Methoden, Springer, 1998
  • Braun, Feulner, Malaka: Praktikum Neuronale Netze, Springer, 1997
  • Kahlert, J.: Fuzzy Control für Ingenieure, Vieweg, Braunschweig Wiesbaden, 1995
  • Nauck, D., Klawonn, F. und Kruse, R.: Neuronale Netze und Fuzzy-Systeme, Vieweg, 1994
  • Zell, A.: Simulation Neuronaler Netze, Addison-Wesley / Oldenbourg Verlag, Bonn, 1996

Secondary Literature:
  • Altrock, M. O. R.: Fuzzy Logic, R. Oldenbourg Verlag, 1993
  • Bekey, A. and Goldberg, K.Y. (Eds.): Neural Networks in Robotics, Kluwer Academic, 1996
  • Berns, K. und Kolb, T.: Neuronale Netze für technische Anwendungen, Springer, 1994
  • Bothe, H.-H.: Fuzzy Logic, Springer, 1993
  • Bunke, H., Kandel, A. (eds.): Neuro-Fuzzy Pattern Recognition, World Scientific Publ., 2000
  • Kahlert, J. und Hubert, F.: Fuzzy-Logik und Fuzzy-Control, Vieweg, 1993
  • Kim, Y.H. and Lewis, F.L.: High-Level Feedback Control with Neural Networks, World Scientific, 1998
  • Kratzer, K.P.: Neuronale Netze, Carl Hanser, 1993
  • Lämmel, U. und Cleve, J.: Künstliche Intelligenz (neuronale Netze), Fachbuchverlag Leipzig, 2001
  • Lawrence, J.: Neuronale Netze, Systhema Verlag, München, 1992
  • Omidvar, O. and van der Smagt, P. (eds.): Neural Networks for Robotics, Academic Press, 1997
  • Patterson, D.W.: Künstliche neuronale Netze, Prentice Hall, 1996
  • Pham, D.T. a200
  • nd Liu, X.: Neural Networks for Identification, Prediction and Control, Springer, 1997
  • Rigoll, G.: Neuronale Netze, Expert Verlag, Renningen-Malmsheim, 1994
  • Ritter, H., Martinetz, Th. und Schulten, K.: Neuronale Netze, Addison-Wesley, 1991
  • Schulte, U.: Einführung in Fuzzy-Logik, Franzis-Verlag, München, 1993
  • Tizhoosh, H.R.: Fuzzy-Bildverarbeitung, Springer, 1998
  • von Altrock, C.: Fuzzy Logic: Technologie, Oldenbourg, 1993
  • White, D. and Sofge, D. (Eds.): Handbook of Intelligent Control, Van Nostrand Reinhold, New York, 1992
  • Zakharian, S. Ladewig-Riebler, P. und Thoer, St.: Neuronale Netze für Ingenieure, Vieweg, Wiesbaden, 1998
  • Zalzala, A. and Morris, A. (Eds.): Neural Networks for Robotic Control, Ellis Horwood, London, 1996
  • Zimmermann H.-J. (Hrsg.): Datenanalyse, VDI-Verlag, 1995
  • Zimmermann, H.-J. (Hrsg.): Neuro + Fuzzy: Technologien und Anwendungen, VDI-Verlag, 1995
  • Zimmermann, H.-J. und von Altrock, C. (Hrsg.): Fuzzy Logic: Anwendungen, Oldenbourg, 1994
Languages of instruction English , German
Duration (semesters) 1 Semester
Module frequency once a year
Module capacity unlimited
Modullevel / module level AS (Akzentsetzung / Accentuation)
Modulart / typ of module Pflicht o. Wahlpflicht / compulsory or optioal
Lehr-/Lernform / Teaching/Learning method V+Ü
Vorkenntnisse / Previous knowledge Regelungstechnik
Course type Comment SWS Frequency Workload of compulsory attendance
3 SuSe 42
1 SuSe 14
Total time of attendance for the module 56 h
Examination Time of examination Type of examination
Final exam of module
At the end of the lecture period until the beginning of the next semester
Hands-on-exercises and oral Exam