Skip to main content
Springer Nature Link
Log in

Inverse Kinematics via a Network Ensemble and Learning Method

  • Conference paper
  • First Online:
Proceedings of the 22nd Engineering Applications of Neural Networks Conference (EANN 2021)

Part of the book series: Proceedings of the International Neural Networks Society ((INNS,volume 3))

  • 893 Accesses

Abstract

A difficult goal in robotics is solving the inverse kinematics for N degree-of-freedom (DOF) robotic arms. Solving for the joint angles for a robot to follow a specified trajectory is a complex task as this requires solving for the solution of an end-effector with respect to its links and base coordinates. Depending on the number of DOFs, finding a closed form solution becomes impossible to find and computationally expensive. An alternative to this consists of function approximations in the form of neural networks (NN). Neural networks have the utility of mapping functions to inherently nonlinear processes such as solving for the trajectories of complicated manipulators through an iterative process of updating weight coefficients based on cost functions, error criteria, and optimization algorithms. In this paper, we propose a method that combines several different NN models along with a method for specifying different batches from the training set based on a set of error criteria with the ultimate goal of improving accuracy.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016 )

    Google Scholar 

  2. 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 (2013). https://doi.org/10.1007/s00366-013-0313-2

    Article  Google Scholar 

  3. Nagata, F., et al.: Neural network-based inverse kinematics for an industrial robot and its learning method. In: The Proceedings of the 4th International Conference on Industrial Application Engineering (2016)

    Google Scholar 

  4. Almusawi, A.R.J., Dülger, L.C., Kapucu, S.: A new artificial neural network approach in solving inverse kinematics of robotic arm (Denso VP6242). Comput. Intell. Neurosci. 2016, 14 (2016)

    Article  Google Scholar 

  5. Wang, J., Li, Y., Zhao, X.: Inverse kinematics and control of a 7-DOF redundant manipulator based on the closed-loop algorithm. Int. J. Adv. Rob. Syst. 7(4), 37 (2010)

    Article  Google Scholar 

  6. Waegeman, T., Schrauwen, B.: Towards learning inverse kinematics with a neural network based tracking controller. In: Lu, B.-L., Zhang, L., Kwok, J. (eds.) ICONIP 2011. LNCS, vol. 7064, pp. 441–448. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-24965-5_50

    Chapter  Google Scholar 

  7. Köker, R., et al.: A study of neural network based inverse kinematics solution for a three-joint robot. Robot. Auton. Syst. 49, 227–234 (2004)

    Article  Google Scholar 

  8. Shah, S.K., Mishra, R., Ray, L.S.: Solution and validation of inverse kinematics using deep artificial neural network. Mater. Today Proc. 26, 1250–1254 (2020)

    Article  Google Scholar 

  9. Corke, P.I.: A simple and systematic approach to assigning Denavit-Hartenberg parameters. IEEE Trans. Rob. 23(3), 590–594 (2007)

    Article  Google Scholar 

  10. Jha, P., Biswal, B.B.: A neural network approach for inverse kinematic of a SCARA manipulator. IAES Int. J. Robot. Autom. 3, 31–40 (2014)

    Google Scholar 

  11. Csiszar, A., Eilers, J., Verl, A.: On solving the inverse kinematics problem using neural networks. In: 2017 24th International Conference on Mechatronics and Machine Vision in Practice (M2VIP). IEEE (2017)

    Google Scholar 

  12. Takatani, H., Araki, N., Sato, T., Konishi, Y.: Neural network-based construction of inverse kinematics model for serial redundant manipulators. Artif. Life Robot. 24(4), 487–493 (2019). https://doi.org/10.1007/s10015-019-00552-y

    Article  Google Scholar 

  13. Hasan, A.T., et al.: An adaptive-learning algorithm to solve the inverse kinematics problem of a 6 DOF serial robot manipulator. Adv. Eng. Softw. 37, 432–438 (2006)

    Article  Google Scholar 

  14. Sebastian Starke, DeepIK: GitHub repository (2017). https://github.com/sebastianstarke/DeepIK

  15. Rajpura, P.: Neural Networks for Inverse Kinematics. Github repository (2017). https://github.com/paramrajpura/Neural-Networks-for-Inverse-Kinematics

  16. Liu, Y.: On writing custom loss functions in Keras. Github repository (2019). https://github.com/yanfengliu/neural_inverse_kinematics

  17. Perceptrón, 7 March 2015. https://en.wikipedia.org/wiki/Perceptron

  18. Andersen, P.A.: An answer to questions about deep Q-learning. Stack Overflow (2019). https://stackoverflow.com/questions/56777123/questions-about-deep-q-learning

Download references

Acknowledgment

The authors would like to thank the students of Dr. Moh’s research group for their motivation and to Paaras Chand for helping us debug code.

Author information

Authors and Affiliations

  1. San Jose State University, San Jose, CA, 95192, USA

    Joshua Ramayrat & Teng-Sheng Moh

Authors
  1. Joshua Ramayrat
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Teng-Sheng Moh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Teng-Sheng Moh .

Editor information

Editors and Affiliations

  1. School of Engineering, Department of Civil Engineering, Democritus University of Thrace, Xanthi, Greece

    Lazaros Iliadis

  2. Faculty of Applied Sciences, University of Sunderland, Sunderland, UK

    John Macintyre

  3. School of Computing and Digital Technologies, Teesside University, Middlesbrough, UK

    Chrisina Jayne

  4. University of the West of England, Bristol, UK

    Elias Pimenidis

Rights and permissions

Reprints and permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ramayrat, J., Moh, TS. (2021). Inverse Kinematics via a Network Ensemble and Learning Method. In: Iliadis, L., Macintyre, J., Jayne, C., Pimenidis, E. (eds) Proceedings of the 22nd Engineering Applications of Neural Networks Conference. EANN 2021. Proceedings of the International Neural Networks Society, vol 3. Springer, Cham. https://doi.org/10.1007/978-3-030-80568-5_34

Download citation

Publish with us

Policies and ethics