Hostname: page-component-cd9895bd7-gbm5v Total loading time: 0 Render date: 2024-12-23T15:58:02.219Z Has data issue: false hasContentIssue false
  • English
  • Français

Learning the forward kinematics behavior of a hybrid robot employing artificial neural networks

Published online by Cambridge University Press:  14 October 2011

Rongjie Kang ,
Hélène Chanal ,
Thomas Bonnemains ,
Sylvain Pateloup ,
David T. Branson III  and
Pascal Ray
Rongjie Kang*
Affiliation:
Laboratoire de Mécanique et Ingénieries, Institut Français de Mécanique Avancée, Rue Roche Genes 27, 63175 Aubiere, France
Hélène Chanal
Affiliation:
Laboratoire de Mécanique et Ingénieries, Institut Français de Mécanique Avancée, Rue Roche Genes 27, 63175 Aubiere, France
Thomas Bonnemains
Affiliation:
Laboratoire de Mécanique et Ingénieries, Institut Français de Mécanique Avancée, Rue Roche Genes 27, 63175 Aubiere, France
Sylvain Pateloup
Affiliation:
Laboratoire de Mécanique et Ingénieries, Institut Français de Mécanique Avancée, Rue Roche Genes 27, 63175 Aubiere, France
David T. Branson III
Affiliation:
Department of Advanced Robotics, Istituto Italiano di Tecnologia, Via Morego 30, 16163 Genova, Italy
Pascal Ray
Affiliation:
Laboratoire de Mécanique et Ingénieries, Institut Français de Mécanique Avancée, Rue Roche Genes 27, 63175 Aubiere, France
*
*Corresponding author. E-mails: [email protected]
Get access Rights & Permissions [Opens in a new window]

Summary

Hybrid robots, composed of a parallel platform and serial wrist, achieve a compromise of stiffness and dexterity. Thus, they are well suited for applications such as aircraft component machining and automotive assembly, where high accuracy and large workspace movements are required. However, their forward kinematics can be highly coupled and be nonlinear. To reduce the time required to define the forward kinematics of a robot with parallel–serial structure, this paper introduces the use of neural networks. Two radial basis function networks are trained to learn the parallel and serial kinematics separately, and then integrated into a complete model. The error of this network model is analyzed and identified by a particle swarm optimization algorithm. Simulation and experiment results are obtained from the hybrid robot, Exechon, which shows that the developed kinematic model is able to produce accurate position and orientation estimates of the end-effector. The computation time of the neural network model is greatly reduced when compared to the time achieved by the numerical model.

Keywords

Hybrid robotForward kinematicsNeural networkParticle swarm optimization
Type
Articles
Information
Robotica , Volume 30 , Issue 5 , September 2012 , pp. 847 - 855
Copyright
Copyright © Cambridge University Press 2011

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1.Neumann, K. E., “Robot,” US Patent 4732525 (United States Patent Office, Alexandria, VA, 1988).Google Scholar
2.Gogu, G., “Mobility Criterion and Overconstraints of Parallel Manipulators,” Proceedings of International Workshop on Computational Kinematics, Cassino, Italy (2005).Google Scholar
3.Dai, J. S., Huang, Z. and Lipkin, H., “Mobility of overconstrained parallel mechanisms,” ASME J. Mech. Des. 128 (1), 220–229 (2006).CrossRefGoogle Scholar
4.Merlet, J. P., Parallel Robots (Springer, Dordrecht, Netherlands, 2006)Google Scholar
5.Husty, M. L., “An algorithm for solving the direct kinematic of Stewart–Gough-type platforms,” Mech. Mach. Theory 31 (4), 365–380 (1996).CrossRefGoogle Scholar
6.Lee, T. Y. and Shim, J. K., “Forward kinematics for the general 6–6 Stewart platform using algebraic elimination,” Mech. Mach. Theory 36 (9), 1073–1085 (2001).CrossRefGoogle Scholar
7.Huang, X. G., Liao, Q. Z., Wei, S. M., Qiang, X. and Huang, S. G., “Forward Kinematics of the 6–6 Stewart Platform with Planar Base and Platform Using Algebraic Elimination,” Proceedings of the IEEE International Conference on Automation and Logistics, Jinan, China (2007).Google Scholar
8.Lazard, D., “Stewart Platform and Gröbner Basis,” Proceedings of ARK, Ferrare, Italy (1992).Google Scholar
9.Huang, X. G. and He, G. P., “Forward Kinematics of the General Stewart–Gough Platform Using Gröbner Basis,” Proceedings of the 2009 IEEE International Conference on Mechatronics and Automation, Changchun, China (2009).Google Scholar
10.Raghavan, M., “The Stewart platform of general geometry has 40 configurations,” J. Mech. Des. 115, 277–282 (1993).CrossRefGoogle Scholar
11.Sommese, A. J., Verschelde, J. and Wampler, C. W., “Advances in polynomial continuation for solving problems in kinematics,” Trans. ASME 126, 262–268 (2004).CrossRefGoogle Scholar
12.Merlet, J. P., “Solving the forward kinematics of a Gough-type parallel manipulator with interval analysis,” Int. J. Robot. Res. 23 (3), 221–235 (2004).CrossRefGoogle Scholar
13.Merlet, J. P., “Closed-Form Resolution of the Direct Kinematics of Parallel Manipulators Using Extra Sensors Data,” Proceedings of 1993 IEEE International Conference on Robotics and Automation, Atlanta, USA (1993).Google Scholar
14.Khalil, W., Garcia, G. and Delagarde, J. F., “Calibration of the Geometric Parameters of Robots Without External Sensors,” Proceedings of the 1995 IEEE International Conference on Robotics and Automation, Nagoya, Japan (1995).Google Scholar
15.Zhuang, H., “Self-calibration of parallel mechanisms with a case study on Stewart platforms,” IEEE Trans. Robot. Autom. 13 (3), 387–397 (1997).CrossRefGoogle Scholar
16.Besnard, S. and Khalil, W., “Identifiable Parameters for Parallel Robots Kinematic Calibration,” Proceedings of the 2001 IEEE International Conference on Robotics and Automation, Seoul, Korea (2001).Google Scholar
17.Luo, G. L. and Qin, S. Y., An Introduction to Intelligent Controls (Zhejiang Science and Technology, Hangzhou, China, 1997).Google Scholar
18.Hagan, M. T., Demuth, H. B. and Beale, M. H., Neural Network Design (PWS, Boston, MA, USA 1996).Google Scholar
19.Boudreau, R., Levesque, G. and Darenfed, S., “Parallel manipulator kinematics learning using holographic neural network models,” Robot. Comput.-Integr. Manuf. 14, 37–44 (1998).CrossRefGoogle Scholar
20.Dehghani, M., Ahmadi, M., Khayatian, A., Eghtesad, M. and Farid, M., “Neural Network Solution for Forward Kinematics Problem of HEXA Parallel Robot,” Proceedings of 2008 American Control Conference (ACC), Seattle, WA, USA (2008).Google Scholar
21.Yee, C. S. and Lim, K., “Forward kinematics solution of Stewart platform using neural networks,” Neurocomputing 16, 333–349 (1997).CrossRefGoogle Scholar
22.Hennes, N., “An Innovative Machinery Concept for High Performance 5-Axis Machining of Large Structural Components in Aircraft Engineering,” Proceedings of 3rd Chemnitz Parallel Kinematic Seminar, Chemnitz, Germany (2002).Google Scholar
23.Kennedy, J. and Eberhart, R., “Particle Swarm Optimization,” Proceedings of IEEE International Conference on Neural Networks (ICNN), Perth, Australia (1995).Google Scholar
24.Shi, Y. and Eberhart, R., “Parameter Selection in Particle Swarm Optimization,” Proceedings of the 1998 Conference on Evolutionary Computation, Alaska, USA (1998).Google Scholar
25.Eberhart, R. and Shi, Y., “Particle Swarm Optimization: Developments, Applications and Resources,” Proceedings of Congress on Evolutionary Computation 2001, Seoul, Korea (2001).Google Scholar
26.Zhou, J. L., Duan, Z. C., Li, Y., Deng, J. C. and Yu, D. Y., “PSO-based neural network optimization and its utilization in a boring machine,” J. Mater. Process. Technol. 178, 19–23 (2006).CrossRefGoogle Scholar
27.Yu, J. B., Wang, S. J. and Xia, L. F., “Evolving artificial neural networks using an improved PSO and DPSO,” Neurocomputing 71, 1054–1060 (2008).CrossRefGoogle Scholar
28.Chen, S., Cowan, C. F. N. and Grant, P. M., “Orthogonal least squares learning algorithm for radial basis function networks,” IEEE Trans. Neural Netw. 2 (2), 302–309 (1991).CrossRefGoogle ScholarPubMed
29.Neumann, K. E., “Exechon Concept – Parallel Kinematic Machines in Research and Practice,” Proceedings of 5th Chemnitz Parallel Kinematics Seminar, Chemnitz, Germany (2006).Google Scholar
30.Pateloup, S., Chanal, H. and Duc, E., “Geometric and Kinematic Modelling of a New Parallel Kinematic Machine Tool: The Tripteor X7 Designed by PCI,” Proceedings of 7th International Conference of Numerical Analysis and Applied Mathematics, Tarbes, France (2009).Google Scholar
31.Bi, Z. M., Jin, Y., Gibson, R. and McTotal, P., “Kinematics of Parallel Kinematic Machine Exechon,” Proceedings of the 2009 IEEE International Conference on Information and Automation, Zhuhai/Macau, China (2009).Google Scholar
32.Chanal, H., Duc, E., Ray, P. and Hascoët, J. Y., “A new approach for the geometrical calibration of parallel kinematics machines tools based on the machining of a dedicated part,” Int. J. Mach. Tools Manuf. 47, 1151–1163 (2007).CrossRefGoogle Scholar