Design and Experimentation of a Neural Network Controller for a Spherical Parallel Robot

Donatello Tina, Luca Carbonari, Massimo Callegari

Abstract

The paper deals with a neural network control for the gravity compensation of a parallel kinematics robot. The network has been designed in a simulation environment then it has been implemented in robot’s controller by using an FPGA device that is part of an embedded system. After the training phase, several experiments have been performed on the prototype manipulator and the related datasets have been collected and elaborated. In the end, a comparative analysis has shown the improved performance of the neural network controller with respect to the inverse dynamics one, mainly due to the well-known difficulties in deriving explicit models of friction and play in the joints.

References

  1. Callegari, M., Carbonari, L., Palmieri, G. and Palpacelli, M.-C. (2012). Parallel Wrists for Enhancing Grasping Performances. In: Grasping in Robotics, G. Carbone ed., Springer, 2012. (In press)
  2. Callegari, M., Marzetti, P., Olivieri, B. (2004). Kinematics of a Parallel Mechanism for the Generation of Spherical Motions, in J. Lenarcic and C. Galletti (eds), On Advances in Robot Kinematics, Kluwer, pp.449- 458.
  3. Carbonari, L. (2012). Extended analysis of the 3-CPU reconfigurable class of parallel robotic manipulators. Ph.D. Thesis, Polytechnic University of Marche, Ancona, Italy
  4. Cybenco, G. (1989). Approximation by Superpositions of a Sigmoidal Function. Mathematics Control, Signals and Systems, Vol. 4, no. 2, pp. 303-314.
  5. Hagan, M.T. & Menhai, M. (1994). Training feed-forward networks with the Marquardt algorithm, IEEE Transactions on Neural Networks, Vol.5, No. 6, pp.989-993
  6. King, S.-Y., and Hwang, J. -N. (1989). Neural network architectures for robotic applications. IEEE Transactions on Robotics and Automation, Vol. 5, no. 5, pp. 641-657.
  7. Kwan, H. K. (D. of E. E.). (1992). Simple sigmoid-like activation function for digital hardware implementation. Electronics Letters, Vol. 28, no. 15, pp. 1379-1380.
  8. Narendra, K. S. and Parthasarathy, K. (1990). Identification and control of dynamical systems using neural networks, IEEE Transaction on Neural Networks, Vol. 1, no. 1, pp. 4-27.
  9. Orlowska-Kowalska, K and Kaminski, M, (2011). FPGA Implementation of the Multilayer Neural Network for speed estimation of the Two-Mass Drive System. IEEE Transaction on Industrial Informatics, Vol. 7, no.3, pp. 436-445.
  10. Serrano, F. E. (2011). Neural Networks Models for Control and Identification of a Two Links Robotics Manipulator. Proceedings CONCAPAN XXXI.
  11. Zhang, D., & Lei, J. (2011). Kinematic analysis of a novel 3-DOF actuation redundant parallel manipulator using artificial intelligence approach. Robotics and Computer-Integrated Manufacturing, Vol. 27, no. 1, pp. 157-163.
Download


Paper Citation


in Harvard Style

Tina D., Carbonari L. and Callegari M. (2012). Design and Experimentation of a Neural Network Controller for a Spherical Parallel Robot . In Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8565-21-1, pages 250-255. DOI: 10.5220/0004047602500255


in Bibtex Style

@conference{icinco12,
author={Donatello Tina and Luca Carbonari and Massimo Callegari},
title={Design and Experimentation of a Neural Network Controller for a Spherical Parallel Robot},
booktitle={Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2012},
pages={250-255},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004047602500255},
isbn={978-989-8565-21-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - Design and Experimentation of a Neural Network Controller for a Spherical Parallel Robot
SN - 978-989-8565-21-1
AU - Tina D.
AU - Carbonari L.
AU - Callegari M.
PY - 2012
SP - 250
EP - 255
DO - 10.5220/0004047602500255