Congress of the Italian Association for Artificial Intelligence

AI*IA 2015 Advances in Artificial Intelligence pp 397-409 | Cite as

Graph-Based Task Libraries for Robots: Generalization and Autocompletion

  • Steven D. Klee
  • Guglielmo Gemignani
  • Daniele Nardi
  • Manuela Veloso
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9336)

Abstract

In this paper, we consider an autonomous robot that persists over time performing tasks and the problem of providing one additional task to the robot’s task library. We present an approach to generalize tasks, represented as parameterized graphs with sequences, conditionals, and looping constructs of sensing and actuation primitives. Our approach performs graph-structure task generalization, while maintaining task executability and parameter value distributions. We present an algorithm that, given the initial steps of a new task, proposes an autocompletion based on a recognized past similar task. Our generalization and autocompletion contributions are effective on different real robots. We show concrete examples of the robot primitives and task graphs, as well as results, with Baxter. In experiments with multiple tasks, we show a significant reduction in the number of new task steps to be provided.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Anderson, J.R., Bothell, D., Lebiere, C., Matessa, M.: An integrated theory of list memory. Journal of Memory and Language (1998)Google Scholar
  2. 2.
    Argall, B.D., Browning, B., Veloso, M.: Learning robot motion control with demonstration and advice-operators. In: IROS (2008)Google Scholar
  3. 3.
    Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robotics and autonomous systems (2009)Google Scholar
  4. 4.
    Borrajo, D., Roubíčková, A., Serina, I.: Progress in case-based planning. ACM Computing Surveys (CSUR) 47(2), 35 (2015)CrossRefGoogle Scholar
  5. 5.
    Borrajo, D., Veloso, M.: Lazy incremental learning of control knowledge for efficiently obtaining quality plans. In: Lazy Learning (1997)Google Scholar
  6. 6.
    Chernova, S., Veloso, M.: Learning equivalent action choices from demonstration. In: IROS (2008)Google Scholar
  7. 7.
    Fikes, R.E., Hart, P.E., Nilsson, N.J.: Learning and executing generalized robot plans. Artificial intelligence (1972)Google Scholar
  8. 8.
    Gemignani, G., Bastianelli, E., Nardi, D.: Teaching robots parametrized executable plans through spoken interaction. In: Proc. of AAMAS (2015)Google Scholar
  9. 9.
    Hammond, K.J.: Chef: A model of case-based planning. In: AAAI (1986)Google Scholar
  10. 10.
    Jiang, C., Coenen, F., Zito, M.: A survey of frequent subgraph mining algorithms. The Knowledge Engineering Review (2013)Google Scholar
  11. 11.
    Kambhampati, S.: A theory of plan modification. In: AAAI (1990)Google Scholar
  12. 12.
    Kimelfeld, B., Kolaitis, P.G.: The complexity of mining maximal frequent subgraphs. In: Proc. of the 32nd Symp. on Principles of Database Systems (2013)Google Scholar
  13. 13.
    Laird, J.E., Rosenbloom, P.S., Newell, A.: Chunking in soar: The anatomy of a general learning mechanism. Machine learning (1986)Google Scholar
  14. 14.
    Langley, P., McKusick, K.B., Allen, J.A., Iba, W.F., Thompson, K.: A design for the icarus architecture. ACM SIGART Bulletin (1991)Google Scholar
  15. 15.
    Meriçli, Ç., Klee, S.D., Paparian, J., Veloso, M.: An interactive approach for situated task specification through verbal instructions. In: Proc. of AAMAS (2014)Google Scholar
  16. 16.
    Minton, S.: Quantitative results concerning the utility of explanation-based learning. Artificial Intelligence (1990)Google Scholar
  17. 17.
    Ng, A.Y., Russell, S.J., et al.: Algorithms for inverse reinforcement learning. In: ICML (2000)Google Scholar
  18. 18.
    Nicolescu, M.N., Matarić, M.J.: Natural methods for robot task learning: Instructive demonstrations, generalization and practice. In: Proc. of AAMAS (2003)Google Scholar
  19. 19.
    Nijssen, S., Kok, J.N.: The gaston tool for frequent subgraph mining. Electronic Notes in Theoretical Computer Science (2005)Google Scholar
  20. 20.
    Ratliff, N.D., Bagnell, J.A., Zinkevich, M.A.: Maximum margin planning. In: Proc. of the 23rd International Conference on Machine Learning (2006)Google Scholar
  21. 21.
    Rybski, P.E., Yoon, K., Stolarz, J., Veloso, M.: Interactive robot task training through dialog and demonstration. In: Proceedings of the 2th ACM/IEEE International Conference on Human-Robot Interaction (2007)Google Scholar
  22. 22.
    Veloso, M.M.: Planning and learning by analogical reasoning. Springer Science & Business Media (1994)Google Scholar
  23. 23.
    Zaki, M.J.: Efficiently mining frequent embedded unordered trees. Fundamenta Informaticae (2005)Google Scholar
  24. 24.
    Zaki, M.J.: Efficiently mining frequent trees in a forest: Algorithms and applications. IEEE Transactions on Knowledge and Data Engineering (2005)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Steven D. Klee
    • 1
  • Guglielmo Gemignani
    • 2
  • Daniele Nardi
    • 2
  • Manuela Veloso
    • 1
  1. 1.Computer Science DepartmentCarnegie Mellon UniversityPittsburghUSA
  2. 2.Department of Computer, Control, and Management Engineering “Antonio Ruberti”Sapienza University of RomeRomeItaly

Personalised recommendations