Inverse kinematics in robotics using neural networks

https://doi.org/10.1016/S0020-0255(98)10098-1Get rights and content

Abstract

The inverse kinematics problem in robotics requires the determination of the jointangles for a desired position of the end-effector. For this underconstrained and ill-conditioned problem we propose a solution based on structured neural networks that can be trained quickly. The proposed method yields multiple and precise solutions and it is suitable for real-time applications.

References (18)

  • SAE Mathematical Formulae and Statistical Tables Book

    (1992)
  • L.L. Bao et al.

    Regularization of inverse kinematics for redundant manipulators using neural network inversions

  • A. Benard et al.

    Self-organizing feature maps and the travelling salesman problem

    Neural Networks

    (1988)
  • J.J. Craig

    Introduction to Robotics: Mechanisms and Controls

    (1989)
  • Dimitri et al.

    Comparison of some neural network and scattered data approximation: The inverse manipulator kinematics example

    Neural Computation

    (1994)
  • J. Duffy

    Analysis of Mechanisms and Robot Manipulators

    (1980)
  • R. Featherstone

    Position and velocity transformation between robot end-efTector coordinate and joint angle

    The International Journal of Robotics Research

    (1983)
  • J.U. Korein et al.

    Techniques for generating the goal-directed motion of articulated structures

    IEEE Computer Graphics and Applications

    (1982)
  • S. Lee et al.

    Inverse mapping of continuous functions using local and global information

    IEEE Transaction on Neural Networks

    (1994)
There are more references available in the full text version of this article.

Cited by (0)

View full text