A robot path planning scheme based on neural network. | [Journal of Theoretical and Applied Information Technology • 2012]

Author(s):

1. Lei Gao: School of Computer Science, Southwest Petroleum University, Chengdu 610500, Sichuan, China

2. Jiao Shen: School of Computer Science, Southwest Petroleum University, Chengdu 610500, Sichuan, China

3. Shulin Pan: School of Resources and Environment Engineering, Southwest Petroleum University, Chengdu 610500, Sichuan, China

Abstract:

A method of Robot path planning based neural network has been raised in order to guarantee that the robot can simultaneously avoid movable obstacle intelligently when it is reaching the destination. In the first instance, every robot will be divided into spheres of influence, and the influence map will be worked out at the same time. Then neural network is used to select the path. In view of the problems of neural network(such as local-optimization and poor convergence, etc.),genetic algorithm is added to optimize neural network to help finding the best path . This technology can be widely used in many fields such as the navigation and computer games. Especially, it can be used in games of robot path planning and will get ideal results.

Page(s): 654-658

DOI: DOI not available

Published: Journal: Journal of Theoretical and Applied Information Technology, Volume: 46, Issue: 2, Year: 2012

Keywords:

Keywords are not available for this article.

References:

References are not available for this document.

Citations

Citations are not available for this document.

Citations

Downloads

Views