Abstract
In this paper, we propose a method to dynamically modulate the input state of recurrent neural networks (RNNs) so as to realize flexible and robust robot behavior. We employ the so-called stochastic continuous-time RNN (S-CTRNN), which can learn to predict the mean and variance (or uncertainty) of subsequent sensorimotor information. Our proposed method uses this estimated uncertainty to determine a mixture ratio for combining actual and predicted sensory states of network input. The method is evaluated by conducting a robot learning experiment in which a robot is required to perform a sensory-dependent task and a sensory-independent task. The sensory-dependent task requires the robot to incorporate meaningful sensory information, and the sensory-independent task requires the robot to ignore irrelevant sensory information. Experimental results demonstrate that a robot controlled by our proposed method exhibits flexible and robust behavior, which results from dynamic modulation of the network input on the basis of the estimated uncertainty of actual sensory states.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Clark, A.: Surfing Uncertainty: Prediction, Action, and the Embodied Mind. Oxford University Press, Oxford (2015)
Noda, K., Ito, M., Hoshino, Y., Tani, J.: Dynamic generation and switching of object handling behaviors by a humanoid robot using a recurrent neural network model. In: Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J.C.T., Marocco, D., Meyer, J.-A., Miglino, O., Parisi, D. (eds.) SAB 2006. LNCS, vol. 4095, pp. 185–196. Springer, Heidelberg (2006). doi:10.1007/11840541_16
Tani, J., Ito, M.: Self-organization of behavioral primitives as multiple attractor dynamics: a robot experiment. IEEE Trans. Syst. Man Cybern. - Part A Syst. Hum. 33(4), 481–488 (2003)
Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270–280 (1989)
Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. arXiv 19994575, pp. 1–9 (2015)
Murata, S., Namikawa, J., Arie, H., Sugano, S., Tani, J.: Learning to reproduce fluctuating time series by inferring their time-dependent stochastic properties: application in robot learning via tutoring. IEEE Trans. Auton. Ment. Dev. 5(4), 298–310 (2013)
Doya, K., Yoshizawa, S.: Adaptive neural oscillator using continuous-time back-propagation learning. Neural Netw. 2(5), 375–385 (1989)
Yamashita, Y., Tani, J.: Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment. PLoS Comput. Biol. 4(11), e1000220 (2008)
Acknowledgement
This work was supported in part by JST CREST Grant Number: JPMJCR15E3, Japan;JSPS KAKENHI Grant Numbers: 25220005, 17K12754, Japan and the “Fundamental Study for Intelligent Machine to Coexist with Nature” program of the Research Institute for Science and Engineering at Waseda University, Japan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Murata, S., Masuda, W., Tomioka, S., Ogata, T., Sugano, S. (2017). Mixing Actual and Predicted Sensory States Based on Uncertainty Estimation for Flexible and Robust Robot Behavior. In: Lintas, A., Rovetta, S., Verschure, P., Villa, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2017. ICANN 2017. Lecture Notes in Computer Science(), vol 10613. Springer, Cham. https://doi.org/10.1007/978-3-319-68600-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-68600-4_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68599-1
Online ISBN: 978-3-319-68600-4
eBook Packages: Computer ScienceComputer Science (R0)