Self Supervised Deep Learning for Robot Grasping
This addresses the issue of costly and biased data labeling for researchers and practitioners in robotics, though it appears incremental as it builds on existing self-supervised learning approaches.
The paper tackles the problem of data labeling in robot grasping by proposing a self-supervised robotic setup that trains a CNN, eliminating the need for human-labeled data and reducing bias.
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.