Next Article in Journal
Autonomous Assessment of Delamination Using Scarce Raw Structural Vibration and Transfer Learning
Previous Article in Journal
Fabrication and Characterization of Line-by-Line Inscribed Tilted Fiber Bragg Gratings Using Femtosecond Laser
Article

Research on Multi-Object Sorting System Based on Deep Learning

1
School of Mechanical and Aerospace Engineering, Jilin University, Changchun 130022, China
2
School of Vehicle and Energy, Yanshan University, Qinhuangdao 066004, China
*
Author to whom correspondence should be addressed.
Academic Editor: Petros Daras
Sensors 2021, 21(18), 6238; https://doi.org/10.3390/s21186238
Received: 9 July 2021 / Revised: 31 August 2021 / Accepted: 15 September 2021 / Published: 17 September 2021
(This article belongs to the Section Navigation and Positioning)
As a complex task, robot sorting has become a research hotspot. In order to enable robots to perform simple, efficient, stable and accurate sorting operations for stacked multi-objects in unstructured scenes, a robot multi-object sorting system is built in this paper. Firstly, the training model of rotating target detection is constructed, and the placement state of five common objects in unstructured scenes is collected as the training set for training. The trained model is used to obtain the position, rotation angle and category of the target object. Then, the instance segmentation model is constructed, and the same data set is made, and the instance segmentation network model is trained. Then, the optimized Mask R-CNN instance segmentation network is used to segment the object surface pixels, and the upper surface point cloud is extracted to calculate the normal vector. Then, the angle obtained by the normal vector of the upper surface and the rotation target detection network is fused with the normal vector to obtain the attitude of the object. At the same time, the grasping order is calculated according to the average depth of the surface. Finally, after the obtained object posture, category and grasping sequence are fused, the performance of the rotating target detection network, the instance segmentation network and the robot sorting system are tested on the established experimental platform. Based on this system, this paper carried out an experiment on the success rate of object capture in a single network and an integrated network. The experimental results show that the multi-object sorting system based on deep learning proposed in this paper can sort stacked objects efficiently, accurately and stably in unstructured scenes. View Full-Text
Keywords: robot sorting; rotating target detection; instance segmentation; pose estimation robot sorting; rotating target detection; instance segmentation; pose estimation
Show Figures

Figure 1

MDPI and ACS Style

Zhang, H.; Liang, H.; Ni, T.; Huang, L.; Yang, J. Research on Multi-Object Sorting System Based on Deep Learning. Sensors 2021, 21, 6238. https://doi.org/10.3390/s21186238

AMA Style

Zhang H, Liang H, Ni T, Huang L, Yang J. Research on Multi-Object Sorting System Based on Deep Learning. Sensors. 2021; 21(18):6238. https://doi.org/10.3390/s21186238

Chicago/Turabian Style

Zhang, Hongyan, Huawei Liang, Tao Ni, Lingtao Huang, and Jinsong Yang. 2021. "Research on Multi-Object Sorting System Based on Deep Learning" Sensors 21, no. 18: 6238. https://doi.org/10.3390/s21186238

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop