Can Movement Primitives be used to model the orientation (or pose) of a robotic arm end effector?

In literature (see for instance this imitation learning review at pag.69) it's common to see DMP (Dynamic Movement Primitives) and ProMP (Probabilistic Movement Primitives) applied to trajectories of positions and velocity pairs. I would like to apply the same formalism to predict the orientation along the trajectory, for instance of the end effector reference frame (given as Euler angles or quaternions).

I don't see a priori obstacles for Euler angles, but the normalisation conditions for quaternions may give issues.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.