Sie sind hier:



Motion Reproduction

Lehrstuhl: Institute of Control Theory and Systems Engineering

Betreuer: Myrel Alsayegh, Freia Irina Mues, Frank Hoffmann,

Beginn ab: 17.10.2016

Maximale Anzahl der Teilnehmer: 7

Beschreibung: Configuration and reconfiguration of a robot to perform a task requires a robotic expert to perform a complete analysis of the task and program the robot. A Human engages many strategies to acquire new skills and adapt them to a novel context. Basically, the human motions consist of variations of simpler motions and are not made from scratch. Thus, the human motion data is first acquired from a Motion Capture system (MoCap), then reproduced in simulation (Gazebo) and by a robot (Mitsubishi). This project group addresses the issue of robust representation and encoding as well as robust generalization of the taught human motion. This involves the following tasks:
- Data acquisition and recording of task and joint space teacher arm motion
- Encoding of demonstrated motion in a Gaussian Mixture Model
- Reproduction of the movement under kinodynamic constraints
- Modelling the robot with ROS Gazebo
- Control the robot offline and via serial interface
- Online trajectory optimization with Timed Elastic Bands* and Gaussian Mixture Models
- (Detection of vibrations of the multi-flexible-link robot arm TUDOR).

Students are expected to have a background in robotics, control theory and optimization. They are also expected to have successfully completed at least one of the two robotics classes offered in the summer term 2016:
- Mobile robots
- Modelling and control of robotic manipulators.
Students are also expected to have a profound programming experience in C++ and/or Matlab. Knowledge about ROS would be an advantage. Registration starts on 05.07.2016.

* C. Rösmann, F. Hoffmann, and T. Bertram, “Timed-elastic-bands for time-optimal point-to-point nonlinear model predictive control”, Control Conference (ECC), 2015 European, pp. 3352–3357, July 2015.
** S. Calinon, “Robot programming by demonstration: a probabilistic approach”, EPFL Press ISBN 978-2-940222-31-5, CRC Press ISBN 978-1-4398-0867-2, 222 pages, hardcover, 2009.