Use of Artificial Neural Networks for the Development of an Inverse Kinematic Solution and Visual Identification of Singularity Zone(s)

This paper presents a non-conventional technique for solving the inverse kinematics problem using artificial neural networks. A feed forward multi-layer perceptron with backpropagation neural network is selected for this research. An inverse kinematic solution for a PUMA 560 robot is developed by tr...

Full description

Saved in:
Bibliographic Details
Published in:Procedia CIRP 2014, Vol.17, p.812-817
Main Authors: Aggarwal, Luv, Aggarwal, Kush, Urbanic, Ruth Jill
Format: Article
Language:English
Subjects:
Artificial Neural Network (ANN)
Backpropagation
Feed Forward Network
Inverse Kinematics
Levenberg-Marquardt (LM)
Mean Square Error (MSE)
Multi Layer Perceptron (MLP)
PUMA 560
Singularity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a non-conventional technique for solving the inverse kinematics problem using artificial neural networks. A feed forward multi-layer perceptron with backpropagation neural network is selected for this research. An inverse kinematic solution for a PUMA 560 robot is developed by training the neural network with the robot's end-effector Cartesian co-ordinates and its corresponding joint configurations. Once the network is well trained (90th percentile) and confident predictions can be achieved, a test input set (singularity conditions) is introduced to the trained network to simulate results. This technique proves promising since it requires little computation time over other traditional methods.
ISSN:2212-8271
2212-8271
DOI:10.1016/j.procir.2014.01.107