Learning stable robotic skills on Riemannian manifolds
Loading...
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal
View/Open full text file from the Research portal
Other link related to publication
View publication in the Research portal
View/Open full text file from the Research portal
Other link related to publication
Date
2023-11
Department
University of Trento
Technical University of Munich
Department of Electrical Engineering and Automation
Department of Electrical Engineering and Automation
Technical University of Munich
Department of Electrical Engineering and Automation
Department of Electrical Engineering and Automation
Major/Subject
Mcode
Degree programme
Language
en
Pages
14
Series
Robotics and Autonomous Systems, Volume 169
Abstract
In this paper, we propose an approach to learn stable dynamical systems that evolve on Riemannian manifolds. Our approach leverages a data-efficient procedure to learn a diffeomorphic transformation, enabling the mapping of simple stable dynamical systems onto complex robotic skills. By harnessing mathematical techniques derived from differential geometry, our method guarantees that the learned skills fulfill the geometric constraints imposed by the underlying manifolds, such as unit quaternions (UQ) for orientation and symmetric positive definite (SPD) matrices for impedance. Additionally, the method preserves convergence towards a given target. Initially, the proposed methodology is evaluated through simulation on a widely recognized benchmark, which involves projecting Cartesian data onto UQ and SPD manifolds. The performance of our proposed approach is then compared with existing methodologies. Apart from that, a series of experiments were performed to evaluate the proposed approach in real-world scenarios. These experiments involved a physical robot tasked with bottle stacking under various conditions and a drilling task performed in collaboration with a human operator. The evaluation results demonstrate encouraging outcomes in terms of learning accuracy and the ability to adapt to different situations.Description
Funding Information: Part of the research presented in this work has been conducted when: M. Saveriano was at the Department of Computer Science, University of Innsbruck, Innsbruck, Austria, and F. Abu-Dakka was at the Intelligent Robotics Group, Department of Electrical Engineering and Automation, Aalto University, Finland. This work has been partially supported by the Austrian Research Foundation (Euregio IPN 86-N30, OLIVER), by CHIST-ERA project IPALM (Academy of Finland decision 326304), by the European Union under NextGenerationEU project iNest (ECS 00000043), and by euROBIN project under grant agreement No. 101070596. | openaire: EC/HE/101070596/EU//euROBIN Funding Information: This work has been partially supported by the Austrian Research Foundation (Euregio IPN 86-N30, OLIVER) , by CHIST-ERA project IPALM (Academy of Finland decision 326304), by the European Union under NextGenerationEU project iNest ( ECS 00000043 ), and by euROBIN project under grant agreement No. 101070596 . Publisher Copyright: © 2023 The Author(s)
Keywords
Learning from Demonstration, Learning stable dynamical systems, Riemannian manifold learning
Citation
Saveriano , M , Abu-Dakka , F J & Kyrki , V 2023 , ' Learning stable robotic skills on Riemannian manifolds ' , Robotics and Autonomous Systems , vol. 169 , 104510 . https://doi.org/10.1016/j.robot.2023.104510
