An Experiment in Robot Discovery with ILP

  • Gregor Leban
  • Jure Žabkar
  • Ivan Bratko
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5194)


We describe an experiment in the application of ILP to autonomous discovery in a robotic domain. An autonomous robot is performing experiments in its world, collecting data and formulating predictive theories about this world. In particular, we are interested in the robot’s “gaining insights” through predicate invention. In the first experimental scenario in a pushing blocks domain, the robot discovers the notion of objects’ movability. The second scenario is about discovering the notion of obstacle. We describe experiments with a simulated robot, as well as an experiment with a real robot when robot’s observations contain noise.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Awaad, I.S., Leon, B.E.: Xpersim: Simulation of the robotic experimenter. Technical report, University of Applied Sciences Bonn-Rhein-Sieg (2006)Google Scholar
  2. 2.
    Boström, H.: Predicate invention and learning from positive examples only. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 226–237. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  3. 3.
    Bratko, I.: Prolog Programming for Artificial Intelligence. Addison-Wesley, Reading (2001)Google Scholar
  4. 4.
    Cocora, A., Kersting, K., Plagemann, C., Burgard, W., De Raedt, L.: Learning relational navigation policies. In: Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (2006)Google Scholar
  5. 5.
    Deshpande, A., Milch, B., Zettlemoyer, L.S., Kaelbling, L.P.: Learning probabilistic relational dynamics for multiple tasks. In: Proceedings of the Twenty Third Conference on Uncertainty in Artificial Intelligence (UAI) (2007)Google Scholar
  6. 6.
    Dzeroski, S., De Raedt, L., Blockeel, H.: Relational reinforcement learning. In: Page, D.L. (ed.) ILP 1998. LNCS, vol. 1446, pp. 11–22. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  7. 7.
    Kaiser, M., Klingspor, V., Morik, K., Rieger, A., Acame, M., del, J., Millan, R.: Learning techniques for mobile systems (1995)Google Scholar
  8. 8.
    Kersting, K., Van Otterlo, M., De Raedt, L.: Bellman goes relational. In: Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004), Banff, Alberta, Canada (2004)Google Scholar
  9. 9.
    Klingspor, V., Morik, K., Rieger, A.D.: Learning concepts from sensor data of a mobile robot. Machine Learning 23(2-3), 305–332 (1996)CrossRefGoogle Scholar
  10. 10.
    Kramer, S.: Predicate invention: A comprehensive view. Technical Report OFAI-TR-95-32 (1995)Google Scholar
  11. 11.
    Langley, P., Simon, H., Bradshaw, G., Zytkow, J.: Scientific discovery: Computational explorations of the creative processes (1987)Google Scholar
  12. 12.
    Muggleton, S.: A strategy for constructing new predicates in first order logic. In: Sleeman, D. (ed.) Proceedings of the 3rd European Working Session on Learning, pp. 123–130. Pitman (1988)Google Scholar
  13. 13.
    Muggleton, S.: Predicate invention and utility. Journal of Experimental and Theoretical Artificial Intelligence 6(1), 121–130 (1994)zbMATHCrossRefGoogle Scholar
  14. 14.
    Rieger, A.: Data preparation for inductive learning in robotics (1995)Google Scholar
  15. 15.
    Rieger, A.: Learning to guide a robot via perceptrons. In: Ghallab, M., Milani, A. (eds.) New Directions in AI Planning, pp. 383–394. IOS Press, Amsterdam (1996)Google Scholar
  16. 16.
    Scott, P.D., Markovitch, S.: Learning novel domains through curiosity and conjecture. In: IJCAI, pp. 669–674 (1989)Google Scholar
  17. 17.
    Shen, W.-M.: Discovery as autonomous learning from the environment. Machine Learning 12, 143–165 (1993)Google Scholar
  18. 18.
    Stahl, I., Weber, I.: The arguments of newly invented predicates in ILP. In: Wrobel, S. (ed.) Proceedings of the 4th International Workshop on Inductive Logic Programming. Gesellschaft für Mathematik und Datenverarbeitung MBH, vol. 237, pp. 233–246 (1994)Google Scholar
  19. 19.
    Stolcke, A., Omohundro, S.M.: Best-first model merging for hidden Markov model induction. Technical Report TR-94-003, 1947 Center Street, Berkeley, CA (1994)Google Scholar
  20. 20.
    Zettlemoyer, L.S., Pasula, H.M., Kaelbling, L.P.: Learning planning rules in noisy stochastic worlds. In: Proc. 20th National Conference on Artificial Intelligence (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Gregor Leban
    • 1
  • Jure Žabkar
    • 1
  • Ivan Bratko
    • 1
  1. 1.Faculty of Computer and Information ScienceUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations