Advertisement

Inferring Capabilities by Experimentation

  • Ashwin Khadke
  • Manuela Veloso
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 867)

Abstract

We present an approach to enable an autonomous agent (learner) in building a model of a new unknown robot’s (subject) performance at a task through experimentation. The subject’s appearance can provide cues to its physical as well as cognitive capabilities. Building on these cues, our active experimentation approach learns a model that captures the effect of relevant extrinsic factors on the subject’s ability to perform a task. As personal robots become increasingly multi-functional and adaptive, such autonomous agents would find use as tools for humans in determining “What can this robot do?”. We applied our algorithm in modelling a NAO and a Pepper robot at two different tasks. We first demonstrate the advantages of our active experimentation approach, then we show the utility of such models in identifying scenarios a robot is well suited for, in performing a task.

Notes

Acknowledgements

This research is partially sponsored by DARPA under agreements FA87501620042 and FA87501720152 and NSF under grant IIS1637927. The views and conclusions contained in this document are those of the authors only.

References

  1. 1.
    Mitchell, T.M., Utgoff, P.E., Banerji, R.: Readings in knowledge acquisition and learning. In: Buchanan, B.G., Wilkins, D.C. (eds.) Learning by Experimentation: Acquiring and Refining Problem-solving Heuristics (1993)Google Scholar
  2. 2.
    Scott, P.D., Markovitch, S.: Experience selection and problem choice in an exploratory learning system. Mach. Learn. (1993)Google Scholar
  3. 3.
    Gil, Y.: Learning by experimentation: incremental refinement of incomplete planning domains. In: Proceedings of the Eleventh International Conference on International Conference on Machine Learning (1994)Google Scholar
  4. 4.
    Gibson, J.J.: The Theory of Affordances Chapt (1977)Google Scholar
  5. 5.
    Şahin, E., Çakmak, M., R. Doğar, M., Uğur, E., Üçoluk, G.: To afford or not to afford: a new formalization of affordances toward affordance-based robot control. Adapt. Behav. (2007)Google Scholar
  6. 6.
    Dearden, A., Demiris, Y., Kaelbling, L., Saffotti, A.: Learning forward models for robots. In: IJCAI-International Joint Conference in Artificial Intelligence (2005)Google Scholar
  7. 7.
    Montesano, L., Lopes, M., Bernardino, A., Santos-Victor, J.: Learning object affordances: from sensory–motor coordination to imitation. IEEE Trans. Robot. (2008)Google Scholar
  8. 8.
    Jordan, M.I., Rumelhart, D.E.: Forward models: supervised learning with a distal teacher. Cogn. Sci. (1992)Google Scholar
  9. 9.
    Baranès, A., Oudeyer, P.-Y.: R-IAC: Robust intrinsically motivated exploration and active learning. IEEE Trans. Auton. Ment. Dev. (2009)Google Scholar
  10. 10.
    Baranes, A., Oudeyer, P.-Y.: Active learning of inverse models with intrinsically motivated goal exploration in robots. Robot. Auton. Syst. (2013)Google Scholar
  11. 11.
    Wang, C., Hindriks, K.V., Babuska, R.: Active learning of affordances for robot use of household objects. In: IEEE-RAS International Conference on Humanoid Robots (2014)Google Scholar
  12. 12.
    Forestier, S., Oudeyer, P.Y.: Modular active curiosity-driven discovery of tool use. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (2016)Google Scholar
  13. 13.
    Forestier, S., Mollard, Y., Oudeyer, P.: Intrinsically motivated goal exploration processes with automatic curriculum learning. CoRR (2017)Google Scholar
  14. 14.
    Hofer, S., Brock, O.: Coupled learning of action parameters and forward models for manipulation. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (2016)Google Scholar
  15. 15.
    Mugan, J., Kuipers, B.: Autonomous learning of high-level states and actions in continuous environments. IEEE Trans. Auton. Ment. Dev. (2012)Google Scholar
  16. 16.
    Tong, S., Koller, D.: Active learning for parameter estimation in Bayesian networks. In: Proceedings of the 13th International Conference on Neural Information Processing Systems (2000)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Robotics InstituteCarnegie Mellon UniversityPittsburghUSA
  2. 2.Department of Machine LearningCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations