Abstract
Biologically inspired control system is necessary to be increased. This paper proposed the new design of multimodal neural network inspired from human learning system which takes different action in different condition. The multimodal neural network consists of some recurrent neural networks (RNNs) those are separated into different condition. There is selector system that decides certain RNN system depending the current condition of the robot. In this paper, we implemented this system in pendulum mobile robot as the basic object of study. Several certain number of RNNs are implemented into certain different condition of tilt robot. RNN works alternately depending on the condition of robot. In order to prove the effectiveness of the proposed model, we simulated in the computer simulation Open Dynamic Engine (ODE) and compared with ordinary RNN. The proposed neural model successfully stabilize the applied robot (2-wheeled robot). This model is developed for implemented into humanoid balancing learning system as the final object of study.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Saputra, A.A., Sulistijono, I.A., Khalilullah, A.S., Takeda, T., Kubota, N.: Combining pose control and angular velocity control for motion balance of humanoid robot soccer EROS. In: IEEE Symposium on Robotic Intelligence in Informatically Structured Space, USA, pp. 16–21, December 2015
Saputra, A.A., Khalilullah, A.S., Sulistijono, I.A., Kubota, N.: Adaptive motion pattern generation on balancing of humanoid robot movement. In: Canadian Conference on Electrical and Computer Engineering, pp. 1479–1484, May 2015
Lin, F.-J., Shieh, P.-H., Shen, P.-H.: Robust recurrent-neural-network sliding-mode control for the x-y table of a CNC machine. IEEE Proc. Control Theor. Appl. 153(1), 111–123 (2006)
Zhang, L., Quan, S., Xiang, K.: Recurrent neural network optimization for model predictive control. In: IEEE World Congress on Computational Intelligence, IEEE International Joint Conference on Neural Networks (IJCNN), pp. 751–757, June 2008
Li, Y., Wang, Y.: Trajectory tracking control of a redundantly actuated parallel robot using diagonal recurrent neural network. In: 5th International Conference on Natural Computation, vol. 2, pp. 292–296, August 2009
Tran, D.T., Koo, I.M., Lee, Y.H., Moon, H., Park, S., Koo, J.C., Choi, H.R.: Central pattern generator based reflexive control of quadruped walking robots using a recurrent neural network. Robot. Auton. Syst. 62(10), 1497–1516 (2014)
Sungmoon, J., Yunjung, P., Rammohan, M., Jun, T., Minho, L.: Goal-oriented behavior sequence generation based on semantic commands using multiple timescales recurrent neural network with initial state correction. Neurocomputing 129, 67–77 (2014)
Lin, C., Boldbaatar, E.: Fault accommodation control for a biped robot using a recurrent wavelet Elman neural network. Syst. J. IEEE 99, 1–12 (2015)
Fukuda, T., Komata, Y., Arakawa, T.: Recurrent neural network with self-adaptive GAs for biped locomotion robot. In: International Conference on Neural Networks, vol. 3, pp. 1710–1715, June 1997
Saputra, A.A., Botzheim, J., Sulistijono, I.A., Kubota, N.: Biologically inspired control system for 3-D locomotion of a humanoid biped robot. IEEE Trans. Syst. Man Cybern. Syst. 46, 898–911 (2015)
Cruse, H.: Neural Networks as Cybernetic Systems - 2nd and Revised Edition. Brains, Minds & Media, Bielefeld (2006)
Yamaguchi, S., Itakura, H.: A modular neural network for control of mobile robots. In: 6th International Conference on Neural Information Processing, vol. 2, pp. 661–666 (1999)
Azam, F.: Biologically inspired modular neural networks, Ph.D. dissertation, Virginia Polytechnic Institute and State University, Blacksburg, Virginia, May 2000
Kiros, R., Salakhutdinov, R., Zemel, R.: Multimodal neural language models. In: 31st International Conference on Machine Learning, pp. 595–603 (2014)
Wermter, S., Weber, C., Elshaw, M., Panchev, C., Erwin, H.R., Pulvermller, F.: Towards multimodal neural robot learning. Robot. Auton. Syst. 47, 171–175 (2004)
Karras, D.A.: An improved modular neural network model for adaptive trajectory tracking control of robot manipulators. In: Köppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008, Part I. LNCS, vol. 5506, pp. 1063–1070. Springer, Heidelberg (2009)
Saputra, A.A., Sulistijono, I.A., Botzheim, J., Kubota, N.: Interconnection structure optimization for neural oscillator based biped robot locomotion. In: 2015 IEEE Symposium Series on Computational Intelligence, pp. 288–294, December 2015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Saputra, A.A., Sulistijono, I.A., Kubota, N. (2016). Multimodal Recurrent Neural Network (MRNN) Based Self Balancing System: Applied into Two-Wheeled Robot. In: Kubota, N., Kiguchi, K., Liu, H., Obo, T. (eds) Intelligent Robotics and Applications. ICIRA 2016. Lecture Notes in Computer Science(), vol 9834. Springer, Cham. https://doi.org/10.1007/978-3-319-43506-0_52
Download citation
DOI: https://doi.org/10.1007/978-3-319-43506-0_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-43505-3
Online ISBN: 978-3-319-43506-0
eBook Packages: Computer ScienceComputer Science (R0)