Fast Grasp Learning for Novel Objects

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 440)

Abstract

This paper presents a method for fast learning of dexterous grasps for unknown objects. We use two probabilistic models of each grasp type learned from a single demonstrated grasp example to generate many grasp candidates for new objects with unknown shapes. These models encode probability density functions representing relationship between fingers and object local features, and whole hand configuration that is particular to a grasp example, respectively. Both, in the training and in the grasp generation stage we use an incomplete 3D point cloud from a depth sensor. The results of simulation experiments performed with the BarrettHand gripper and several objects of different shapes indicate that the proposed learning approach is applicable in realistic scenarios.

Keywords

Grasp learning Probabilistic models Kernel density estimation 

References

  1. 1.
    Kopicki, M., Detry, R., Adjigble, M., Stolkin, R., Leonardis, A., Wyatt, J.L.: One-shot learning and generation of dexterous grasps for novel objects. Int. J. Robot. Res. (2015) 0278364915594244Google Scholar
  2. 2.
    Bohg, J., Morales, A., Asfour, T., Kragic, D.: Data-driven grasp synthesis-a survey. IEEE Trans. Rob. 30(2), 289–309 (2014)CrossRefGoogle Scholar
  3. 3.
    Szynkiewicz, W.: Robot grasp synthesis under object pose uncertainty. J. Autom. Mobile Robot. Intell. Syst. 9(1), 53–61 (2015)CrossRefGoogle Scholar
  4. 4.
    Seredyński, D., Winiarski, T., Banachowicz, K., Zieliński, C.: Grasp planning taking into account the external wrenches acting on the grasped object. In: 10th International Workshop on Robot Motion and Control (RoMoCo), pp. 40–45 IEEE (2015)Google Scholar
  5. 5.
    Winiarski, T., Banachowicz, K., Seredyński, D.: Multi-sensory feedback control in door approaching and opening. In: Intelligent Systems’2014 of Advances in Intelligent Systems and Computing, vol. 323, pp. 57–70. Springer International Publishing (2015)Google Scholar
  6. 6.
    Detry, R., Ek, C., Madry, M., Kragic, D.: Learning a dictionary of prototypical grasp-predicting parts from grasping experience. In: 2013 IEEE International Conference on Robotics and Automation (ICRA), pp. 601–608 (2013)Google Scholar
  7. 7.
    Herzog, A., Pastor, P., Kalakrishnan, M., Righetti, L., Bohg, J., Asfour, T., Schaal, S.: Learning of grasp selection based on shape-templates. Auton. Robots 36(1–2), 51–65 (2014)CrossRefGoogle Scholar
  8. 8.
    Kroemer, O., Ugur, E., Oztop, E., Peters, J.: A kernel-based approach to direct action perception. In: 2012 IEEE International Conference on Robotics and Automation (ICRA), pp. 2605–2610 (2012)Google Scholar
  9. 9.
    Pelossof, R., Miller, A., Allen, P., Jebara, T.: An SVM learning approach to robotic grasping. In: Proceedings. ICRA ’04. 2004 IEEE International Conference on Robotics and Automation, vol. 4, pp. 3512–3518 (2004)Google Scholar
  10. 10.
    Saxena, A., Driemeyer, J., Ng, A.Y.: Robotic grasping of novel objects using vision. Int. J. Robot. Res. 27(2), 157–173 (2008)CrossRefGoogle Scholar
  11. 11.
    Ben Amor, H., Kroemer, O., Hillenbrand, U., Neumann, G., Peters, J.: Generalization of human grasping for multi-fingered robot hands. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2043–2050 (2012)Google Scholar
  12. 12.
    Hillenbrand, U., Roa, M.: Transferring functional grasps through contact warping and local replanning. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2963–2970 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Warsaw University of TechnologyWarsawPoland

Personalised recommendations