Abstract
The pillow spring grabbing robot is the core module of the intelligent assembly of railway wagon pillow springs in the overhauling workshop. The pillow spring end face and the center of the outer spring notch need to be quickly detected and accurately positioned. To address the shortage of hardware computing power in pillow spring assembly systems, a lightweight object detection YOLO model based on MobileNetv3 and GhostNet network architecture is proposed in this paper: M-G-YOLOv5s. The COCO2017 dataset and custom dataset are employed for model training and validation. The results indicate that compared to the YOLOv5s model, the M-G-YOLOv5s model reduces the model size by 81%, decreases the model parameter count by 83%, and improves the detection speed by 1.7 times. Based on the M-G-YOLOv5s algorithm, a novel image visual serving control method is proposed to address the automatic positioning problem of pillow springs and improve the efficiency of grabbing operations. This method is based on the mixed corner point features composed of the corner points of the pillow end object detection box and the pillow spring gap center. The visual servo positioning and grasping comparison experiments are carried out on the pillow spring grasping robot platform. The results show that the proposed M-G-YOLOv5s detection model can meet the grasping requirements of the pillow spring assembly system based on IBVS. The research findings have been successfully applied to the development of the pillow spring assembly manipulator for railway wagon bogie.
Similar content being viewed by others
Data Availability
Not applicable.
Code Availability
Not applicable.
References
Xin, J.S., Shang, Y.J., Xue, H., et al.: Dynamic reliability sensitivity analysis of bolster spring for heavy-haul Freight Car[J]. J. Lanzhou Jiaotong Univ. 39(06), 86–91 (2020)
Li, C.S., Luo, S.H., Cole, C., et al.: Bolster spring fault detection strategy for heavy haul wagons[J]. Veh. Syst. Dyn. Int. J. Veh. Mech. Mobil. 56(10), 1604–1621 (2018)
Li, D.F., Liu, H.L., Wei, T., Zhou, J.Y.: Robotic grasping method of bolster spring based on image-based visual servoing with YOLOv3 object detection algorithm[J]. Proc. Inst. Mech. Eng. C J. Mech. Eng. Sci. 236(3), 1780–1795 (2022)
Liu, H.L., Li, D., Jiang, B., et al.: MGBM-YOLO: a faster light-weight object detection model for robotic grasping of bolster spring based on image-based visual servoing[J]. J. Intell. Rob. Syst. 104(4), 1–17 (2022)
Xu, D.: A tutorial for monocular visual servoing. Acta Aotumatica Sinica. 44(10), 1729–1746 (2018)
Chaumette, F., Hutchinson, S.: Visual servo control, Part I: Basic approaches[J]. IEEE Robot. Autom. Mag. 13(4), 82–90 (2006)
Malis, E., Ezio, S., Chaumette, F., et al.: 2–1/2-D visual servoing[J]. IEEE Trans. Robot. Autom. 15, 238–250 (1999)
Espiau, B.: Effect of Camera Calibration Errors on Visual Servoing in Robotics[C]// Preprints of the Third International Symposium on Experimental Robotics, pp 182–192 (1993)
Yang, Y., Song, Y., Pan, H., et al.: Visual servo simulation of EAST articulated maintenance arm Robot[J]. Fusion Eng. Des. 104(Mar.), 28–33 (2016)
Dong, G.Q., Zhu, Z.H.: Kinematics-based incremental visual servo for robotic capture of non-cooperative Target[J]. Robot. Auton. Syst. 112, 221–228 (2019)
Xie, W.F., Li, Z., Tu, X.W., et al.: Switching control of image-based visual servoing with laser pointer in robotic manufacturing systems[J]. IEEE Trans. Industr. Electron. 56(2), 520–529 (2009)
Ibarguren, A., Martínez-Otzeta, J.M., Maurtua, I.: Particle filtering for industrial 6DOF visual servoing[J]. J. Intell. Rob. Syst. 74(3), 689–696 (2014)
Zhao, K., Wang, Y., Zuo, Y., et al.: Palletizing robot positioning bolt detection based on improved YOLO-V3[J]. J. Intell. Rob. Syst. 104(3), 1–12 (2022)
Howard, A., Sandler, M., Chu, G., et al.: Searching for Mobilenetv3[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, pp 1314–1324 (2020)
Sandler, M., Howard, A., Zhu, M., et al.: Mobilenetv2: Inverted Residuals and Linear Bottlenecks[C]//. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4510-4520 (2018)
Howard, A., Sandler, M., Chu, G., et al.: Searching for Mobilenetv3[C]// 2019 IEEE/ CVF International Conference on Computer Vision (I CCV). IEEE, pp 1314–1324 (2020)
Zhang, X., Zhou, X., Lin, M., et al.: ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices[C]// 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 6848-6856 (2018)
Ma, N., Zhang, X., Zheng, H.T., et al.: ShuffleNet v2: Practical Guidelines for Efficient CNN Architecture Design[C]// European Conference on Computer Vision (ECCV). Springer, Cham, pp 116–131 (2018)
Han, K., Wang, Y., Tian, Q., et al.: GhostNet: More Features from Cheap Operations[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1580–1589 (2020)
Kragic, D., Christensen, H.I.: A framework for visual servoing[J]. Lect. Notes Comput. Sci. 22, 345–354 (2003)
Corke, P.: Robotics, Vision and Control[M]// Robotics, Vision and Control - Fundamental Algorithms in MATLAB®. Springer Berlin Heidelberg (2011)
Funding
This work is supported by National Natural Science Foundation of China under Grant 52275030.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study. Hao Tian: Software, Experimental validation, Data curation, Writing-Reviewing and Editing. Wenhai Wu: Conceptualization and Funding Acquisition. Huanlong Liu: Conceptualization, Methodology and Funding Acquisition. Yadong Liu: Data curation, Visualization. Jincheng Zou: Investigation. Yifei Fei: Investigation and Edition.
Corresponding author
Ethics declarations
Conflicts of Interest
No conflict of interest exits in the submission of this article, and the article is approved by all authors for publication.
Ethics Approval
Not applicable.
Consent to Participate
Not applicable.
Consent for Publication
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Tian, H., Wu, W., Liu, H. et al. Robotic Grasping of Pillow Spring Based on M-G-YOLOv5s Object Detection Algorithm and Image-Based Visual Serving. J Intell Robot Syst 109, 67 (2023). https://doi.org/10.1007/s10846-023-01989-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10846-023-01989-x