Collect experiments on the superquadric grasping demo
The module experiment-1
implements a wrapper code for performing the superquadric modeling and grasping pipeline described in [1].
This wrapper code communicates with existing modules developed in robotology repo
and its structure can be summarized as follow:
- The wrapper code asks the object property collector for the 2D bounding box information of the object.
- Given that, lbpExtract module provides the 2D blob of the object.
- The wrapper code sends the 2D blob of the object to the Structure From Motion module for getting the relative 3D point cloud.
- The 3D point cloud is then sent to the superquadric-model for computing the superquadric modeling the object.
- The wrapper code sends the estimated superquadric to the superquadric-grasp module, which computes suitable poses.
- Finally, the superquadric-grasp is asked to perform the grasping task.
A detailed description of the developed code is available also in [2].
Information about how to compile, launch and interact with the module is provided in the experiment-1 folder
.
The online documentation of this module is available here.
[1] G. Vezzani, U. Pattacini and L. Natale, "A grasping approach based on superquadric models", IEEE-RAS International Conference on Robotics and Automation 2017, pp 1579-1586.
[2] G. Vezzani and L. Natale, "Real-time Pipeline for Object Modeling and Grasping Pose Selection via Superquadric Functions", Frontiers in Robotics and AI 4, 59.