Skip to main content
SpringerLink
Log in

Local Models for Learning Inverse Kinematics of Redundant Robots: A Performance Comparison

  • Conference paper
  • First Online:
Advances in Self-Organizing Maps and Learning Vector Quantization

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 428))

Abstract

In this paper we report the results of a comprehensive comparative analysis of the performances of six local models applied to the task of learning the inverse kinematics of a redundant robotic arm (Motoman HP6). The evaluated algorithm are the following ones: SOM-based Local Linear Mapping (LLM), Radial Basis Functions Network (RBFN), Local Model Network (LMN), Local Weighted Regression (LWR), Takagi-Sugeno-Kang Fuzzy Model (TSK) and Local Linear Mapping over K-winners (KSOM). Each algorithm is evaluated with respect to its accuracy in estimating the joint angles given the Cartesian coordinates along end-effector trajectories within the robot workspace. Also, a careful evaluation of the performances of the aforementioned algorithms is carried out based on correlation analysis of the residuals of the best model.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Available for download from www.cis.hut.fi/somtoolbox/.

  2. 2.

    Available in the Robotics Toolbox for Matlab [2].

References

  1. Barreto, G.A., Araújo, A.F.R., Ritter, H.J.: Self-organizing feature maps for modeling and control of robotic manipulators. J. Intell. Robot. Syst. 36(4), 407–450 (2003)

    Article  MATH  Google Scholar 

  2. Corke, P.: Robotics, Vision and Control: Fundamental Algorithms in MATLAB, vol. 73. Springer Science & Business Media (2011)

    Google Scholar 

  3. Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1), 489–501 (2006)

    Article  Google Scholar 

  4. Kohonen, T.: Essentials of the self-organizing map. Neural Netw. 37, 52–65 (2013)

    Article  Google Scholar 

  5. Köker, R., Çakar, T., Sari, Y.: A neural-network committee machine approach to the inverse kinematics problem solution of robotic manipulators. Eng. Comput. 30(4), 641–649 (2014)

    Article  Google Scholar 

  6. Murray-Smith, R., Johansen, T.A.: Local learning in local model networks. In: Proceedings of the ICANN’95, pp. 40–46 (1995)

    Google Scholar 

  7. Poggio, T., Girosi, F.: Networks for approximation and learning. Proc. IEEE 78(9), 1481–1497 (1990)

    Article  Google Scholar 

  8. Schaal, S., Atkeson, C.G., Vijayakumar, S.: Scalable techniques from nonparametric statistics for real time robot learning. Appl. Intell. 17(1), 49–60 (2002)

    Article  MATH  Google Scholar 

  9. Souza, L.G.M., Barreto, G.A.: On building local models for inverse system identification with vector quantization algorithms. Neurocomputing 73(10–12), 1993–2005 (2010)

    Article  Google Scholar 

  10. Takagi, T., Sugeno, M.: Fuzzy identification of systems and its application to modeling and control. IEEE Trans. Syst. Man Cybern. 15(1), 116–132 (1985)

    Article  MATH  Google Scholar 

  11. Walter, J., Ritter, H., Schulten, K.: Non-linear prediction with self-organizing map. In: Proceedings of the IJCNN’90, pp. 587–592 (1990)

    Google Scholar 

Download references

Acknowledgments

Authors thank CNPq (grant 309841/2012-7) and NUTEC for their financial support.

Author information

Authors and Affiliations

  1. Department of Teleinformatics Engineering, Center of Technology, Federal University of Ceará (UFC), Campus of Pici, Fortaleza, Ceará, Brazil

    Humberto I. Fontinele, Davyd B. Melo & Guilherme A. Barreto

Authors
  1. Humberto I. Fontinele
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Davyd B. Melo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Guilherme A. Barreto
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Humberto I. Fontinele , Davyd B. Melo or Guilherme A. Barreto .

Editor information

Editors and Affiliations

  1. Department of Statistics, Rice University, Houston, Texas, USA

    Erzsébet Merényi

  2. Department of Electrical and Computer En, Air Force Institute of Technology, Wright-Patterson AFB, Ohio, USA

    Michael J. Mendenhall

  3. Applied Physics, Rice University, Houston, Texas, USA

    Patrick O'Driscoll

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Fontinele, H.I., Melo, D.B., Barreto, G.A. (2016). Local Models for Learning Inverse Kinematics of Redundant Robots: A Performance Comparison. In: Merényi, E., Mendenhall, M., O'Driscoll, P. (eds) Advances in Self-Organizing Maps and Learning Vector Quantization. Advances in Intelligent Systems and Computing, vol 428. Springer, Cham. https://doi.org/10.1007/978-3-319-28518-4_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-28518-4_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-28517-7

  • Online ISBN: 978-3-319-28518-4

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation