| Publication type: |
Article |
| Author: |
Jesse Richter-Klug, Patrick Mania, Gayane Kazhoyan, Michael Beetz, Udo Frese |
| Title: |
Improving Object Pose Estimation by Fusion with a Multimodal Prior – Utilizing Uncertainty-based CNN Pipelines for Robotics |
| Journal: |
IEEE Robotics and Automation Letters |
| Year published: |
2022 |
| Abstract: |
Estimating the pose of an object is essential for
robot manipulation. In many applications the spatial and
geometric relations between the object and the other parts
of the world, e.g. the relation between the object and its
supporting plane, are a-priori known or can be assumed with
a certain accuracy. This information can be leveraged for pose
estimation. In this work, we show how this information can
be formulated as multimodal prior and probabilistically fused
with pose information that a CNN extracts from an image. For
this purpose, the CNN pipeline from prior work is utilized. In
the cases where the prior fits the ground truth, the approach is
able to propel monocular results to binocular / depth data levels.
Importantly, in the cases of no fitting priors, the pose estimation
does not get negatively affected. The proposed method was
evaluated on the T-Less dataset and used in a sample robotic
application. |
| Internet: |
https://doi.org/10.1109/LRA.2022.3140450 |
| PDF Version: |
https://ieeexplore.ieee.org/iel7/7083369/7339444/09670642.pdf |
| Keywords: |
sensor-fusion pose estimation prior service-robotics |
| Status: |
Reviewed |
| Last updated: |
01. 02. 2022 |
|
 |
