Learning to Detect the Functional Components of Doorbell Buttons
Using Active Exploration and Multimodal Correlation

Overview

Abstract

This project produced a large-scale experimental study, in which a humanoid robot learned to press and detect doorbell buttons autonomously. The models for action selection and visual detection were grounded in the robot's sensorimotor experience and learned without human intervention. Experiments were performed with seven doorbell buttons, which provided auditory feedback when pressed. The robot learned to predict the locations of the functional components of each button accurately. The trained visual model was also able to detect the functional components of novel buttons.

Paper

Sukhoy, V. and Stoytchev, A., "Learning to Detect the Functional Components of Doorbell Buttons Using Active Exploration and Multimodal Correlation," In Proceedings of 2010 IEEE International Conference on Humanoid Robots (Humanoids), Nashville, TN, pp. 572-579, December 6-8, 2010.
The Framework video video video video video

BibTeX

@InProceedings{sukhoy2010Humanoids,
  author     = {V. Sukhoy and A. Stoytchev},
  title      = {Learning to Detect the Functional Components of Doorbell Buttons
                Using Active Exploration and Multimodal Correlation},
  booktitle  = {In Proceedings of the 2010 IEEE-RSJ Conference on Humanoid Robots},
  year       = {2010},
  pages      = {572-579}
  address    = {Nashville, TN},
  month      = {December}
}
      

Earlier Papers

  • Sukhoy, V., Sinapov, J., Wu, L., and Stoytchev, A., "Learning to Press Doorbell Buttons," In Proceedings of the 9th IEEE International Conference on Development and Learning (ICDL), Ann Arbor, MI, pp. 132-139, August 18-21, 2010.
  • Wu, L., Sukhoy, V., and Stoytchev, A., "Toward Learning to Press Doorbell Buttons," In Proceedings of the 24-th National Conference on Artificial Intelligence (AAAI), Atlanta, GA, July 11-15, pp. 1965-1966, 2010.

See More Videos Here or on YouTube