IN2106 Cybathlon Challenge: Task Control & User Experiments
|Language of instruction||English|
|Position within curricula||See TUMonline|
- 19.10.2022 13:30-18:00 M001, Seminarraum
- 26.10.2022 13:30-18:00 L022, Campus D, Seminarraum
- 02.11.2022 13:30-18:00 L022, Campus D, Seminarraum
- 09.11.2022 13:30-18:00 L022, Campus D, Seminarraum
- 16.11.2022 13:30-18:00 L022, Campus D, Seminarraum
- 23.11.2022 13:30-18:00 L022, Campus D, Seminarraum
- 30.11.2022 13:30-18:00 L022, Campus D, Seminarraum
- 07.12.2022 13:30-18:00 L022, Campus D, Seminarraum
- 14.12.2022 13:30-18:00 L022, Campus D, Seminarraum
- 21.12.2022 13:30-18:00 L022, Campus D, Seminarraum
- 11.01.2023 13:30-18:00 L022, Campus D, Seminarraum
- 18.01.2023 13:30-18:00 L022, Campus D, Seminarraum
- 25.01.2023 13:30-18:00 L022, Campus D, Seminarraum
- 01.02.2023 13:30-18:00 L022, Campus D, Seminarraum
- 08.02.2023 11:00-12:00 Online: Videokonferenz / Zoom etc., Meeting über Zoom: https://tum-conf.zoom.us/j/66624891252?pwd=WjJYL01KMGlZLzB4dEhMTGpwZTl3QT09 Meeting-ID: 666 2489 1252 Kenncode: 2022
- 08.02.2023 13:30-18:00 L022, Campus D, Seminarraum
The students form competences depending on the thematic focus they have chosen. In the area of perception, students can develop object recognition algorithms using the OpenCV, Caffe or PCL software libraries and classify EMG signals via support vector machines or neural networks. In the field of control engineering & modeling, students are able to model mechatronic prosthesis systems in MATLAB / Simulink based on the Newton-Euler and Langrange methods kinematically and dynamically, as well as to design and implement advanced model-based control methods such as impedance control. Furthermore, an intuitive user task control has to be programmed, which is based on the natural, coordinated human motor control. Students learn how to integrate mechatronic components into a functioning prosthesis system. After successfully completing their studies, students are also able to plan purposefully in a team and carry out an engineering project cooperatively.
This laboratory focuses on the development of a lightweight, wearable and intelligent upper limb prosthesis whose mechatronic base modules were developed in the previous Cybathlon course. Extended model-based and AI-supported control and regulation approaches will be addressed. In addition, novel user task control methods are developed and training sessions with a human user are planned and carried out. The results are validated on the prototype both under laboratory conditions and in field tests.
Participation in the Cybathlon Challenge: Fundamental mechanism design and lowlevel control is recommended, but is not necessary for participation in this laboratory course. Students should have sound knowledge in at least one of the following areas: - Basic knowledge in image processing - Model-based methods of automatic control - Robotics and multi-body systems - Construction (CAD) - Embedded systems - Programming (C,C++)
Teaching and learning methods
- Introductory lectures - Independent student work - Team work (including supervised and unsupervised work in the laboratory)
In this laboratory course, students develop the prototype of an intelligent mechatronic prosthesis with the aim of participating in the international cybathlon competition. The evaluation of the project work is determined by the final group prototype (75%) and the documentation (25%). Students from the Informatics department must carry out additional scientific and logistical investigation. The content and results of this work will be summarized in a 10-page report.
- Introduction to Robotics: Mechanics and Control, 3rd Edition, John J. Craig, Pearson - http://www.cybathlon.ethz.ch/ - Muzumdar, ‘Powered Upper Limb Prostheses: Control, Implementation and Clinical Application’, Springer Science & Business Media, 2004. - H. Choset, K. Lynch, S. Hutchinson, G. Kantor, W. Burgard, L. Kavraki, S. Thrun, ‘Principles of Robot Motion: Theory, Algorithms, and Implementation’, MIT Press, 2005. - Siciliano, O. Khatib, ‘Springer Handbook of Robotics’, Springer, 2016. - M. W. Spong, S. Hutchinson, M. Vidyasagar, ‘Robot modeling and control’, vol. 3. New York: Wiley, 2006. - M. Bishop, ‘Neural networks for pattern recognition’, Oxford university press, 1995.