Suction Grasp Region Prediction using Self-supervised Learning for Object Picking in Dense Clutter
This addresses robotic picking in dense clutter, but it appears incremental as it combines existing CNN structures for a specific task.
The paper tackles robotic picking in cluttered scenarios by using a ResNet-U-Net CNN framework to predict suction grasp regions without object recognition or pose estimation, achieving learning from scratch with end-to-end training on online samples.
This paper focuses on robotic picking tasks in cluttered scenario. Because of the diversity of poses, types of stack and complicated background in bin picking situation, it is much difficult to recognize and estimate their pose before grasping them. Here, this paper combines Resnet with U-net structure, a special framework of Convolution Neural Networks (CNN), to predict picking region without recognition and pose estimation. And it makes robotic picking system learn picking skills from scratch. At the same time, we train the network end to end with online samples. In the end of this paper, several experiments are conducted to demonstrate the performance of our methods.