Look Who it Was Random video

Transferring Grasping Skills to Novel Instances by Latent Space Non-Rigid Registration

292 views · Published 23 March 2018 · 4:22 · Indexed 5 October 2026

Channel: nimbro · 2018 · Science & Technology

Watch on YouTube

Video attachement for:
D. Rodriguez, C. Cogswell, S. Koo, and S. Behnke:
"Transferring Grasping Skills to Novel Instances by Latent Space Non-Rigid Registration"
IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, May 2018. 
https://www.ais.uni-bonn.de/papers/ICRA_2018_Rodriguez.pdf

Abstract: Robots acting in open environments need to be
able to handle novel objects. Based on the observation that
objects within a category are often similar in their shapes and
usage, we propose an approach for transferring grasping skills
from known instances to novel instances of an object category.
Correspondences between the instances are established by
means of a non-rigid registration method that combines the
Coherent Point Drift approach with subspace methods.
The known object instances are modeled using a canonical
shape and a transformation which deforms it to match the
instance shape. The principle axes of variation of these deformations
define a low-dimensional latent space. New instances
can be generated through interpolation and extrapolation in
this shape space. For inferring the shape parameters of an
unknown instance, an energy function expressed in terms of the
latent variables is minimized. Due to the class-level knowledge
of the object, our method is able to complete novel shapes from
partial views. Control poses for generating grasping motions
are transferred efficiently to novel instances by the estimated
non-rigid transformation.

More from this channel