Neural Network Control of a Biped Robot Model with Composite Adaptation Low

this paper presents a novel neural network controller with composite adaptation low to improve the trajectory tracking problems of biped robots comparing with classical controller. The biped model has 5_link and 6 degrees of freedom and actuated by Plated Pneumatic Artificial Muscle, which have a very high power to weight ratio and it has large stoke compared to similar actuators. The proposed controller employ a stable neural network in to approximate unknown nonlinear functions in the robot dynamics, thereby overcoming some limitation of conventional controllers such as PD or adaptive controllers and guarantee good performance. This NN controller significantly improve the accuracy requirements by retraining the basic PD/PID loop, but adding an inner adaptive loop that allows the controller to learn unknown parameters such as friction coefficient, therefore improving tracking accuracy. Simulation results plus graphical simulation in virtual reality show that NN controller tracking performance is considerably better than PD controller tracking performance.

Authors:

• Ahmad Forouzantabar

Keywords:

• Biped robot
• Neural network
• Plated Pneumatic Artificial Muscle
• Composite adaptation

References:

[1] K. Yokoi and al., "Humanoid robot's applications in HRP," in IEEE
International Conference on Humanoid Robots IEEE International
Conference on Humanoid Robots, Karlsruhe, Germany, 2003.
[2] F.Pfeiffer, K. Loffer, and M. Gienger, "Sensor and control aspects of
biped robot "Johnnie"," IEEE International Conference on Humanoid
Robots, Munich, Germany, 2003.
[3] Sony-PressRelease, "World's first running humanoid robot," December
18th 2003.
[4] K. Hirai, M. Hirose, Y. Haikawa, and T. Takenaka, , "The development
of honda homanoid robot," IEEE International Conference on Robotics
and Automation, Leuven, Belgium, pp. 1321{1326, 1998.
[5] Zhi Liu Yun Zhang Yaonan Wang,"A Type-2 Fuzzy Switching Control
System for Biped Robots", IEEE Transaction on systems, man and
cybernetics, Vol.37, No.6, November 2007.
[6] Zhi Liu, Chunwen Li,"Fuzzy Neural Networks Quadratic Stabilization
Output Feedback Control for Biped Robots via Hinf Approach", IEEE
Transaction on systems, man and cybernetics, Vol.32, No.1, February
2003.
[7] Verrelst B., Van Ham R., Vanderborght B., Daerden F. & Lefeber D."
The Pneumatic Biped "LUCY" Actuated with Pleated Pneumatic
Artificial Muscles". Autonomous Robots 18, pp.201-213, 2005.
[8] Verrelst B., Vermeulen J., Vanderborght B., Van Ham R., Naudet J.,
Lefeber D., Daerden F. & Van Damme M." Motion Generation and
Control for the Pneumatic Biped "Lucy", International Journal of
Humanoid Robotics (IJHR), Vol. 3, No. 1 (2006) 1-35.
[9] Vanderborght B., Verrelst B., Van Ham R. & Lefeber D. "Controlling a
Bipedal Walking Robot Actuated by Pleated Pneumatic Artificial
Muscles". Robotica, Volume 24, Issue 04, July 2006, pp 401-410.
[10] Bram Vanderborght, Ronald Van Ham, Björn Verrelst, Micha├½l Van
Damme & Dirk Lefeber "Locomotion Control Architecture for a Biped
Actuated with Pneumatic Artificial Muscles".Proceedings of the 15th
International Symposium on Measurement and Control in Robotics, 08-
10 November 2005, Brussels, Belgium.
[11] Vermeulen J., Verrelst B., Vanderborght B., & Lefeber D. "Trajectory
Planning for the Walking Biped "Lucy" ". The International Journal of
Robotics Research (IJRR), accepted for publication.
[12] Verrelst B. "A dynamic walking biped actuated by pleated pneumatic
artificial muscles: Basic concepts and control issues". PhD Dissertation,
Vrije Universiteit Brussel, February 2005.
[13] Daerden F "Conception and realization of pleated pneumatic artificial
muscles and their use as compliant actuation elements "PhD
Dissertation, Vrije Universiteit Brussel, July 1999.
[14] Ahmad Forouzantabar, Ahmadreza khoogar, mohammad javade
fakharzadegan, "Controlling a New Biped Robot Model Since Walking
Using Neural Network",IEEE ICIT Conference, March 2007,Shenzhen,
China.
[15] F.L.Lewis, S.Jagannathan and A. Yesildirek , "Neural Network Control
of Robot Manipulators and Nonlinear systems", Taylor & Francis ,
1999.
[16] Barron, A.R., ÔÇÿUniversal approximation bounf for superpositons of
sigmoidal function." IEEE Trans. Info. Theory, vol. 39, no. 3, pp.930-
945, May1993.
[17] Sanner R.M , Slotin, J.-J.E, and W. LI, "Stable adaptive control of robot
manipulators using "neural" networks", Neural Computation, Volume 7
, Issue 4 (July 1995) Pages: 753 - 790.
[18] Ahmad Forouzantabar, Ahmadreza khoogar, Ahmad Reza Vali, "Neural
Network Control of a New Biped Robot Model with Back Propagation
Algorithm", IEEE RO-MAN 2007, August 26-29, Korea.