Neural network approach to collision free path-planning for robotic manipulators

Author: Pashkevich A.   Kazheunikau M.   Ruano A. E.  

Publisher: Taylor & Francis Ltd

ISSN: 1464-5319

Source: International Journal of Systems Science, Vol.37, Iss.8, 2006-06, pp. : 555-564

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

The paper deals with collision free path-planning for industrial robotic manipulators A new efficient approach is proposed that is based on the topologically ordered neural network model. This model describes harmonic potential field of the robot configuration space, sampled by the non-regular grid. The developed path-planning algorithm takes into account highly-irregular shape of the obstacles of welding and assembling robotic cells, and provides reduced number of collision checking. The stability of the topologically ordered neural network is investigated. The algorithm has been successfully applied to the off-line programming of a robotic manufacturing cell for the automotive industry.