A Relational Approach to Tool-Use Learning in Robots

  • Solly Brown
  • Claude Sammut
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7842)


We present a robot agent that learns to exploit objects in its environment as tools, allowing it to solve problems that would otherwise be impossible to achieve. The agent learns by watching a single demonstration of tool use by a teacher and then experiments in the world with a variety of available tools. A variation of explanation-based learning (EBL) first identifies the most important sub-goals the teacher achieved using the tool. The action model constructed from this explanation is then refined by trial-and-error learning with a novel Inductive Logic Programming (ILP) algorithm that generates informative experiments while containing the search space to a practical number of experiments. Relational learning generalises across objects and tasks to learn the spatial and structural constraints that describe useful tools and how they should be employed. The system is evaluated in a simulated robot environment.


robot learning planning constrain solving explanation-based learning version space 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Plotkin, G.: A note on inductive generalization. In: Meltzer, B., Mitchie, D. (eds.) Machine Intelligence, vol. 5, pp. 153–163. Edinburgh University Press (1970)Google Scholar
  2. 2.
    Mitchell, T.: Generalization as search. Artificial Intelligence 18, 203–266 (1982)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Fikes, R., Nilsson, N.: STRIPS: A new approach to the application of theorem proving to problem solving. Artificial Intelligence 2(3-4), 189–208 (1971)zbMATHCrossRefGoogle Scholar
  4. 4.
    Hoffmann, J., Nebel, B.: The FF planning system: Fast plan generation through heuristic search. Journal of Artificial Intelligence Research 14 (2001)Google Scholar
  5. 5.
    Apt, K.R., Wallace, M.G.: Constraint Logic Programming using ECLiPSe. Cambridge University Press (2007)Google Scholar
  6. 6.
    Kuffner, J., LaValle, S.: RRT-Connect: An efficient approach to single-query path planning. In: International Conference on Robotics and Automation (April 2000)Google Scholar
  7. 7.
    Brown, S.: A relational approach to tool-use learning in robots. PhD thesis, School of Computer Science and Engineering, The University of New South Wales (2009)Google Scholar
  8. 8.
    Muggleton, S., Feng, C.: Efficient induction of logic programs. In: Muggleton, S. (ed.) Inductive Logic Programming, pp. 281–298. Academic Press (1992)Google Scholar
  9. 9.
    Koenig, N., Howard, A.: Design and use paradigms for Gazebo, an open-source multi-robot simulator. In: International Conference on Intelligent Robots and Systems, vol. 3, pp. 2149–2154 (September 2004)Google Scholar
  10. 10.
    Bicici, E., St Amant, R.: Reasoning about the functionality of tools and physical artifacts. Technical Report 22, NC State University (2003)Google Scholar
  11. 11.
    Wood, A., Horton, T., St Amant, R.: Effective tool use in a habile agent. In: IEEE Systems and Information Engineering Design Symposium, pp. 75–81 (April 2005)Google Scholar
  12. 12.
    Stoytchev, A.: Behaviour-grounded representation of tool affordances. In: International Conference on Robotics and Automation (April 2005)Google Scholar
  13. 13.
    Gil, Y.: Learning by experimentation: Incremental refinement of incomplete planning domains. In: International Conference on Machine Learning (1994)Google Scholar
  14. 14.
    Benson, S.: Learning action models for reactive autonomous agents. PhD thesis, Department of Computer Science, Stanford University (1996)Google Scholar
  15. 15.
    Pasula, H.M., Zettlemoyer, L.S., Kaelbling, L.P.: Learning symbolic models of stochastic domains. Journal of Artificial Intelligence Research 29, 309–352 (2007)zbMATHGoogle Scholar
  16. 16.
    Amir, E.: Learning partially observable deterministic action models. In: International Joint Conference on Artificial Intelligence (IJCAI 2005), Edinburgh, Scotland, UK, pp. 1433–1439 (August 2005)Google Scholar
  17. 17.
    Levine, G., DeJong, G.: Explanation-based acquisition of planning operators. In: ICAPS, pp. 152–161 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Solly Brown
    • 1
  • Claude Sammut
    • 1
  1. 1.School of Computer Science and EngineeringThe University of New South Wales SydneyAustralia

Personalised recommendations