Object grasp pose detection based on the region of interest

被引：0

作者：

Sun X. ^{[1
]}

Jiang W. ^{[1
]}

Chen W. ^{[1
]}

Zhi Y. ^{[1
]}

机构：

[1] School of Electrical Engineering and Automation, Anhui University, Hefei

[2] School of Automation Science and Electrical Engineering, Beihang University, Beijing

来源：

Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2024年 / 46卷 / 06期

关键词：

deep learning; lightweight network; mask; pose detection; region of interest;

D O I：

10.12305/j.issn.1001-506X.2024.06.05

中图分类号：

学科分类号：

摘要：

In industrial production, the objects to be grasped often have the characteristics of varions types, messy placements, irregular shapes, etc. , which make it difficult to accurately obtain the grasping pose of the object. In view of the above problems, this paper proposes a two-stage grasp pose estimation method based on deep learning. In the first stage, a lightweight rotating target detection algorithm based on improved you only look once version4 (YOLOv4) is proposed to enhance the detection speed and improve detection accuracy of targets. Firstly, the lightweight network GhostNet and deep separable convolution are used to reconstruct the original network to reduce the parameters of the entire model. Then, the adaptive spatial feature fusion structure and the non-reference attention module are added to the neck network to improve the positioning accuracy of the region of interest. Finally, the approximate skew intersection over union (SkewloU) loss is used to solve the periodic problem of the angle. In the second stage, a mask extraction region of interest is made with the same size as the original picture. At the same time, an improved DeepLabV3 + algorithm is proposed to detect the grasping pose of objects in the area of interest. Experimental results show that the detection accuracy of the improved YOLOv4 network reaches 92. 5%, and the improved DeepLabV3 + algorithm achieves 94. 6% and 92. 4% of the image splitting and object splitting accuracy on the Cornell capture dataset, respectively, and can accurately detect the grasping pose of objects. © 2024 Chinese Institute of Electronics. All rights reserved.

引用

页码：1867 / 1877

页数：10

共 30 条

[1]

CAI J H, CEN J, WANG H K, Et al., Real-time collision-free grasp pose detection with geometry-aware refinement using high-resolution volume, IEEE Robotics and Automation Letters, 7, 2, pp. 1888-1895, (2022)

[2]

CHENG H, WANG Y Y, MENG M Q H., A robot grasping system with single-stage anchor-free deep grasp detector, IEEE Trans, on Instrumentation and Measurement, 71, (2022)

[3]

WEN H T, YAN J H, PENG W L, Et al., TransGrasp: grasp pose estimation of a category of objects by transferring grasps from only one labeled instance, Proc. of the 17th European Conference, pp. 445-461, (2022)

[4]

WEI H, PAN S C, MA G, Et al., Vision-guided hand-eye coordination for robotic grasping and its application in tangram puzzles, Artificial Intelligence, 2, 2, pp. 209-228, (2021)

[5]

LENZ I, LEE H, SAXENA A., Deep learning for detecting robotic grasps, The International Journal of Robotics Research, 34, 4, pp. 705-724, (2015)

[6]

MORRISON D, CORKE P, LEITNER J., Learning robust, realtime, reactive robotic grasping, The International Journal of Robotics Research, 39, 2, pp. 183-201, (2020)

[7]

LIANG H Z, MAXJ, LIS, Et al., Pointnetgpd: detecting grasp configurations from point sets, Proc. of the International Conference on Robotics and Automation, pp. 3629-3635, (2019)

[8]

ZHANG L Z, WU D M., A single target grasp detection network based on convolutional neural network, Computational Intelligence and Neuroscience, 5, (2021)

[9]

CHU F J, XU R N, VELA P A., Real-world multi-object, multi-grasp detection, IEEE Robotics and Automation Letters, 3, 4, pp. 3355-3362, (2018)

[10]

AINETTER S, FRAUNDORFER F., End-to-end trainable deep neural network for robotic grasp detection and semantic segmentation from RGB, Proc. of the IEEE International Conference on Robotics and Automation, pp. 13452-13458, (2021)

← 1 2 3 →