Review Paper: PointNetGPD- Detecting Grasp Configuration from Point Sets

Introduction

In this post, I want to review a technique which works directly with point clouds to detect a grasp configuration. By grasp configuration, I mean the position and orientation of the gripper. The following picture shows a general overview of the approach.

To summarize, the key contributions of this work are:
• Proposing a network to evaluate the grasp quality by performing geometry analysis directly from a 3D point cloud based on the network architecture of PointNet. Compared
with other CNN-based methods, this method can exploit the 3D geometry information in the depth image better without any hand-crafted features and sustain a relatively small amount of parameters for learning and inference efficiency. Also, this method still works well even when the point cloud is very sparse, which implies its potential for planning grasps under imprecise and deficient sensing.
• Releasing a large-scale grasp dataset that contains 350k real point cloud and parallel-jaw grasps.

Algorithm

This work uses PointNet-based network to detect reliable grasp configuration from point clouds. The pipeline is as follows:

• Taking raw sensor input…