An Artificial Neural Network approach for the obstacle avoidance of redundant robot manipulators

Abstract

In this article an artificial neural network (ANN) approach for the obstacle avoidance of redundant robot manipulators is presented. The approach is based on formulating an inverse kinematics problem under an inexact context. This procedure permits to deal with the avoidance of obstacles with an appropriate and easy to compute null space vector; whereas the avoidance of singularities is attained by the proper pseudo inverse perturbation. Here the computation of the inverse kinematics problem is performed by a properly trained ANN and including a null space vector for obstacle avoidance which is also realized by another properly trained ANN. The approach is tested on the simulation of a planar redundant manipulator performing some obstacle avoidance tasks. From the results obtained, the approach compares favorably with the numerical approach.