An effective method for grasp planning on objects with complex geometry combining human experience and analytical approach

一种基于经验与分析相结合的抓取规划方法

Abstract

In this paper, an effective method for identifying the graspable components of objects with complex geometry is proposed for grasp planning based on human experience. Instead of focusing on individual objects, our method identifies graspable components on the category level under the assumption that geometrically alike objects share similar graspable components. Firstly, employing a modified SHOT descriptor, a fast KNN-based method is developed for object categorization. Then, the graspable components are identified by adopting a learning framework based on human experience. Afterwards, a fast analytical grasp planning method is proposed which comprises of contact points exaction and hand kinematics calculation. Finally, a regression model based on the extreme learning method (ELM) is built which inputs the desired contact points and the wrist orientation and outputs the wrist position. This approach is time-saving comparing with the optimization method. The simulations and experiments demonstrate the effectiveness of the proposed approach by realizing grasps on the graspable components of human choice for objects with complex geometry.

创新点

本文提出一种有效的基于人类经验识别复杂形状物体可抓取部位的方法。假设形状相似物体(功能也相似)的可抓取部位也相似, 所提方法能够在物体类别层面上识别可抓取部位。首先, 算法对SHOT三维形状描述子进行改进, 提出一种基于KNN的物体分类方法, 并实现可抓取部位的识别; 在此基础上, 提出一种快速的抓取规划方法, 包括力封闭点的提取与手运动学求解; 最后, 利用极限学习机(ELM), 建立抓取点、手腕方向与位置之间的回归模型。这种方法比运动学求解的方法更节省时间。所提算法的有效性在仿真与机器人平台上得到验证。

This is a preview of subscription content, access via your institution.

References

  1. 1

    Lin G D, Li Z J, Liu L, et al. Development of multi-fingered dexterous hand for grasping manipulation. Sci China Inf Sci, 2014, 57: 120208

    Google Scholar 

  2. 2

    Li Z J, Deng S M, Su C Y, et al. Decentralized adaptive control of cooperating mobile manipulators with disturbance observers. IET Control Theory Appl, 2014, 8: 515–521

    MathSciNet  Article  Google Scholar 

  3. 3

    Li Z J, Ge S S, Liu S B. Contact-force distribution optimization and control for quadruped robots using both gradient and adaptive neural networks. IEEE Trans Neural Netw Learn Syst, 2014, 25: 1460–1473

    Article  Google Scholar 

  4. 4

    Li Z J, Xiao S T, Ge S S, et al. Constrained multilegged robot system modeling and fuzzy control with uncertain kinematics and dynamics incorporating foot force. IEEE Trans Syst Man Cybern-Syst, 2015, 99: 1–14

    Article  Google Scholar 

  5. 5

    El-Khoury S, Sahbani A. A new strategy combining empirical and analytical approaches for grasping unknown 3d objects. Robot Auton Syst, 2010, 58: 497–507

    Article  Google Scholar 

  6. 6

    Guo D, Sun F C, Liu C F. A system of robotic grasping with experience acquisition. Sci China Inf Sci, 2014, 57: 120202

    Google Scholar 

  7. 7

    Miller A T, Knoop S, Christensen H I, et al. Automatic grasp planning using shape primitives. In: Proceedings of IEEE International Conference on Robotics and Automation, Taipei, 2003. 1824–1829

    Google Scholar 

  8. 8

    Novotni M, Klein R. 3d zernike descriptors for content based shape retrieval. In: Proceedings of ACM Symposium on Solid Modeling and Applications, Washington, 2003. 216–225

    Google Scholar 

  9. 9

    Johnson A E, Hebert M. Using spin images for efficient object recognition in cluttered 3d scenes. IEEE Trans Patt Anal Mach Intell, 1999, 21: 433–449

    Article  Google Scholar 

  10. 10

    Körtgen M, Park G J, Novotni M, et al. 3d shape matching with 3d shape contexts. In: Proceedings of the 7th Central European Seminar on Computer Graphics, Budmerice, 2003

    Google Scholar 

  11. 11

    Bohg J, Kragic D. Learning grasping points with shape context. Robot Auton Syst, 2010, 58: 362–377

    Article  Google Scholar 

  12. 12

    Alexandre L A. 3D descriptors for object and category recognition: a comparative evaluation. In: Proceedings of IEEE Internatinal Conference on Intelligent Robots and Systems, Vilamoura, 2012. 1–6

    Google Scholar 

  13. 13

    Gori I, Pattacini U, Tikhanoff V, et al. Three-finger precision grasp on incomplete 3d point clouds. In: Proceedings of IEEE International Conference on Robotics and Automation, Hong Kong, 2014. 5366–5373

    Google Scholar 

  14. 14

    Pelossof R, Miller A, Allen P, et al. An SVM learning approach to robotic grasping. In: Proceedings of IEEE Internatinal Conference on Robotics and Automation, New Orleans, 2004. 3512–3518

    Google Scholar 

  15. 15

    Huang B D, El-Khoury S, Li M, et al. Learning a real time grasping strategy. In: Proceedings of IEEE International Conference on Robotics and Automation, Karlsruhe, 2013. 593–600

    Google Scholar 

  16. 16

    Aleotti J, Caselli S. A 3d shape segmentation approach for robot grasping by parts. Robot Auton Syst, 2012, 60: 358–366

    Article  Google Scholar 

  17. 17

    Hübner K, Kragic D. Grasping by parts: robot grasp generation from 3d box primitives. In: Proceedings of IEEE International Conference on Cognitive Systems, ETH Zurich, 2010

    Google Scholar 

  18. 18

    Tombari F, Salti S, Stefano L. Unique signatures of histograms for local surface description. In: Proceedings of European Conference on Computer Vision. Berlin: Springer, 2010. 356–369

    Google Scholar 

  19. 19

    Chen X, Ishwaran H. Random forests for genomic data analysis. Genomics, 2012, 99: 323–329

    Article  Google Scholar 

  20. 20

    Park C H, Kim S B. Sequential random k-nearest neighbor feature selection for high-dimensional data. Expert Syst Appl, 2015, 42: 2336–2342

    Article  Google Scholar 

  21. 21

    Nguyen V D. Constructing force-closure grasps. Int J Robot Res, 1988, 7: 240–245

    Article  Google Scholar 

  22. 22

    Kennedy J, Eberhart R. Particle swarm optimization. In: Proceedings of Internatinal Conference on Neural Networks, Perth, 1995. 1942–1948

    Google Scholar 

  23. 23

    Huang G B, Zhou H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B-Cybern, 2012, 42: 513–529

    Article  Google Scholar 

  24. 24

    Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications. Neurocomputing, 2006, 70: 489–501

    Article  Google Scholar 

  25. 25

    Grana C, Davolio M, Cucchiara R. Similarity-based retrieval with mpeg-7 3d descriptors: performance evaluation on the princeton shape benchmark. In: Proceedings of the 1st International DELOS Conference, Pisa, 2007. 308–317

    Google Scholar 

  26. 26

    Lai K, Bo L F, Ren X F, et al. A large-scale hierarchical multi-view RGB-D object dataset. In: Proceedings of IEEE International Conference on Robotics and Automation, Shanghai, 2011. 1817–1824

    Google Scholar 

  27. 27

    Malvezzi M, Gioioso G, Salvietti G, et al. Syngrasp: a MATLAB toolbox for grasp analysis of human and robotic hands. In: Proceedings of IEEE International Conference on Robotics and Automation, Karlsruhe, 2013. 1088–1093

    Google Scholar 

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (Grant Nos. 61210013, 61327809, 91420302, 91520201).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Chunfang Liu.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Liu, C., Sun, F. & Ban, X. An effective method for grasp planning on objects with complex geometry combining human experience and analytical approach. Sci. China Inf. Sci. 59, 112212 (2016). https://doi.org/10.1007/s11432-015-0463-9

Download citation

Keywords

  • grasp planning
  • human experience
  • analytical method
  • kinematics learning
  • ELM

关键词

  • 抓取规划
  • 人类经验
  • 分析法
  • 极限学习机(ELM)
  • 运动学