Relational Affordance Learning for Task-Dependent Robot Grasping

  • Laura AntanasEmail author
  • Anton Dries
  • Plinio Moreno
  • Luc De Raedt
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10759)


Robot grasping depends on the specific manipulation scenario: the object, its properties, task and grasp constraints. Object-task affordances facilitate semantic reasoning about pre-grasp configurations with respect to the intended tasks, favoring good grasps. We employ probabilistic rule learning to recover such object-task affordances for task-dependent grasping from realistic video data.



Partial support from the CHIST-ERA ReGROUND project on relational symbol grounding through affordance learning.


  1. 1.
    Abdo, N., Kretzschmar, H., Stachniss, C.: From low-level trajectory demonstrations to symbolic actions for planning. In: ICAPS Workshop on Combining Task and Motion Planning for Real-World Applications, pp. 1–8 (2012)Google Scholar
  2. 2.
    Antanas, L., Moreno, P., Neumann, M., Pimentel de Figueiredo, R., Kersting, K., Santos-Victor, J., De Raedt, L.: High-level reasoning and low-level learning for grasping: a probabilistic logic pipeline. CoRR, abs/1411.1108 (2014)Google Scholar
  3. 3.
    Baltzakis, H.: Orca simulatorGoogle Scholar
  4. 4.
    Barck-Holst, C., Ralph, M., Holmar, F., Kragic, D.: Learning grasping affordance using probabilistic and ontological approaches. In: ICRA, pp. 1–6 (2009)Google Scholar
  5. 5.
    Dang, H., Allen, P.K.: Semantic grasping: planning robotic grasps functionally suitable for an object manipulation task. In: IEEE/RSJ ICIRS, pp. 1311–1317 (2012)Google Scholar
  6. 6.
    de Figueiredo, R., Moreno, P., Bernardino, A.: Automatic object shape completion from 3D point clouds for object manipulation. In: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications VISIGRAPP, pp. 565–570 (2017)Google Scholar
  7. 7.
    De Raedt, L., Dries, A., Thon, I., Van Den Broeck, G., Verbeke, M.: Inducing probabilistic relational rules from probabilistic examples. In: IJCAI, pp. 1835–1843. AAAI Press (2015)Google Scholar
  8. 8.
    De Raedt, L., Thon, I.: Probabilistic rule learning. In: Frasconi, P., Lisi, F.A. (eds.) ILP 2010. LNCS (LNAI), vol. 6489, pp. 47–58. Springer, Heidelberg (2011). CrossRefGoogle Scholar
  9. 9.
    Detry, R., Ek, C.H., Madry, M., Kragic, D.: Compressing grasping experience into a dictionary of prototypical grasp-predicting parts. In: The 5th International Workshop on Human-Friendly Robotics, October 2012Google Scholar
  10. 10.
    Detry, R., Ek, C.H., Madry, M., Kragic, D.: Learning a dictionary of prototypical grasp-predicting parts from grasping experience. In: ICRA, pp. 601–608 (2013)Google Scholar
  11. 11.
    Detry, R., Ek, C.H., Madry, M., Piater, J.H., Kragic, D.: Generalizing grasps across partly similar objects. In: ICRA, pp. 3791–3797 (2012)Google Scholar
  12. 12.
    Dries, A., Kimmig, A., Meert, W., Renkens, J., Van den Broeck, G., Vlasselaer, J., De Raedt, L.: ProbLog2: probabilistic logic programming. In: Bifet, A., May, M., Zadrozny, B., Gavalda, R., Pedreschi, D., Bonchi, F., Cardoso, J., Spiliopoulou, M. (eds.) ECML PKDD 2015. LNCS (LNAI), vol. 9286, pp. 312–315. Springer, Cham (2015). CrossRefGoogle Scholar
  13. 13.
    Džeroski, S.: Handling imperfect data in inductive logic programming. In: SCAI, pp. 111–125 (1993)Google Scholar
  14. 14.
    Kulick, J., Toussaint, M., Lang, T., Lopes, M.: Active learning for teaching a robot grounded relational symbols. In: IJCAI, pp. 1451–1457. AAAI Press (2013)Google Scholar
  15. 15.
    Landwehr, N., Kersting, K., De Raedt, L.: nFOIL: Integrating Naïve Bayes and FOIL. In: Proceedings of the 20th National Conference on Artificial Intelligence, AAAI 2005, vol. 2, pp. 795–800. AAAI Press (2005)Google Scholar
  16. 16.
    Limketkai, B., Liao, L., Fox, D.: Relational object maps for mobile robots. In: IJCAI, pp. 1471–1476 (2005)Google Scholar
  17. 17.
    Madry, M., Song, D., Ek, C.H., Kragic, D.: “Robot bring me something to drink from”: object representation for transferring task specific grasps. In: ICRA Workshop on Semantic Perception, Mapping and Exploration, pp. 1–6 (2012)Google Scholar
  18. 18.
    Madry, M., Song, D., Kragic, D.: From object categories to grasp transfer using probabilistic reasoning. In: ICRA, pp. 1716–1723 (2012)Google Scholar
  19. 19.
    Moldovan, B., Antanas, L., Hoffmann, M.E.: Opening doors: an initial SRL approach. In: Riguzzi, F., Železný, F. (eds.) ILP 2012. LNCS (LNAI), vol. 7842, pp. 178–192. Springer, Heidelberg (2013). CrossRefGoogle Scholar
  20. 20.
    Moldovan, B., Moreno, P., Nitti, D., Santos-Victor, J., De Raedt, L.: Relational affordances for multiple-object manipulation. Autonomous Robots, May 2017CrossRefGoogle Scholar
  21. 21.
    Neumann, M., Moreno, P., Antanas, L., Garnett, R., Kersting, K.: Graph Kernels for object category prediction in task-dependent robot grasping. In: MLG, pp. 1–6 (2013)Google Scholar
  22. 22.
    KUKA robotics. Kuka lightweight robot (LWR)Google Scholar
  23. 23.
    Song, D., Huebner, K., Kyrki, V., Kragic, D.: Learning task constraints for robot grasping using graphical models. In: IEEE/RSJ ICIRS, pp. 1579–1585 (2010)Google Scholar
  24. 24.
    Sweeney, J., Grupen, R.A.: A model of shared grasp affordances from demonstration. In: Humanoids, pp. 27–35 (2007)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Laura Antanas
    • 1
    Email author
  • Anton Dries
    • 1
  • Plinio Moreno
    • 2
  • Luc De Raedt
    • 1
  1. 1.Department of Computer ScienceKatholieke Universiteit LeuvenLeuvenBelgium
  2. 2.Institute for Systems and Robotics, ISTUniversity of LisboaLisbonPortugal

Personalised recommendations