EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning stable robotic skills on Riemannian manifolds

Matteo Saveriano, Fares J. Abu-Dakka, Ville Kyrki

Robotics and Autonomous Systems · 2023-11 · 169 · 104510

DOI: 10.1016/j.robot.2023.104510 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Robotics and Autonomous Systems, 2023-11. Verfasst von Matteo Saveriano und 2 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose an approach to learn stable dynamical systems evolving on Riemannian manifolds. The approach leverages a data-efficient procedure to learn a diffeomorphic transformation that maps simple stable dynamical systems onto complex robotic skills. By exploiting mathematical tools from differential geometry, the method ensures that the learned skills fulfill the geometric constraints imposed by the underlying manifolds, such as unit quaternion (UQ) for orientation and symmetric positive definite (SPD) matrices for impedance, while preserving the convergence to a given target. The proposed approach is firstly tested in simulation on a public benchmark, obtained by projecting Cartesian data into UQ and SPD manifolds, and compared with existing approaches. Apart from evaluating the approach on a public benchmark, several experiments were performed on a real robot performing bottle stacking in different conditions and a drilling task in cooperation with a human operator. The evaluation shows promising results in terms of learning accuracy and task adaptation capabilities.

Zitieren

APA

Saveriano, M., Abu-Dakka, F. J., & Kyrki, V. (2023). Learning stable robotic skills on Riemannian manifolds. Robotics and Autonomous Systems, 169, 104510. https://doi.org/10.1016/j.robot.2023.104510

Vancouver

Saveriano M, Abu-Dakka FJ, Kyrki V. Learning stable robotic skills on Riemannian manifolds. Robotics and Autonomous Systems. 2023;169:104510. doi:10.1016/j.robot.2023.104510

BibTeX
@article{Saveriano2023,
  author = {Saveriano, Matteo and Abu-Dakka, Fares J. and Kyrki, Ville},
  title = {Learning stable robotic skills on Riemannian manifolds},
  journal = {Robotics and Autonomous Systems},
  year = {2023},
  volume = {169},
  pages = {104510},
  doi = {10.1016/j.robot.2023.104510}
}
Kostenlos starten →