基于多层级网络的像素级抓取姿态估计
Pixel-Wise Grasp Pose Detection Based on Hierarchical Network
DOI: 10.12677/CSA.2023.131008, PDF,   
作者: 张志刚：广东工业大学自动化学院，广东 广州；程良伦：广东工业大学计算机学院，广东 广州
关键词: 机器人抓取；抓取检测；卷积神经网络；Robotic Grasping； Grasp Detection； Convolutional Neural Network
摘要: 为了解决在杂乱场景下从单视角图像中准确估计抓取位姿的问题，本文提出基于多层级特征的像素级端到端抓取检测网络。我们在全卷积神经网络中集成了多层级金字塔池化模块和多分支输出结构形成高精度抓取位姿检测网络，从而有效处理尺寸和位姿各异的未知物体在杂乱场景下的抓取问题。实验表明，我们的方法在Cornell抓取数据集上的理论抓取精度相比现有方法有明显提升；同时，在机械臂实物抓取实验上，我们的方法在多物体杂乱场景中以88.0%的平均抓取成功率实现了100%的抓取完成率。
Abstract: In order to address the problem of estimating grasp pose under cluttered scenes using single-view image, we proposed an end-to-end pixel-wise grasp detection network based on hierarchical features. We integrated a pyramid pooling module and multi-head structure into a fully convolutional neural network to form a high-precision grasp pose detection network, effectively handling the problem of predicting grasps for unknown objects with diverse sizes and poses in clutters. The experiments showed that our proposed method significantly outperforms existing methods in Cornell grasp dataset. Physical experiments on real robotic arms are also conducted, our method achieved average grasp success rate of 88.0% at 100% completion rate in the challenging grasping task in clutter with multiple unknown objects.
文章引用：张志刚, 程良伦. 基于多层级网络的像素级抓取姿态估计[J]. 计算机科学与应用, 2023, 13(1): 72-82. https://doi.org/10.12677/CSA.2023.131008

参考文献

[1] Redmon, J. and Angelova, A. (2015) Real-Time Grasp Detection Using Convolutional Neural Networks. Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), Seattle, 26-30 May 2015, 1316-1322. [Google Scholar] [CrossRef] 
[2] Lenz, I., Lee, H. and Saxena, A. (2015) Deep Learning for De-tecting Robotic Grasps. The International Journal of Robotics Research, 34, 705-724. [Google Scholar] [CrossRef] 
[3] Kumra, S. and Kanan, C. (2017) Robotic Grasp Detection Using Deep Convolutional Neural Networks. Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, 24-28 September 2017, 769-776. [Google Scholar] [CrossRef] 
[4] Morrison, D., Corke, P. and Leitner, J. (2018) Closing the Loop for Robotic Grasping: A Real-Time, Generative Grasp Synthesis Approach. [Google Scholar] [CrossRef] 
[5] Morrison, D., Corke, P. and Leitner, J. (2019) Learning Robust, Real-Time, Reactive Robotic Grasping. The International Journal of Robotics Research, 39, 183-201. [Google Scholar] [CrossRef] 
[6] Kumra, S., Joshi, S. and Sahin, F. (2020) Antipodal Robotic Grasping Using Generative Residual Convolutional Neural Network. Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, 24 October-24 January 2021, 9626-9633. [Google Scholar] [CrossRef] 
[7] Chu, F.J., Xu, R. and Vela, P.A. (2018) Real-World Mul-tiobject, Multigrasp Detection. IEEE Robotics and Automation Letters, 3, 3355-3362. [Google Scholar] [CrossRef] 
[8] Zhou, X., Lan, X., Zhang, H., Tian, Z., et al. (2018) Fully Con-volutional Grasp Detection Network with Oriented Anchor Box. Proceedings of the 2018 IEEE/RSJ International Con-ference on Intelligent Robots and Systems (IROS), Madrid, 1-5 October 2018, 7223-7230. [Google Scholar] [CrossRef] 
[9] He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[10] Zhao, H., Shi, J., Qi, X., Wang, X., et al. (2017) Pyramid Scene Pars-ing Network. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 6230-6239. [Google Scholar] [CrossRef] 
[11] Woo, S., Park, J., Lee, J.-Y. and Kweon, I.S. (2018) CBAM: Con-volutional Block Attention Module. 15th European Conference on Computer Vision, Munich, 8-14 September 2018, 1-17. [Google Scholar] [CrossRef] 
[12] Hu, J., Shen, L., Albanie, S., Sun, G., et al. (2020) Squeeze-and-Excitation Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 2011-2023. [Google Scholar] [CrossRef] 
[13] Yun, J., Moseson, S. and Saxena, A. (2011) Efficient Grasp-ing from RGBD Images: Learning Using a New Rectangle Representation. Proceedings of the 2011 IEEE International Conference on Robotics and Automation, Shanghai, 9-13 May 2011, 3304-3311.
[14] Zhang, H., Lan, X., Bai, S., Zhou, X., et al. (2019) ROI-Based Robotic Grasp Detection for Object Overlapping Scenes. Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, 3-8 November 2019, 4768-4775. [Google Scholar] [CrossRef] 
[15] Song, Y., Gao, L., Li, X. and Shen, W. (2020) A Novel Robotic Grasp Detection Method Based on Region Proposal Networks. Robotics and Computer-Integrated Manufactur-ing, 65, Article ID: 101963. [Google Scholar] [CrossRef]