Techniques to Control Robot Action Consisting of Multiple Segmented Motions using Recurrent Neural Network with Butterfly Structure

Wataru Torii, Shinpei Fujimoto, Masahiro Furukawa, Hideyuki Ando, Taro Maeda

Abstract

In the field of robot control, there have been several studies on humanoid robots operating in remote areas. We propose a methodology to control a robot using input from an operator with fewer degrees of freedom than the robot. This method is based on the concept that time-continuous actions can be segmented because human intentions are discrete in the time domain. Additionally, machine learning is used to determine components with a high correlation to input data that are often complex or large in quantity. In this study, we implemented a new structure on a conventional neural network to manipulate a robot using a fast Fourier transform. The neural network was expected to acquire robustness for amplitude and phase variations. Thus, our model can reflect a fluctuating operator input to control a robot. We applied the proposed neural network to manipulate a robot and verified the validity and performance compared with traditional models.

References

  1. Ando, H., Niwa, M., IIzuka, H., and Maeda, T., editors (2012). Effects of observed motion speed on segmenting behavioural intention.
  2. G. E. Hinton, S. O. and Teh, Y. (2006). A fast learn-ing algorithm for deep belief nets. Neural Computation, 18(2):1527-1544.
  3. Hinton, G. E. and Salakhutdinov, R. (2006). Reducing the dimensionality of data with neural networks. Science, 313:504-507.
  4. Hirai, K., Hirose, M., Haikawa, Y., and Takenaka, T., editors (1998). The Development of Honda Humanoid Robot, volume 2. IEEE.
  5. Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8):1735-1780.
  6. Le, Q., Ranzato, M. A., Monga, R., Devin, M., Chen, K., Corrado, G., Dean, J., and Ng, A., editors (2012). Building high-level features using large scale unsupervised learning.
  7. Mikolov, T., Kombrink, S., Burget, L., Cernocky, J., and S.Khudanpur, editors (2011). Recurrent Neural Network Based Language Model.
  8. Niwa, M., S.Okada, Sakaguchi, S., Azuma, K., Iizuka, H., H, A., and Maeda, T., editors (2010). Detection and Transmission of Tsumori : an Archetype of Behavioral Intention in Controlling a Humanoid Robot.
  9. Yamamoto, T. and Fujinami, T. (2004). Synchronisation and differentiation: Two stage of coordinative structure. In Third International Work-shop on Epigenetic Robotics, pages 97-104.
Download


Paper Citation


in Harvard Style

Torii W., Fujimoto S., Furukawa M., Ando H. and Maeda T. (2016). Techniques to Control Robot Action Consisting of Multiple Segmented Motions using Recurrent Neural Network with Butterfly Structure . In Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3: BIOINFORMATICS, (BIOSTEC 2016) ISBN 978-989-758-170-0, pages 174-181. DOI: 10.5220/0005664801740181


in Bibtex Style

@conference{bioinformatics16,
author={Wataru Torii and Shinpei Fujimoto and Masahiro Furukawa and Hideyuki Ando and Taro Maeda},
title={Techniques to Control Robot Action Consisting of Multiple Segmented Motions using Recurrent Neural Network with Butterfly Structure},
booktitle={Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3: BIOINFORMATICS, (BIOSTEC 2016)},
year={2016},
pages={174-181},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005664801740181},
isbn={978-989-758-170-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 3: BIOINFORMATICS, (BIOSTEC 2016)
TI - Techniques to Control Robot Action Consisting of Multiple Segmented Motions using Recurrent Neural Network with Butterfly Structure
SN - 978-989-758-170-0
AU - Torii W.
AU - Fujimoto S.
AU - Furukawa M.
AU - Ando H.
AU - Maeda T.
PY - 2016
SP - 174
EP - 181
DO - 10.5220/0005664801740181