Hostname: page-component-7857688df4-zx5rz Total loading time: 0 Render date: 2025-11-16T10:44:06.317Z Has data issue: false hasContentIssue false
  • English
  • Français

Research on robotic grasp detection using improved generative convolution neural network with Gaussian representation

Published online by Cambridge University Press:  14 November 2025

Zhanglai Chen Open the ORCID record for Zhanglai Chen [Opens in a new window] ,
Xu Zhang  and
Dawei Tu
Zhanglai Chen
Affiliation:
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
Xu Zhang
Affiliation:
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
Dawei Tu*
Affiliation:
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
*
Corresponding author: Dawei Tu; Email: tdw@shu.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

Grasp detection is a significant research direction in the field of robotics. Traditional analysis methods typically require prior knowledge of the object parameters, limiting grasp detection to structured environments and resulting in suboptimal performance. In recent years, the generative convolutional neural network (GCNN) has gained increasing attention, but they suffer from issues such as insufficient feature extraction capabilities and redundant noise. Therefore, we proposed an improved method for the GCNN, aimed at enabling fast and accurate grasp detection. First, a two-dimensional (2D) Gaussian kernel was introduced to re-encode grasp quality to address the issue of false positives in grasp rectangular metrics, emphasizing high-quality grasp poses near the central point. Additionally, to address the insufficient feature extraction capabilities of the shallow network, a receptive field module was added at the neck to enhance the network’s ability to extract distinctive features. Furthermore, the rich feature information in the decoding phase often contains redundant noise. To address this, we introduced a global-local feature fusion module to suppress noise and enhance features, enabling the model to focus more on target information. Finally, relevant evaluation experiments were conducted on public grasping datasets, including Cornell, Jacquard, and GraspNet-1 Billion, as well as in real-world robotic grasping scenarios. All results showed that the proposed method performs excellently in both prediction accuracy and inference speed and is practically feasible for robotic grasping.

Keywords

robot graspinggrasp detectiongenerative convolutional neural networktwo-dimensional gaussian kernel

Information

Type
Research Article
Information
Robotica , First View , pp. 1 - 21
Copyright
© The Author(s), 2025. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Dong, M. and Zhang, J., “A review of robotic grasp detection technology,” Robotica 41(12), 3846–3885 (2023).10.1017/S0263574723001285CrossRefGoogle Scholar
Yun, J., Jiang, D., Huang, L., Tao, B., Liao, S., Liu, Y., Liu, X., Li, G., Chen, D. and Chen, B., “Grasping detection of dual manipulators based on Markov decision process with neural network,” Neural Netw. 169, 778–792 (2024).10.1016/j.neunet.2023.09.016CrossRefGoogle Scholar
Huang, X., Halwani, M., Muthusamy, R., Ayyad, A., Swart, D., Seneviratne, L., Gan, D. and Zweiri, Y., “Real-time grasping strategies using event camera,” J. Intell. Manuf. 33(2), 593–615 (2022).10.1007/s10845-021-01887-9CrossRefGoogle Scholar
Marwan, Q. M., Chua, S. C. and Kwek, L. C., “Comprehensive review on reaching and grasping of objects in robotics,” Robotica 39(10), 1849–1882 (2021).10.1017/S0263574721000023CrossRefGoogle Scholar
Du, G., Wang, K., Lian, S. and Zhao, K., “Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: A review,” Artif. Intell. Rev. 54(3), 1677–1734 (2021).10.1007/s10462-020-09888-5CrossRefGoogle Scholar
Chen, L., Niu, M., Yang, J., Qian, Y., Li, Z., Wang, K., Yan, T. and Huang, P., “Robotic grasp detection using structure prior attention and multiscale features,” IEEE Trans. Syst. Man Cybern. -Syst. 54(11), 7039–7053 (2024).10.1109/TSMC.2024.3446841CrossRefGoogle Scholar
Zhu, M., Derpanis, K. G., Yang, Y., Brahmbhatt, S., Zhang, M., Phillips, C., Lecce, M. and Daniilidis, K., "Single Image 3D Object Detection and Pose Estimation for Grasping," In: 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China (2014).Google Scholar
Ten Pas, A. and Platt, R., “Using geometry to detect grasp poses in 3d point clouds,” Robotics Research. 2, 307–324 (2018).10.1007/978-3-319-51532-8_19CrossRefGoogle Scholar
Newbury, R., Gu, M., Chumbley, L., Mousavian, A., Eppner, C., Leitner, J. C., Bohg, J., Morales, A., Asfour, T., Kragic, D., Fox, D. and Cosgun, A., “Deep learning approaches to grasp synthesis: A review,” IEEE Trans. Robot. 39(5), 3994–4015 (2023).10.1109/TRO.2023.3280597CrossRefGoogle Scholar
Kushwaha, V., Shukla, P. and Nandi, G. C., “Vision-based intelligent robot grasping using sparse neural network,” Int J Intell Robot Appl. 9, 1214–1227 (2025).10.1007/s41315-025-00428-4CrossRefGoogle Scholar
Kim, D., Li, A. and Lee, J., “Stable robotic grasping of multiple objects using deep neural networks,” Robotica 39(4), 735–748 (2021).10.1017/S0263574720000703CrossRefGoogle Scholar
Yun, J., Moseson, S. and Saxena, A., "Efficient Grasping from RGBD Images: Learning Using a New Rectangle Representation," In: 2011 IEEE International Conference on Robotics and Automation, Shanghai, China (2011).Google Scholar
Lenz, I., Lee, H. and Saxena, A., “Deep learning for detecting robotic grasps,” Int. J. Robot. Res. 34(4-5), 705–724 (2015).10.1177/0278364914549607CrossRefGoogle Scholar
Redmon, J. and Angelova, A., "Real-time Grasp Detection Using Convolutional Neural Networks," In: 2015 IEEE International Conference on Robotics and Automation (ICRA), Washington, USA (2015).Google Scholar
Chu, F.-J., Xu, R. and Vela, P. A., “Deep grasp: Detection and localization of grasps with deep neural networks,” ArXiv. abs/1802.00520, (2018).Google Scholar
Zhou, X., Lan, X., Zhang, H., Tian, Z., Zhang, Y. and Zheng, N., "Fully Convolutional Grasp Detection Network with Oriented Anchor Box," In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain (2018).Google Scholar
Morrison, D., Corke, P. and Leitner, J., “Learning robust, real-time, reactive robotic grasping,” Int. J. Robot. Res. 39(2-3), 183–201 (2020).10.1177/0278364919859066CrossRefGoogle Scholar
Kumra, S., Joshi, S. and Sahin, F., "Antipodal Robotic Grasping Using Generative Residual Convolutional Neural Network," In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, Nevada, USA (2020).Google Scholar
Kumra, S., Joshi, S. and Sahin, F., “GR-ConvNet v2: A real-time multi-grasp detection network for robotic grasping,” Sensors 22(16), 6208 (2022).10.3390/s22166208CrossRefGoogle Scholar
Prew, W., Breckon, T., Bordewich, M. and Beierholm, U., "Evaluating Gaussian Grasp Maps for Generative Grasping Models," In: 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy (2022).Google Scholar
Cao, H., Chen, G., Li, Z., Feng, Q., Lin, J. and Knoll, A., “Efficient grasp detection network with Gaussian-based grasp representation for robotic manipulation,” IEEE/ASME Trans. Mechatron. 28(3), 1384–1394 (2022).10.1109/TMECH.2022.3224314CrossRefGoogle Scholar
Liu, S., Huang, D. and Wang, Y., “Receptive Field Block Net for Accurate and Fast Object Detection,” In: Computer Vision – ECCV 2018, Cham, (2018).Google Scholar
Hu, J., Shen, L. and Sun, G., "Squeeze-and-Excitation Networks," In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah (2018).Google Scholar
Depierre, A., Dellandréa, E. and Chen, L., "Jacquard: A Large Scale Dataset for Robotic Grasp Detection," In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain (2018).Google Scholar
Fang, H. S., Wang, C., Gou, M. and Lu, C., "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping," In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA (2020).Google Scholar
Kumra, S. and Kanan, C., "Robotic Grasp Detection Using Deep Convolutional Neural Networks," In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada (2017).Google Scholar
Karaoguz, H. and Jensfelt, P., "Object Detection Approach for Robot Grasp Detection," In: 2019 International Conference on Robotics and Automation (ICRA), Montreal, Canada (2019).Google Scholar
Chen, L., Huang, P., Li, Y. and Meng, Z., “Edge-dependent efficient grasp rectangle search in robotic grasp detection,” IEEE/ASME Trans. Mechatron. 26(6), 2922–2931 (2021).10.1109/TMECH.2020.3048441CrossRefGoogle Scholar
Yu, S., Zhai, D. H., Xia, Y., Wu, H. and Liao, J., “SE-ResUNet: A novel robotic grasp detection method,” IEEE Rob. Autom. Lett. 7(2), 5238–5245 (2022).10.1109/LRA.2022.3145064CrossRefGoogle Scholar
Zhai, D. H., Yu, S. and Xia, Y., “FANet: Fast and accurate robotic grasp detection based on keypoints,” IEEE Trans. Autom. Sci. Eng. 21(3), 2974–2986 (2024).10.1109/TASE.2023.3272664CrossRefGoogle Scholar
Wang, S., Zhou, Z. and Kan, Z., “When transformer meets robotic grasping: Exploits context for efficient grasp detection,” IEEE Rob. Autom. Lett. 7(3), 8170–8177 (2022).10.1109/LRA.2022.3187261CrossRefGoogle Scholar
Xi, H., Li, S. and Liu, X., “A pixel-level grasp detection method based on efficient grasp aware network,” Robotica 42(9), 3190–3210 (2024).10.1017/S0263574724001358CrossRefGoogle Scholar
Zhou, Z., Zhang, X., Ran, L., Han, Y. and Chu, H., "DSC-GraspNet: A Lightweight Convolutional Neural Network for Robotic Grasp Detection," In: 2023 9th International Conference on Virtual Reality (ICVR), Xianyang, China (2023).Google Scholar
Johns, E., Leutenegger, S. and Davison, A. J., "Deep learning a grasp function for grasping under gripper pose uncertainty," In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea (2016).Google Scholar
Guo, C., Zhu, C., Liu, Y., Huang, R., Cao, B., Zhu, Q., Zhang, R. and Zhang, B., “End-to-end lightweight transformer-based neural network for grasp detection towards fruit robotic handling,” Comput. Electron. Agric. 221, 109014 (2024).10.1016/j.compag.2024.109014CrossRefGoogle Scholar
Zhu, Z., Huang, S., Xie, J., Meng, Y., Wang, C. and Zhou, F., “A refined robotic grasp detection network based on coarse-to-fine feature and residual attention,” Robotica 43(2), 415–432 (2025).10.1017/S0263574724001929CrossRefGoogle Scholar
Yan, Y., Tong, L., Song, K., Tian, H., Man, Y. and Yang, W., “SISG-Net: Simultaneous instance segmentation and grasp detection for robot grasp in clutter,” Adv. Eng. Inform. 58, 102189 (2023).10.1016/j.aei.2023.102189CrossRefGoogle Scholar