Advertisement

Solving the Forward Kinematics of Cable-Driven Parallel Robots with Neural Networks and Interval Arithmetic

  • Valentin SchmidtEmail author
  • Bertram Müller
  • Andreas Pott
Conference paper
Part of the Mechanisms and Machine Science book series (Mechan. Machine Science, volume 15)

Abstract

This paper investigates a new approach for solving the forward kinematics of cable-driven parallel robots. This approach combines an interval algorithm with neural networks to provide a fast but accurate initial guess. The neural networks increase the computation speed by a factor of 200 or more, while the interval algorithm provides guaranteed convergence and a definite solution to any chosen degree of accuracy. Iterative techniques are faster still, but the proposed algorithm is considered real-time feasible.

Keywords

Cable-driven robots Neural networks Interval analysis Kinematics 

Notes

Acknowledgments

This work was partially supported by the Fraunhofer-Gesellschaft Internal Programs under Grant No. WISA 823 244. Furthermore, the research leading to these results received founding for the European Community’s Seventh Framework Program under Grant agreement number NMP2-SL-2011-285404-CableBot.

References

  1. 1.
    Bergmeir, C., Benítez, J.M.: Neural networks in R using the Stuttgart neural network simulator: RSNNS. J. Stat. Softw. 46(7), 1–26 (2012). http://www.jstatsoft.org/v46/i07/
  2. 2.
    Berti, A., Merlet, J.P., Carricato, M.: Solving the direct geometrico-static problem of 3–3 cable-driven parallel robots by interval analysis: preliminary results. In: Bruckmann, T., Pott, A. (eds.) Cable-Driven Parallel Robots. vol. 12, pp. 251–268. Springer, Heidelberg (2013)Google Scholar
  3. 3.
    Bosscher, P., Williams II, R.L.: Cable-suspended robotic contour crafting system. Autom. Constr. 17(1), 45–55 (2007)CrossRefGoogle Scholar
  4. 4.
    Carricato, M., Abbasnejad, G.: Direct geometrico-static analysis of under-constrained cable-driven parallel robots with 4 cables. In: Bruckmann, T., Pott, A. (eds.) Cable-Driven Parallel Robots. vol.12, pp. 269–285 (2013)Google Scholar
  5. 5.
    Ghasemi, A., Eghtesad, M., Farid, M.: Neural network solution for forward kinematics problem of cable robots. J. Intell. Rob. Syst. 60(2), 201–215 (2010)CrossRefzbMATHGoogle Scholar
  6. 6.
    Goualard, F.: Fast and correct SIMD algorithms for interval arithmetic. In: Proceedings of PARA ’08, Lecture Notes in Computer Science. Springer, Trondheim (2010)Google Scholar
  7. 7.
    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
  8. 8.
    Khalilpour, S., Loloei, A., Taghirad, H., Masouleh, M.: Feasible kinematic sensitivity in cable robots based on interval analysis. In: Bruckmann, T., Pott, A. (eds.) Cable-Driven Parallel Robots, vol. 12, pp. 233–249. Springer, Heidelberg (2013)Google Scholar
  9. 9.
    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
  10. 10.
    Pott, A.: An algorithm for real-time forward kinematics of cable-driven parallel robots. International symposium on advances in robot kinematics, Springer (2010)Google Scholar
  11. 11.
    Shary, S.: Interval Gauss-Seidel method for generalized solution sets to interval linear systems. Reliable Comput. 7, 141–155 (2001)CrossRefzbMATHMathSciNetGoogle Scholar
  12. 12.
    Won Jeong, J., Hyun Kim, S., Keun Kwak, Y.: Kinematics and workspace analysis of a parallel wire mechanism for measuring a robot pose. Mech. Mach. Theory 34(6), 825–841 (1999)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  • Valentin Schmidt
    • 1
    Email author
  • Bertram Müller
    • 1
  • Andreas Pott
    • 1
  1. 1.Fraunhofer Institute for Manufacturing Engineering and Automation IPAStuttgartGermany

Personalised recommendations