An Improved Dual Quaternion Dynamic Movement Primitives Based Algorithm for Robot-Agnostic Learning and Execution of Throwing Tasks
Résumé
Abstract Inspired by human nature, roboticists have conceived robots as tools meant to be flexible, capable of performing a wide variety of tasks. Learning from Demonstration (LfD) methods allow us to “teach” robots the way we would perform tasks, in a versatile and adaptive manner. Dynamic Movement Primitives (DMP) aims for learning complex behaviours in such a way, representing tasks as stable, well understood dynamical systems. By modelling movements over the SE(3) group, modelled primitives can be generalised for any robotic manipulator capable of full end-effector 3D movement. In this article, we present a robot-agnostic formulation of Discrete DMP based on Dual Quaternion algebra, oriented to modelling throwing movements. We consider adapted initial and final poses and velocities, all computed from a projectile kinematic model and from the goal at which the projectile is aimed. Experimental demonstrations are carried out in both a simulated and a real environment. Results support the effectiveness of the improved method formulation.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |