Incremental Learning of Full-Pose Via-Point Movement Primitives on Riemannian Manifolds

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Daab, Tilman, Jaquier, Noémie, Dreher, Christian, Meixner, Andre, Krebs, Franziska, Asfour, Tamim
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929560234229760
author Daab, Tilman
Jaquier, Noémie
Dreher, Christian
Meixner, Andre
Krebs, Franziska
Asfour, Tamim
author_facet Daab, Tilman
Jaquier, Noémie
Dreher, Christian
Meixner, Andre
Krebs, Franziska
Asfour, Tamim
contents Movement primitives (MPs) are compact representations of robot skills that can be learned from demonstrations and combined into complex behaviors. However, merely equipping robots with a fixed set of innate MPs is insufficient to deploy them in dynamic and unpredictable environments. Instead, the full potential of MPs remains to be attained via adaptable, large-scale MP libraries. In this paper, we propose a set of seven fundamental operations to incrementally learn, improve, and re-organize MP libraries. To showcase their applicability, we provide explicit formulations of the spatial operations for libraries composed of Via-Point Movement Primitives (VMPs). By building on Riemannian manifold theory, our approach enables the incremental learning of all parameters of position and orientation VMPs within a library. Moreover, our approach stores a fixed number of parameters, thus complying with the essential principles of incremental learning. We evaluate our approach to incrementally learn a VMP library from motion capture data provided sequentially.
format Preprint
id arxiv_https___arxiv_org_abs_2312_08030
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Incremental Learning of Full-Pose Via-Point Movement Primitives on Riemannian Manifolds
Daab, Tilman
Jaquier, Noémie
Dreher, Christian
Meixner, Andre
Krebs, Franziska
Asfour, Tamim
Robotics
Movement primitives (MPs) are compact representations of robot skills that can be learned from demonstrations and combined into complex behaviors. However, merely equipping robots with a fixed set of innate MPs is insufficient to deploy them in dynamic and unpredictable environments. Instead, the full potential of MPs remains to be attained via adaptable, large-scale MP libraries. In this paper, we propose a set of seven fundamental operations to incrementally learn, improve, and re-organize MP libraries. To showcase their applicability, we provide explicit formulations of the spatial operations for libraries composed of Via-Point Movement Primitives (VMPs). By building on Riemannian manifold theory, our approach enables the incremental learning of all parameters of position and orientation VMPs within a library. Moreover, our approach stores a fixed number of parameters, thus complying with the essential principles of incremental learning. We evaluate our approach to incrementally learn a VMP library from motion capture data provided sequentially.
title Incremental Learning of Full-Pose Via-Point Movement Primitives on Riemannian Manifolds
topic Robotics
url https://arxiv.org/abs/2312.08030