Hostname: page-component-78c5997874-xbtfd Total loading time: 0 Render date: 2024-11-05T16:29:24.843Z Has data issue: false hasContentIssue false

Training oscillatory neural networks using natural gradient particle swarm optimization

Published online by Cambridge University Press:  15 April 2014

Hamed Shahbazi*
Affiliation:
Faculty of Engineering, University of Isfahan, Isfahan, Iran
Kamal Jamshidi
Affiliation:
Faculty of Engineering, University of Isfahan, Isfahan, Iran
Amir Hasan Monadjemi
Affiliation:
Faculty of Engineering, University of Isfahan, Isfahan, Iran
Hafez Eslami Manoochehri
Affiliation:
Faculty of Engineering, University of Isfahan, Isfahan, Iran
*
*Corresponding author. E-mail: [email protected]

Summary

In this paper, a new design of neural networks is introduced, which is able to generate oscillatory patterns in its output. The oscillatory neural network is used in a biped robot to enable it to learn to walk. The fundamental building block of the neural network proposed in this paper is O-neurons, which can generate oscillations in its transfer functions. O-neurons are connected and coupled with each other in order to shape a network, and their unknown parameters are found by a particle swarm optimization method. The main contribution of this paper is the learning algorithm that can combine natural policy gradient with particle swarm optimization methods. The oscillatory neural network has six outputs that determine set points for proportional-integral-derivative controllers in 6-DOF humanoid robots. Our experiment on the simulated humanoid robot presents smooth and flexible walking.

Type
Articles
Copyright
Copyright © Cambridge University Press 2014 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1. Alcaraz-Jimenez, J. J., Herrero-Perez, D. and Martınez-Barberá, H., “Motion planning for omnidirectional dynamic gait in humanoid soccer robots,” J. Phys. Agents 5 (1), 2534 (2011).Google Scholar
2. Basheer, I. A. and Hajmeer, M., “Artificial neural networks: Fundamentals, computing, design, and application,” J. Microbiol. Methods 43 (1), 331 (2000).Google Scholar
3. Clark, M. R., Anderson, G. T. and Skinner, R. D., “Coupled oscillator control of autonomous mobile robots,” Auton. Robots 9 (2), 189198 (2000).Google Scholar
4. Degallier, S., Righetti, L., Gay, S. and Ijspeert, A., “Toward simple control for complex, autonomous robotic applications: Combining discrete and rhythmic motor primitives,” Auton. Robots 31 (2–3), 155181 (2011).Google Scholar
5. Duysens, J. and Van de Crommert, H. W. A. A., “Neural control of locomotion; part 1: The central pattern generator from cats to humans,” Gait Posture 7 (2), 131141 (1998).Google Scholar
6. Farzaneh, Y., Akbarzadeh, A. and Akbari, A. A., “Online bio-inspired trajectory generation of seven-link biped robot based on T–S fuzzy system,” Appl. Soft Comput. 14, 167180 (2014).Google Scholar
7. Filippov, A. F., “A sufficient condition for the existence of a stable limit cycle for an equation of the second order,” Matematicheskii Sbornik 72 (1), 171180 (1952).Google Scholar
8. Gams, A., Ijspeert, A. J., Schaal, S. and Lenarčič, J., “On-line learning and modulation of periodic movements with nonlinear dynamical systems,” Auton. Robots 27 (1), 323 (2009).Google Scholar
9. Grillner, S., “Biological pattern generation: The cellular and computational logic of networks in motion,” Neuron 52 (5), 751766 (2006).Google Scholar
10. Hackenberger, F., “Balancing central pattern generator based humanoid robot gait using reinforcement learning,” Graz University of Technology (2007).Google Scholar
11. Ijspeert, A. J., “Central pattern generators for locomotion control in animals and robots: A review,” Neural Netw. (special issue) 21 (4), 642653 (2008).Google Scholar
12. Ijspeert, A. J., Nakanishi, J., Hoffmann, H., Pastor, P. and Schaal, S., “Dynamical movement primitives: Learning attractor models for motor behaviors,” Neural Comput. 25 (2), 328373 (2013).Google Scholar
13. Izhikevich, E. M. and Kuramoto, Y., “Weakly coupled oscillators,” Encyclopedia Math. Phys. 5, 448 (2006).Google Scholar
14. Kennedy, J., “Particle Swarm Optimization,” In: Encyclopedia of Machine Learning (Springer, New York, NY, 2010), pp. 760766.Google Scholar
15. Kiehn, O. and Butt, S. J. B., “Physiological, anatomical and genetic identification of CPG neurons in the developing mammalian spinal cord,” Prog. Neurobiol. 70 (4), 347361 (2003).Google Scholar
16. Peters, J. and Schaal, S., “Policy Gradient Methods for Robotics,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IEEE 2006) (2006) pp. 22192225.Google Scholar
17. Peters, J. and Schaal, S., “Natural actor-critic,” Neurocomputing 71 (7), 11801190 (2008).Google Scholar
18. Righetti, L. and Ijspeert, A. J., “Programmable Central Pattern Generators: An Application to Biped Locomotion Control,” Proceedings of 2006 IEEE International Conference on Robotics and Automation (ICRA 2006) (2006) pp. 15851590.Google Scholar
19. Righetti, L., Buchli, J. and Ijspeert, A. J., “Dynamic Hebbian learning in adaptive frequency oscillators,” Physica D. 216 (2), 269281 (2006).Google Scholar
20. Shahbazi, H., Jamshidi, K. and Monadjemi, A. H., “Modeling of mesencephalic locomotor region for NAO humanoid robot,” Ind. Robot. Int. J. 39 (2), 136145 (2012).Google Scholar
21. Strom, J., Slavov, G. and Chown, E., “Omnidirectional Walking Using Zmp and Preview Control for the NAO Humanoid Robot,” In: RoboCup 2009: Robot Soccer World Cup XIII (Springer, New York, NY, 2010) pp. 378389.Google Scholar
22. Zielińska, T., “Biological inspiration used for robots motion synthesis,” J. Physiol. (Paris) 103 (3), 133140 (2009).Google Scholar