A Semi-local Surface Feature for Learning Successful Grasping Affordances

Mikkel Tang Thomsen, Dirk Kraft, Norbert Krüger

2016

Abstract

We address the problem of vision based grasp affordance learning and prediction on novel objects by proposing a new semi-local shape-based descriptor, the Sliced Pineapple Grid Feature (SPGF). The primary characteristic of the feature is the ability to encode semantically distinct surface structures, such as “walls”, “edges” and “rims”, that show particular potential as a primer for grasp affordance learning and prediction. When the SPGF feature is used in combination with a probabilistic grasp affordance learning approach, we are able to achieve grasp success-rates of up to 84% for a varied object set of three classes and up to 96% for class specific objects.

References

  1. Archive3D. Archive3d free online cad model database. http://www.archive3d.net.
  2. Curtis, N., Xiao, J., and Member, S. (2008). Efficient and effective grasping of novel objects through learning and adapting a knowledge base. In IEEE International Conference on Robotics and Automation (ICRA), pages 2252-2257.
  3. Detry, R., Ek, C. H., Madry, M., and Kragic, D. (2013). Learning a dictionary of prototypical grasp-predicting parts from grasping experience. In IEEE International Conference on Robotics and Automation.
  4. Durrant-Whyte, H. and Bailey, T. (2006). Simultaneous localization and mapping: part i. Robotics Automation Magazine, IEEE, 13(2):99-110.
  5. Huebner, K., Ruthotto, S., and Kragic, D. (2008). Minimum volume bounding box decomposition for shape approximation in robot grasping. In Robotics and Automation, 2008. ICRA 2008. IEEE International Conference on, pages 1628-1633. IEEE.
  6. J. Bohg, A. Morales, T. A. and Kragic, D. (2014). Datadriven grasp synthesis a survey. IEEE Transactions on Robotics, 30(2):289-309.
  7. Jiang, Y., Moseson, S., and Saxena, A. (2011). Efficient grasping from rgbd images: Learning using a new rectangle representation. In ICRA'11, pages 3304- 3311.
  8. Jørgensen, J. A., Ellekilde, L.-P., and Petersen, H. G. (2010). RobWorkSim - an Open Simulator for Sensor based Grasping. Robotics (ISR), 2010 41st International Symposium on and 2010 6th German Conference on Robotics (ROBOTIK), pages 1 -8.
  9. Kasper, A., Xue, Z., and Dillmann, R. (2012). The KIT object models database: An object model database for object recognition, localization and manipulation in service robotics. The International Journal of Robotics Research.
  10. Kootstra, G., Popovic, M., Jørgensen, J. A., Kuklinski, K., Miatliuk, K., Kragic, D., and Krüger, N. (2012). Enabling grasping of unknown objects through a synergistic use of edge and surface information. Has been accepted for Internation Journal of Robotic Research.
  11. Kopicki, M., Detry, R., Schmidt, F., Borst, C., Stolkin, R., and Wyatt, J. L. (2014). Learning dexterous grasps that generalise to novel objects by combining hand and contact models. In to appear in IEEE International Conference on Robotics and Automation.
  12. Kraft, D., Mustafa, W., Popovic, M., Jessen, J. B., Buch, A. G., Savarimuthu, T. R., Pugeault, N., and Krüger, N. (2014). Using surfaces and surface relations in an early cognitive vision system. Computer Vision and Image Understanding.
  13. Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097-1105.
  14. Krüger, N., Janssen, P., Kalkan, S., Lappe, M., Leonardis, A., Piater, J., , Rodríguez-Sánchez, A. J., and Wiskott, L. (2013). Deep hierarchies in the primate visual cortex: What can we learn for computer vision? IEEE PAMI, 35(8):1847-1871.
  15. Lenz, I., Lee, H., and Saxena, A. (2013). Deep learning for detecting robotic grasps. CoRR, pages -1-1.
  16. Lloyd, S. (2006). Least squares quantization in pcm. IEEE Trans. Inf. Theor., 28(2):129-137.
  17. Mustafa, W., Pugeault, N., and Krüger, N. (2013). Multiview object recognition using view-point invariant shape relations and appearance information. In IEEE International Conference on Robotics and Automation (ICRA).
  18. Myers, A., Teo, C. L., Fermüller, C., and Aloimonos, Y. (2015). Affordance detection of tool parts from geometric features. In ICRA.
  19. Redmon, J. and Angelova, A. (2014). Real-time grasp detection using convolutional neural networks. CoRR, abs/1412.3128.
  20. Saxena, A., Driemeyer, J., and Ng, A. Y. (2008). Robotic grasping of novel objects using vision. Int. J. Rob. Res., 27:157-173.
  21. Thomsen, M., Kraft, D., and Krüger, N. (2015). Identifying relevant feature-action associations for grasping unmodelled objects. Paladyn, Journal of Behavioral Robotics.
  22. Wahl, E., Hillenbrand, U., and Hirzinger, G. (2003). Surfletpair-relation histograms: a statistical 3d-shape representation for rapid classification. In3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings. Fourth International Conference on, pages 474-481. IEEE.
Download


Paper Citation


in Harvard Style

Thomsen M., Kraft D. and Krüger N. (2016). A Semi-local Surface Feature for Learning Successful Grasping Affordances . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 562-572. DOI: 10.5220/0005784505620572


in Bibtex Style

@conference{visapp16,
author={Mikkel Tang Thomsen and Dirk Kraft and Norbert Krüger},
title={A Semi-local Surface Feature for Learning Successful Grasping Affordances},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={562-572},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005784505620572},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)
TI - A Semi-local Surface Feature for Learning Successful Grasping Affordances
SN - 978-989-758-175-5
AU - Thomsen M.
AU - Kraft D.
AU - Krüger N.
PY - 2016
SP - 562
EP - 572
DO - 10.5220/0005784505620572