Abstract
How to learn from both sensory data (numerical) and a prior knowledge (linguistic) for a robot to acquire perception and motor skills is a challenging problem in the field of autonomous robotic systems. To make the most use of the information available for robot learning, linguistic and numerical heterogeneous dada (LNHD) Integration is firstly investigated in the frame of the fuzzy data fusion theory. With neural fuzzy systems' unique capabilities of dealing with both linguistic information and numerical data, the LNHD can be translated into an initial structure and parameters and then robots start from this configuration to further improve their behaviours. A neural- fuzzy-architecture-based reinforcement learning agent is finally constructed and verified using the simulation model of a physical biped robot. It shows that by incorporation of various kinds of LNHD on human gait synthesis and walking evaluation the biped learning rate for gait synthesis can be tremendously improved.
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
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Akbarzadeh-T, M.R., Kumbla, K., Tunstel, E., Jashidi, M.: Soft computing for autonomous robotic systems. Computers and Electrical Engineering 26 (2000) 5–32
Bloch, I.: Information combination operators for data fusion: a comparative review with classification. IEEE Trans. on Systems, Man, and Cybernetics 26 (1996) 52–67
Bonissone, P.P., Chen, Y.-T., Goebel, K., Khedhar, P.S.: Hybrid soft computing systems: industrial and commercial applications. Proceedings of IEEE 87 (1999) 1641–1667
Ghosh, B.K., Xi, N., Tarn, T.J. (Eds.): Control in Robotics and Automation: Sensor-Based Integration. Academic Press (1999)
Hathaway, H.J., Bezdek, J.C., Pedrycz, W.: A parametric model for fusing heterogeneous fuzzy data. IEEE Trans. on Fuzzy Systems 4 (1996) 270–281
Lin, C.T., Lee, C.S.G.: Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems. Prentice-Hall, Englewood Cliffs, NJ (1996)
Schaal, S.: Robot learning. Technical Report, University of Southern California (2000)
Sutton, R.S. and Barto, A.G.: Reinforcement learning: an introduction. MIT Press (1998)
Vokobratovic, M., Borovac, B., Surla, D. Stokic, D.: Biped Locomotion: Dynamics, Stability, Control and Application. Springer-Verlag (1990)
Zapata, G.O.A., Galvao, R.K.H., Yoneyama, T.: Extraction fuzzy control rules from experimental human operator data. IEEE Trans. Systems, Man, and Cybernetics B29 (1999) 398–406
Zhou, C., Ruan, D.: Integration of linguistic and numerical information for biped control. Robotics and Autonomous Systems 28 (1999) 53–77
Zhou, C., Ruan, D: Fuzzy rules extraction-based linguistic and numerical data fusion for intelligent robotic control. In: Fuzzy If-Then Rules in Computational Intelligence: Theory and Applications, Ruan, D., Kerre, E.E. (eds.), Kluwer Academic Publishers (2000) 243–265
Zhou, C.: Neuro-fuzzy gait synthesis with reinforcement learning for a biped walking robot. Soft Computing 4 (2000) 238–250
Zhou, C., Meng, M., Kanniah, J.: Dynamic balance of a biped robot using fuzzy reinforcement learning agents, Fuzzy Sets and Systems (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhou, C., Kanniah, J., Yang, Y. (2001). Information Integration for Robot Learning Using Neural Fuzzy Systems. In: Mira, J., Prieto, A. (eds) Bio-Inspired Applications of Connectionism. IWANN 2001. Lecture Notes in Computer Science, vol 2085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45723-2_56
Download citation
DOI: https://doi.org/10.1007/3-540-45723-2_56
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42237-2
Online ISBN: 978-3-540-45723-7
eBook Packages: Springer Book Archive