Learning Deep Robotic Skills on Riemannian Manifolds

Learning Deep Robotic Skills on Riemannian Manifolds

In this paper, we propose RiemannianFlow, a deep generative model that allows robots to learn complex and stable skills evolving on Riemannian manifolds. Examples of Riemannian data in robotics include stiffness (symmetric and positive definite matrix (SPD)) and orientation (unit quaternion (UQ)) tr...

Full description

Bibliographic Details
Main Authors: Weitao Wang, Matteo Saveriano, Fares J. Abu-Dakka
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Compliance and impedance control
deep learning methods
learning from demonstration
motion control of manipulators
Riemannian manifold
Online Access:https://ieeexplore.ieee.org/document/9931714/

Similar Items

Similar Items