Research on 3D object optimal grasping method based on cascaded Faster RCNN

被引：0
|
作者：
Chen D. [1 ]
Lin Q. [1 ]
机构：
[1] College of Electrical engineering and automation, Fuzhou University, Fuzhou
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2019年 / 40卷 / 04期
关键词：
Deep learning; Faster RCNN model; Object detection; Optimal grasping;
D O I：
10.19650/j.cnki.cjsi.J1804463
中图分类号：
学科分类号：
摘要：
The difficulty of robot in 3D object recognition and optimal grasping lies in the complex background environment and the irregular shape of the target object. It requires the robot to determine the position and pose of the optimal grasping part of the target while recognizing different 3D targets like human. One kind of deep learning method based on the cascaded faster region-based convolutional neural networks (RCNN) model is proposed to identify the target object and its optimal grasping pose. The improved Faster RCNN model is proposed at the first level, which can recognize small target objects and accurately locate them in the image. Then, a faster RCNN model at the second level is designed to find the optimal grasping pose of the target object recognized by the previous level to realize the optimal grasping of the robot. Experimental results show that the method proposed in this paper can find the object accurately and determine its optimal grasping pose. © 2019, Science Press. All right reserved.
引用
收藏
页码：229 / 237
页数：8
相关论文
共 16 条
  • [1] Pi S.Y., Tang H., Xiao N.F., Graspable object recognition based on full convolution deep learning model, Journal of Chongqing University of Technology (Natural Science), 32, 2, pp. 166-173, (2018)
  • [2] Varley J., Weisz J., Weiss J., Et al., Generating multi-fingered robotic grasps via deep learning, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4415-4420, (2015)
  • [3] El-Khoury S., Sahbani A., A new strategy combining empirical and analytical approaches for grasping unknown 3D objects, Robotics and Autonomous Systems, 58, 5, pp. 497-507, (2010)
  • [4] Pelossof R., Miller A., Allen P., Et al., An SVM learning approach to robotic grasping, IEEE International Conference on Robotics & Automation, 4, 4, pp. 3512-3518, (2004)
  • [5] Kumar R., Hanson A.R., Robust methods for estimating pose and a sensitivity analysis, Computer Vision and Image Understanding, 60, 3, pp. 313-342, (1994)
  • [6] Lenz I., Lee H., Saxena A., Deep learning for detecting robotic grasps, International Journal of Robotics Research, 34, 4-5, pp. 705-724, (2015)
  • [7] Redmon J., Divvala S., Girshick R., Et al., You only look once: Unified, real-time object detection, IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, (2016)
  • [8] Liu W., Anguelov D., Erhan D., Et al., SSD: Single shot multibox detector, European Conference on Computer Vision, pp. 21-37, (2016)
  • [9] Ren S., He K., Girshick R., Et al., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Transaction on Pattern Analysis and Machine Intelligence, 6, pp. 1137-1149, (2017)
  • [10] Yuan G.L., Yin K.Y., Li Q.X., Research on vehicle target detection in aerial images based on migration learning, Electronic Measurement Technology, 41, 22, pp. 77-81, (2018)
12