Applying Neural Network to Inverse Kinematic Problem for 6R Robot Manipulator with Offset Wrist

  • Z. Bingul
  • H. M. Ertunc
  • C. Oysu


An Artificial Neural Network (ANN) using backpropagation algorithm is applied to solve inverse kinematics problems of industrial robot manipulator. 6R robot manipulator with offset wrist was chosen as industrial robot manipulator because geometric feature of this robot does not allow to solve inverse kinematics problems analytically. In other words, there is no closed form solution for this problem. As the number of neurons at hidden layer is varied between 4 and 32, the robot joint angles (θ1θ2θ6) were predicted with average errors of 8.9°, 7.8°, 8.3°, 13°, 8.5°, and 10.5° for the 1st, 2nd, 3rd, 4th and 6th joint, respectively.


Artificial Neural Network Hide Layer Joint Angle Robot Manipulator Cartesian Space 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Guez, A., Ahmad, Z., (1989) Accelerated Convergence in the Inverse Kinematics via Multilayer Feedforward Networks. IJCNN89. vol. II, 341–344Google Scholar
  2. [2]
    Guez, A., Ahmad, Z. (1989) A Solution to the Inverse Kinematic in Robotics Using Neural Network Processing. IJCNN89. vol. II, 299–304Google Scholar
  3. [3]
    Nguyen, L., Patel, RV., Khorasani, K. (1990) Neural Network Architectures for the Forward Kinematics Problem in Robotics. IJCNN90. vol. III, 393–399Google Scholar
  4. [4]
    Lee, S., Kil, RM. (1990) Robot Kinematic Control based on Bidirectional mapping Neural Network. IJCNN90. vol. III, 327–335Google Scholar
  5. [5]
    Torras, C. (1993)Symbolic planning versus neural control in robots. From Neural Networks to Artifical Intelligence, Research Notes in Neural Computing 4, Springer-Verlag: Berlin Heidelberg New-York, 509–523.Google Scholar
  6. [6]
    Krose, BJA. and van der Smagt, PP. (1993) An Introduction to Neural Networks. 5th ed. Chap. 7 Robot Control, University of Amsterdam.Google Scholar
  7. [7]
    Xiaolin, Z., Lewis, J., N-Nagy, FL. (1996) Inverse Robot Calibration Using Artificial Neural Networks. Engineering Applications of Artificial Intelligence, 9: 83–93.CrossRefGoogle Scholar
  8. [8]
    Lou, YF., Brunn, P. (1999) A Hybrid Artificial Neural Network Inverse Kinematic Solution for Accurate Robot Path Control. Proceedings of the I MECH E Part I Journal of Systems & Control in Engineering, 213: 23–32.Google Scholar
  9. [9]
    Martn, P., Millan, JDR. (2000) Robot arm reaching through neural inversions and reinforcement learning. Robotics and Autonomous Systems, 31: 227–246.CrossRefGoogle Scholar
  10. [10]
    Oyama, E.,, (2001) Inverse Kinematics Learning by Modular Architecture Neural Networks with Performance Prediction Networks. Proc. IEEE Int. Conf. on Robotics and Automation, 1006–1012Google Scholar
  11. [11]
    Vijayakumar, S., D’souza, A., Shibata, T., Conradt, J., Schaal, S., (2002) Statistical Learning for Humanoid Robots. Autonomous Robots, 12: 55–69CrossRefGoogle Scholar
  12. [12]
    Torras C. (2003) Handbook of Brain Theory and Neural Networks, 2nd ed. MIT Press, Cambridge, Massachusetts, 979–983Google Scholar

Copyright information

© Springer-Verlag/Wien 2005

Authors and Affiliations

  • Z. Bingul
    • 1
  • H. M. Ertunc
    • 1
  • C. Oysu
    • 1
  1. 1.Department of Mechatronics EngineeringKocaeli UniversityTurkey

Personalised recommendations