Improving the Successful Robotic Grasp Detection Using Convolutional Neural Networks
This work addresses real-time grasp detection for robots, but it is incremental as it builds on existing convolutional neural network methods.
The paper tackles robotic grasp detection by proposing an improved pipeline model that uses pre-processing, output normalization, and data augmentation to increase accuracy by 4.3% without slowing the system, and finds AlexNet outperforms other pre-trained models for real-time use.
Robotic grasp should be carried out in a real-time manner by proper accuracy. Perception is the first and significant step in this procedure. This paper proposes an improved pipeline model trying to detect grasp as a rectangle representation for different seen or unseen objects. It helps the robot to start control procedures from nearer to the proper part of the object. The main idea consists in pre-processing, output normalization, and data augmentation to improve accuracy by 4.3 percent without making the system slow. Also, a comparison has been conducted over different pre-trained models like AlexNet, ResNet, Vgg19, which are the most famous feature extractors for image processing in object detection. Although AlexNet has less complexity than other ones, it outperformed them, which helps the real-time property.