Efficient Fully Convolution Neural Network for Generating Pixel Wise Robotic Grasps With High Resolution Images

TL;DR

This paper introduces an efficient fully convolutional neural network that generates high-resolution pixel-wise robotic grasp predictions, achieving high accuracy and fast inference on RGB-D images without needing multiple object training.

Contribution

The novel fully convolutional network enables pixel-wise grasp detection on high-resolution images, outperforming traditional methods in accuracy and speed, and generalizes to unseen objects.

Findings

94.42% image-wise accuracy

91.02% object-wise accuracy

8ms prediction time

Abstract

This paper presents an efficient neural network model to generate robotic grasps with high resolution images. The proposed model uses fully convolution neural network to generate robotic grasps for each pixel using 400 $\times$ 400 high resolution RGB-D images. It first down-sample the images to get features and then up-sample those features to the original size of the input as well as combines local and global features from different feature maps. Compared to other regression or classification methods for detecting robotic grasps, our method looks more like the segmentation methods which solves the problem through pixel-wise ways. We use Cornell Grasp Dataset to train and evaluate the model and get high accuracy about 94.42% for image-wise and 91.02% for object-wise and fast prediction time about 8ms. We also demonstrate that without training on the multiple objects dataset, our model can directly output robotic grasps candidates for different objects because of the pixel wise implementation.