Self Supervised Deep Learning for Robot Grasping

TL;DR

A simpler self-supervised robotic setup, that will train a Convolutional Neural Network (CNN), that will label and collect the data during the training process to make a robot that is less costly, small and easily maintainable in a lab setup.

Abstract

Learning Based Robot Grasping currently involves the use of labeled data. This approach has two major disadvantages. Firstly, labeling data for grasp points and angles is a strenuous process, so the dataset remains limited. Secondly, human labeling is prone to bias due to semantics. In order to solve these problems we propose a simpler self-supervised robotic setup, that will train a Convolutional Neural Network (CNN). The robot will label and collect the data during the training process. The idea is to make a robot that is less costly, small and easily maintainable in a lab setup. The robot will be trained on a large data set for several hundred hours and then the trained Neural Network can be mapped onto a larger grasping robot.

Figures (13)

• Figure 1: Overall Project Overview
• Figure 2: Detailed Project Modules
• Figure 3: Object Detector GUI
• Figure 4: YOLOv4 Object Detector with GUI
• Figure 5: Object Detection on various objects