Journal
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
Volume 52, Issue 2, Pages 1167-1181Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSMC.2020.3018757
Keywords
Grasping; Robot kinematics; Manipulators; Image segmentation; Deconvolution; Machine learning; Global deconvolution network (GDN); robotic grasping; simultaneous detection and segmentation; two-stream grasping convolutional neural network (CNN)
Funding
- National Natural Science Foundation of China [61633017, 61633020, 61836015]
- Beijing Advanced Innovation Center for Intelligent Robots and Systems [2018IRS21]
Ask authors/readers for more resources
In this article, a novel two-stream grasping CNN with simultaneous detection and segmentation is proposed. The proposed method achieves improved detection and segmentation accuracy by introducing a channel-based attention mechanism and combining the learning of multitask loss weightings and background suppression. Experimental results show that the proposed method performs well in grasp detection and has good adaptability to background.
The manipulating robots receive much attention by offering better services, where object grasping is still challenging especially under background interferences. In this article, a novel two-stream grasping convolutional neural network (CNN) with simultaneous detection and segmentation is proposed. The proposed method is cascaded by an improved simultaneous detection and segmentation network BlitzNet and a two-stream grasping CNN TsGNet. The improved BlitzNet introduces the channel-based attention mechanism, and achieves an improvement of detection accuracy and segmentation accuracy with the combination of the learning of multitask loss weightings and background suppression. Based on the obtained bounding box and the segmentation mask of the target object, the target object is separated from the background, and the corresponding depth map and grayscale map are sent to TsGNet. By adopting depthwise separable convolution and designed global deconvolution network, TsGNet achieves the best grasp detection with only a small amount of network parameters. This best grasp in the pixel coordinate system is converted to a desired 6-D pose for the robot, which drives the manipulator to execute grasping. The proposed method combines a grasping CNN with simultaneous detection and segmentation to achieve the best grasp with a good adaptability to background. With the Cornell grasping dataset, the image-wise accuracy and object-wise accuracy of the proposed TsGNet are 93.13% and 92.99%, respectively. The effectiveness of the proposed method is verified by the experiments.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available