Skip to content

Latest commit

 

History

History

DMP

README.md

Obstacle Avoidance with Dynamic Movements Primitives

Robotics toolbox for matlab.

Litterature

Dynamic Movement Primitives

  • Ijspeert, A. J., Nakanishi, J., Hoffmann, H., Pastor, P., & Schaal, S. (2013). Dynamical movement primitives: learning attractor models for motor behaviors. Neural computation, 25(2), 328-373.
  • Ijspeert, A. J., Nakanishi, J., & Schaal, S. (2002, May). Movement imitation with nonlinear dynamical systems in humanoid robots. In Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No. 02CH37292) (Vol. 2, pp. 1398-1403). IEEE.

Obstacle Avoidance

  • Park, D. H., Hoffmann, H., Pastor, P., & Schaal, S. (2008, December). Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields. In Humanoids 2008-8th IEEE-RAS International Conference on Humanoid Robots (pp. 91-98). IEEE.
  • Hoffmann, H., Pastor, P., Park, D. H., & Schaal, S. (2009, May). Biologically-inspired dynamical systems for movement generation: automatic real-time goal adaptation and obstacle avoidance. In 2009 IEEE International Conference on Robotics and Automation (pp. 2587-2592). IEEE.

Intuitive explanations and some simple Python code

More information is given in lecture 10: Programming by Demonstration in Advanced Robotics 2.

Admittance Control for Learning from Demonstration

Kinesthetic teaching of complex tasks becomes easier for the operator with the use of an admittance controller that adapts to the dynamics of the user’s arm. The taught trajectory can be then encoded as a Dynamic Movement Primitive and adapt to a change in the location of the workpieces using pose estimation. This project will involve exploring admittance control.

The project will contain the following subjects:

  • Force (admittance) control
  • Dynamic movement primitives
  • Pose estimation (optional)