Abstract
This paper proposes a parallel stochastic approach to neural oscillator based motion control for bipedal humanoid locomotion. The motion control is based on the Central Pattern Generator (CPG), and is optimized by Simulated Annealing. Optimization of parameters in the motion control based on the CPG is a very hard problem. The number of the parameters which should be optimized increases as a robot’s link structure becomes complicated. To optimize all parameters simultaneously may cause explosion of search space. Therefore, we divide search space into upper-limbs optimization space and leg optimization space. We then propose a parallel optimization method by two processes, which handles the control parameters of upper-limbs and legs, and communicates them each other. In the experiments, our method succeeded in optimization of all parameters without explosion of search space, and performed superior gaits.
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.
References
Endo, K., Yamasaki, F., Maeno, T., Kitano, H.: Generation of optimal biped walking for humanoid robot by co-evolving morphology and controller. In: PRICAI 2002. Trends in Artificial Intelligence, pp. 325–334 (2002)
Fukuoka, H., Kimura, H.: Biologically inspired adaptive dynamic walking of a quadruped on irregular terrain. The Robotics Society of Japan 21(5), 1–12 (2003) (in Japanese)
Itoh, Y., Taki, K., Kato, S., Itoh, H.: A stochastic optimization method of CPG-based motion control for humanoid locomotion. In: IEEE Conference on Robotics, Automation and Mechatronics (RAM 2004), pp. 347–351 (2004)
Kurita, Y., Ueda, J., Matsumoto, Y.: CPG-based manipulation: Generation of rhythmic finger gaits from human observation. In: IEEE International Conference on Robotics and Automation, pp. 1209–1214 (2004)
Matsuoka, K.: Sustained oscillations generated by mutually inhibiting neurons with adaption. Biological Cybernetics 52, 367–376 (1985)
Matsuoka, K.: Mechanisms of frequency and pattern control in the neural rhythm generators. Biological Cybernetics 56, 345–353 (1987)
Shimada, S., Egami, T., Ishimura, K., Wada, M.: Neural control of quadruped robot for autonomous walking on soft terrain. In: 6th International Symposium on Distributed Autonomous Robotic Systems, pp. 415–423 (2002)
Taga, G.: A model of the neuro-musculo-skeletal system for human locomotion i. emergence of basic gait. Biological Cybernetics 73, 97–111 (1995)
Taga, G., Yamaguchi, Y., Shimizu, H.: Self-organized control of bipedal locomotion by neural oscillators. Biological Cybernetics 65, 147–159 (1991)
Taki, K., Itoh, Y., Kato, S., Itoh, H.: Motion generation for bipedal robot using neuro-musculo-skeletal model and simulated annealing. In: IEEE Conference on Robotics, Automation and Mechatronics (RAM 2004), pp. 699–703 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Itoh, Y., Taki, K., Iwata, S., Kato, S., Itoh, H. (2005). Parallel Stochastic Optimization for Humanoid Locomotion Based on Neural Rhythm Generator. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3684. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11554028_103
Download citation
DOI: https://doi.org/10.1007/11554028_103
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28897-8
Online ISBN: 978-3-540-31997-9
eBook Packages: Computer ScienceComputer Science (R0)