Geometry-aware Dynamic Movement Primitives

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

6

Series

Proceedings of the IEEE Conference on Robotics and Automation, ICRA 2020, pp. 4421-4426, IEEE International Conference on Robotics and Automation

Abstract

In many robot control problems, factors such as stiffness and damping matrices and manipulability ellipsoids are naturally represented as symmetric positive definite (SPD) matrices, which capture the specific geometric characteristics of those factors. Typical learned skill models such as dynamic movement primitives (DMPs) can not, however, be directly employed with quantities expressed as SPD matrices as they are limited to data in Euclidean space. In this paper, we propose a novel and mathematically principled framework that uses Riemannian metrics to reformulate DMPs such that the resulting formulation can operate with SPD data in the SPD manifold. Evaluation of the approach demonstrates that beneficial properties of DMPs such as change of the goal during operation apply also to the proposed formulation.

Description

Other note

Citation

Abu-Dakka, F J & Kyrki, V 2020, Geometry-aware Dynamic Movement Primitives. in Proceedings of the IEEE Conference on Robotics and Automation, ICRA 2020., 9196952, IEEE International Conference on Robotics and Automation, IEEE, pp. 4421-4426, IEEE International Conference on Robotics and Automation, Paris, France, 31/05/2020. https://doi.org/10.1109/ICRA40945.2020.9196952