Using Toe-Off Impulse to Control Chaos in the Simplest Walking Model via Artificial Neural Network

Authors:
Saeed Jamali;Karim Faez;Sajjad Taghvaee;Mostafa Ozlati Moghadam
Affiliations:
Department of Computer Engineering, Islamic Azad University Branch of Ghazvin, Ghazvin, Iran;School of Electrical Engineering, Amirkabir University of Tehnology, Tehran, Iran;Department of Mechanical Engineering, Amirkabir University, Tehran, Iran;School of Engineering and Computer Sience, Australian National University, Canberra, Australia
Venue:
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part III
Year:
2009

Citing 7
Cited 0

Control of a four-link biped in a back somersault maneuver

IEEE Transactions on Systems, Man and Cybernetics - Special issue on artificial intelligence
Passive dynamic walking

International Journal of Robotics Research
Limit Cycles in a Passive Compass GaitBiped and Passivity-Mimicking Control Laws

Autonomous Robots
Generating globally optimised sagittal gait cycles of a biped robot

Robotica
A comparative study of stability margins for walking machines

Robotica
Passive dynamic walking model with upper body

Robotica
Modeling, stability and control of biped robots-a general framework

Automatica (Journal of IFAC)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Controlling chaos in a passive biped robot with an artificial neural network is investigated in this paper. The dynamical model is based on the compass-like biped robot proposed by Garcia et al. (1998) with a point-mass at the hip and infinitesimal point-masses at the feet ignoring the scuffing situation. The governing dynamics and chaotic behavior of the system is explored and the bifurcation diagram is drawn with respect to the ramp slope. Controlling chaos is based on stabilizing the unstable periodic orbits in the chaotic attractor. The UPOs are detected using an iterated algorithm. The artificial neural network is constructed using the information of seven previous steps and the control parameters in each one. The network is trained to find the appropriate control parameter in order to put the next step on the unstable periodic orbit. The control parameter is the toe-off impulse at the heel strike.