Robotic Arm Visual Grasping Enhanced by an Improved U-Net Network
DOI:
https://doi.org/10.54097/fne1qc03Keywords:
Robotic Arm Vision-Based Grasping, U-Net, Efficient Channel Attention (ECA), Flexible Objects, Grasping Point OptimizationAbstract
This paper proposes a robotic arm vision-based grasping method utilizing an enhanced U-Net architecture and an Efficient Channel Attention (ECA) mechanism, aimed at addressing the localization challenges of soft belts in industrial automation grasping. Traditional approaches suffer from grasping point localization errors when handling non-rigid objects due to deformation and boundary ambiguity issues. This study enhances U-Net's feature extraction capabilities by embedding an ECA module, combined with image moment theory and edge analysis, achieving precise extraction of target geometric features and optimized grasping point selection. Experimental results demonstrate that the improved U-Net_ECA model achieves mIoU scores of 93.59% and 88.47% on the training and validation sets, respectively, significantly outperforming conventional approaches. Furthermore, the proposed grasp point localization algorithm effectively resolves positioning errors caused by object deformation, validating its practicality and robustness in industrial settings.
Downloads
References
[1] Chiu YJ, Yuan YY, Jian SR. Design of and research on the robot arm recovery grasping system based on machine vision. Journal of King Saud University-Computer and Information Sciences. 2024 Apr 1;36(4):102014.
[2] Yin X, Chen Y, Guo W, Yang Z, Chen H, Liao A, Yao D. Flexible grasping of robot arm based on improved Informed-RRT star. Chinese journal of engineering. 2025 Jan 25;47(1):113-20.
[3] Afzal W, Iqbal S, Tahira Z, Qureshi ME. Gesture control robotic arm using flex sensor. Applied and Computational Mathematics. 2017 Jan;6(4):171-6.
[4] Zhou J, Chen S, Wang Z. A soft-robotic gripper with enhanced object adaptation and grasping reliability. IEEE Robotics and automation letters. 2017 Jun 16;2(4):2287-93.
[5] Domae Y. Recent trends in the research of industrial robots and future outlook. Journal of Robotics and Mechatronics. 2019 Feb 20;31(1):57-62.
[6] Sekkat H, Tigani S, Saadane R, Chehri A. Vision-based robotic arm control algorithm using deep reinforcement learning for autonomous objects grasping. Applied Sciences. 2021 Aug 27;11(17):7917.
[7] Li L, Cherouat A, Snoussi H, Wang T. Grasping with occlusion-aware ally method in complex scenes. IEEE Transactions on Automation Science and Engineering. 2024 Aug 1.
[8] Hui NM, Wu XH, Han XW, Wu BJ. A robotic arm visual grasp detection algorithm combining 2D images and 3D point clouds. Applied Mechanics and Materials. 2024 Mar 5;919:209-23.
[9] Liu C, Shi K, Zhou K, Wang H, Zhang J, Dong H. Rgbgrasp: Image-based object grasping by capturing multiple views during robot arm movement with neural radiance fields. IEEE Robotics and Automation Letters. 2024 May 2;9(6):6012-9.
[10] Ilangovan P, Ilangovan, K. Meena, M. S. Begum: Weed Easy Extraction Using Deep Learning With a Robotic System, Proceedings of the International Conference on Physics and Engineering (Virtual Conference, December 1, 2024), Vol. 2923, p. 012003.
[11] O. Ronneberger, P. Fischer, T. Brox: U-Net: Convolutional Networks for Biomedical Image Segmentation, Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (Munich, Germany, October 5-9, 2015). Vol. 9351, p. 234.
[12] Srinivasan S, Durairaju K, Deeba K, Mathivanan SK, Karthikeyan P, Shah MA. Multimodal biomedical image segmentation using multi-dimensional U-convolutional neural network. BMC Medical Imaging. 2024 Feb 8;24(1):38.
[13] Pacal I, Celik O, Bayram B, Cunha A. Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification. Cluster Computing. 2024 Nov;27(8):11187-212.
[14] Teague MR. Image analysis via the general theory of moments. Journal of the optical society of America. 1980 Aug 1;70(8):920-30.
[15] Liu G, Li H, Yang L. A topology preserving method of evolving contours based on sparsity constraint for object segmentation. IEEE Access. 2017 Sep 18;5:19971-82.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
