Abstract
In this chapter the design and evaluation of artificial neural networks for learning static and dynamic positioning behavior of an industrial robot are presented. For the collection of training data, an approach based on the Levenberg–Marquardt algorithm was used to calibrate the robot and the coordinate measuring machine to a common reference system. A sequential approach for the network design development is presented. The network was verified by measuring different robot path segments with varying motion parameters, e.g. speed, payload and path geometry. Different layouts and configurations of feed-forward networks with backpropagation learning algorithms were examined resulting in a multi-layer network based on the calculation of the forward transformation.
Based on Learning Robot Behavior with Artificial Neural Networks and a Coordinate Measuring Machine, by Benjamin Johnen, Carsten Scheele and Bernd Kuhlenkötter which appeared in the Proceedings of the 5th International Conference on Automation, Robotics and Applications (ICARA 2011). © 2011 IEEE.
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
References
J.J. Craig, Introduction to robotics: mechanics and control, 3rd edn. (Addison-Wesley, Reading and Massachusetts, 2005)
J.M.S.T. Motta, R.S. Mcmaster, Modeling, optimizing and simulating robot calibration with accuracy improvement. J. Brazilian Soc. Mech. Sci. 21, 384–401 (1999)
J. Moré, in The Levenberg-Marquardt Algorithm: Implementation and Theory, Numerical Analysis, volume 630 of Lecture Notes in Mathematics, ed. by G. Watson (Springer, Berlin/Heidelberg, 1978)
Levmar: Levenberg-Marquardt nonlinear least squares algorithms in C/C++. http://www.ics.forth.gr/lourakis/levmar/index.html. Accessed 02 Mar 2012
M. Dehghani, M. Ahmadi, A. Khayatian, M. Eghtesad, M. Farid, Neural network solution for forward kinematics problem of HEXA parallel robot. Am. Control Conf., 4214–4219 (2008)
A. Ghobakhloo, M. Eghtesad, Neural network solution for the forward kinematics problem of a redundant hydraulic shoulder. Ind. Electron. Soc. (IECON) 31st Annu. Conf. IEEE, 6 (2005)
H. Sadjadian, H.D. Taghirad, A. Fateh, Neural networks approaches for computing the forward kinematics of a redundant parallel manipulator. Int. J. Comput. Intell. 2(1), 40–47 (2005)
L. Nguyen, R.V. Patel, K. Khorasani, Neural network architectures for the forward kinematics problem in robotics. JCNN Int. Jt. Conf. Neural Networks 3, 393–399 (1990)
A.T. Hasan, A.M.S. Hamouda, N. Ismail, H.M.A.A. Al-Assadi, An artificial neural network strategy for the forward kinematics of robot control. Int. J. Intell. Syst. Technol. Appl. 2, 41–49 (2007)
Y.I. Al-Mashhadany Inverse kinematics problem (IKP) of 6-DOF manipulator by locally recurrent neural networks (LRNNs). Int. Conf. Manage. Service Sci. (MASS), 1–5 (2010)
S. Manigpan, S. Kiattisin, A. Leelasantitham, A simulation of 6R industrial articulated robot arm using backpropagation neural network. Int Conf. Control Autom. Syst. (ICCAS), 823–826 (2010)
Y. Sahin, I. Eski, A QP artificial neural network inverse kinematic solution for accurate robot path control. J. Mech. Sci. Technol. 20, 917–928 (2006)
T. Bhattacharjee, A. Bhattacharjee, A study of neural network based inverse kinematics solution for a planar three joint robot with obstacle avoidance. Assam Univ. J. Sci. Technol. 5(2), (2010)
Stuttgart Neural Network Simulator (SNNS). http://www.ra.cs.uni-tuebingen.de/SNNS/. Accessed 02 Mar 2012
M. Riedmiller, H. Braun, A direct adaptive method for faster backpropagation learning: the RPROP algorithm. IEEE Int. Conf. Neural Networks 1, 586–591 (1993)
Acknowledgments
This work has been funded by the Deutsche Forschungsgemeinschaft (German Research Foundation) as part of the Sonderforschungsbereich (collaborative research center) 708, project A4 “Efficient simulation of dynamic effects in surface oriented robot processing”. We thank the Deutsche Forschungsgemeinschaft for the support of this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Johnen, B., Scheele, C., Kuhlenkötter, B. (2013). Neural Network Development and Training for the Simulation of Dynamic Robot Movement Behavior. In: Sen Gupta, G., Bailey, D., Demidenko, S., Carnegie, D. (eds) Recent Advances in Robotics and Automation. Studies in Computational Intelligence, vol 480. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37387-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-37387-9_1
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37386-2
Online ISBN: 978-3-642-37387-9
eBook Packages: EngineeringEngineering (R0)