CapriDB - Capture, Print, Innovate: A Low-Cost Pipeline and Database for Reproducible Manipulation Research
Conference poster, 2016

We present a novel approach and database which combines the inexpensive generation of precise 3D object models via monocular camera images with 3D printing and a state of the art object tracking algorithm. Unlike recent efforts towards the creation of 3D object databases for robotics, our approach does not require expensive and controlled 3D scanning setups and enables anyone with a camera to scan, print and track complex objects for manipulation research. The proposed approach results in highly detailed mesh models whose 3D printed replicas are at times difficult to distinguish from the original. A key benefit of utilizing 3D printed objects is the ability to precisely control and vary object properties such as the mass distribution and size in the 3D printing process to obtain reproducible conditions for robotic manipulation research. We present CapriDB - an extensible database resulting from this approach and containing initially over 40 textured and 3D printable mesh models together with tracking features to facilitate the adoption of the proposed approach. We verify that the obtained object models can be 3D printed with texture and that the pose of these printed objects can be tracked successfully. We furthermore perform complete grasping experiments using the estimated poses of printed objects which is calculated using the mesh-models obtained from the original real-world objects.

3D object modelling

Author

Florian Pokorny

Royal Institute of Technology (KTH)

Yasemin Bekiroglu

Chalmers, Signals and Systems, Systems and control, Automatic Control

Karl Pauwels

Royal Institute of Technology (KTH)

Judith Butepage

Royal Institute of Technology (KTH)

Clara Scherer

Royal Institute of Technology (KTH)

Danica Kragic

Royal Institute of Technology (KTH)

EEE ICRA 2016 Workshop: Grasping and Manipulation Datasets
Stockholm, ,

Subject Categories

Media Engineering

Robotics

Computer Vision and Robotics (Autonomous Systems)

More information

Created

9/2/2020 2