基于改进Cascade R-CNN模型的机器人抓取检测研究

doi:10.12068/j.issn.1005-3026.2023.06.006

摘要/Abstract

摘要： 为提高多物体抓取检测网络的抓取检测准确率，提出一种基于改进Cascade R-CNN模型的机械臂抓取检测算法.首先，引入ResNeXt结构能够在不加大网络设计难度的前提下提高了模型的准确率；引入带空洞卷积的空间金字塔池化模块以解决分辨率较低的问题；接着对抓取框回归分支和角度分类分支以分治方法进行优化.其次，针对多物体抓取数据集缺乏的问题，构建多目标抓取数据集(multi-object grasping dataset，MOGD)，有效地扩充了多物体抓取检测数据集.最后，基于改进Cascade R-CNN模型设计抓取检测网络，实验结果表明，改进后的算法效率更高，PI-Cascade R-CNN实验准确率为93%，较Cascade R-CNN提升1.5个百分点.

关键词: 抓取检测；空洞卷积；Cascade R-CNN；多物体检测；机器人抓取

Abstract: In order to improve the grasping detection accuracy of the multi-object grasping detection network， a robotic arm grasping detection algorithm based on the improved Cascade R-CNN model is proposed. Firstly， the introduction of the ResNeXt structure can improve the accuracy of the model without increasing the difficulty of network design. The atrous spatial pyramid pooling module is introduced to solve the problem of low resolution. Then， the grasping box regression branch and the angle classification branch are optimized by the divide and conquer method. Secondly， aiming at the lack of multi-object grasping datasets， a multi-object grasping dataset (MOGD) is constructed， which effectively expands the multi-object grasping detection dataset. Finally， a grasping detection network is designed based on the improved Cascade R-CNN model. The experimental results show that the improved algorithm is more efficient. The experimental accuracy of the PI-Cascade R-CNN is 93 %， which is 1.5 percentage higher than that of the Cascade R-CNN.

Key words: grasping detection; atrous convolution; Cascade R-CNN; multi-object detection; robotic grasping

中图分类号:

TP242.6

姜杨，赵峰禹，陈枭. 基于改进Cascade R-CNN模型的机器人抓取检测研究[J]. 东北大学学报（自然科学版）, 2023, 44(6): 799-807.

JIANG Yang， ZHAO Feng-yu， CHEN Xiao. Research on Robotic Grasping Detection Based on Improved Cascade R-CNN Model[J]. Journal of Northeastern University(Natural Science), 2023, 44(6): 799-807.

参考文献

[1]Lenz I，Lee H，Saxena A.Deep learning for detecting robotic grasps［J］.The International Journal of Robotics Research，2015，34(4/5):705-724.
[2]Wei J，Liu H，Yan G，et al.Robotic grasping recognition using multi-modal deep extreme learning machine［J］.Multidimensional Systems and Signal Processing，2017，28(3):817-833.
[3]Wang Z，Li Z，Wang B，et al.Robot grasp detection using multimodal deep convolutional neural networks［J］.Advances in Mechanical Engineering，2016，8(9):1687814016668077.
[4]李秀智，李家豪，张祥银，等.基于深度学习的机器人最优抓取姿态检测方法［J］.仪器仪表学报，2020，41(5):108-117.(Li Xiu-zhi，Li Jia-hao，Zhang Xiang-yin，et al.Robot optimal grasping posture detection method based on deep learning［J］.Instruments Journal，2020，41(5):108-117.)
[5]崔少伟，魏俊杭，王睿，等.基于视触融合的机器人抓取滑动检测［J］.华中科技大学学报(自然科学版)，2020，48(1):98-102.(Cui Shao-wei，Wei Jun-hang，Wang Rui，et al.Robot grasping sliding detection based on visual-tactile fusion［J］.Journal of Huazhong University of Science and Technology (Natural Science Edition)，2020，48(1):98-102.)
[6]伍广彬.基于领域自适应学习的机器人多目标物体抓取识别算法研究［D］.哈尔滨:哈尔滨工业大学，2021.(Wu Guang-bin.Research on robot multi-target object grasping recognition algorithm based on domain adaptive learning［D］.Harbin :Harbin Institute of Technology，2021.)
[7]Guo D，Sun F，Liu H，et al.A hybrid deep architecture for robotic grasp detection［C］//2017 IEEE International Conference on Robotics and Automation(ICRA).Singapore: IEEE，2017:1609-1614.
[8]夏晶，钱堃，马旭东，等.基于级联卷积神经网络的机器人平面抓取位姿快速检测［J］.机器人，2018，40(6):794-802.(Xia Jing，Qian Kun，Ma Xu-dong，et al.Rapid detection of robot plane grasping pose based on cascaded convolutional neural network［J］.Robot，2018，40(6):794-802.)
[9]喻群超，尚伟伟，张驰.基于三级卷积神经网络的物体抓取检测［J］.机器人，2018，40(5):762-768.(Yu Qun-chao，Shang Wei-wei，Zhang Chi.Object grasping detection based on three-level convolutional neural network［J］.Robot，2018，40(5):762-768.)
[10]Depierre A，Dellandréa E，Chen L.Jacquard:a large scale dataset for robotic grasp detection［C］//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).Madrid，Spain:IEEE，2018:3511-3516.
[11]Morrison D，Corke P，Leitner J.Learning robust，real-time，reactive robotic grasping［J］.The International Journal of Robotics Research，2020，39(2/3):183-201.
[12]Saxena A，Driemeyer J，Ng A Y.Robotic grasping of novel objects using vision［J］.The International Journal of Robotics Research，2008，27(2):157-173.
[13]Le Q V，Kamm D，Kara A F，et al.Learning to grasp objects with multiple contact points［C］//2010 IEEE International Conference on Robotics and Automation.Anchorage: IEEE，2010:5062-5069.
[14]Wang P，Ye F，Chen X，et al.Datanet:deep learning based encrypted network traffic classification in SDN home gateway［J］.IEEE Access，2018，6:55380-55391.
[15]Deng Y，Ren Z，Kong Y，et al.A hierarchical fused fuzzy deep neural network for data classification［J］.IEEE Transactions on Fuzzy Systems，2016，25(4):1006-1012.
[16]Wang K，Zhang D，Li Y，et al.Cost-effective active learning for deep image classification［J］.IEEE Transactions on Circuits and Systems for Video Technology，2016，27(12):2591-2600.
[17]Girshick R，Donahue J，Darrell T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus，2014:580-587.
[18]Girshick R.Fast R-CNN［C］//Proceedings of the IEEE International Conference on Computer Vision.Santiago，2015:1440-1448.
[19]Ren S，He K，Girshick R，et al.Faster R-CNN:towards real-time object detection with region proposal networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2016，39(6):1137-1149.
[20]Redmon J，Angelova A.Real-time grasp detection using convolutional neural networks［C］//2015 IEEE International Conference on Robotics and Automation(ICRA).Seattle，WA:IEEE，2015:1316-1322.
[21]Park D，Chun S Y.Classification based grasp detection using spatial transformer network［J］.arXiv Preprint arXiv:1803.01356，2018.
[22]Asif U，Tang J，Harrer S.GraspNet:an efficient convolutional neural network for real-time grasp detection for low-powered devices［C］//International Joint Conference on Artificial Intelligence.Stockholm:CVPR，2018:4875-4882.
[23]Cai Z，Vasconcelos N.Cascade R-CNN:delving into high quality object detection［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City:CVPR，2018:6154-6162.
[24]Li A，Yang X，Zhang C.Rethinking classification and localization for cascade R-CNN［J］.arXiv Preprint arXiv:1907.11914，2019.
[25]Chen L C，Papandreou G，Kokkinos I，et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs［J］.arXiv Preprint arXiv:1412.7062，2014.
[26]Xie S，Girshick R，Dollár P，et al.Aggregated residual transformations for deep neural networks［C］//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu，2017:1492-1500.
[27]Saxena A，Driemeyer J，Kearns J，et al.Robotic grasping of novel objects［C］//Proceedings of the 19th International Conference on Neural Information Processing Systems.Vancouver，2006:1209-1216.
[28]Jiang Y，Moseson S，Saxena A.Efficient grasping from RGBD images:learning using a new rectangle representation［C］//2011 IEEE International Conference on Robotics and Automation.Shanghai:IEEE，2011:3304-3311.
[29]Tsai R Y，Lenz R K.A new technique for fully autonomous and efficient 3D robotics hand/eye calibration［J］.IEEE Transactions on Robotics and Automation，1989，5(3):345-358.