Building maps of workspace for autonomous mobile robots using self-organizing neural networks

被引：0

作者：

Hori, K ^{[1
]}

Hashimoto, Y ^{[1
]}

Wang, SY ^{[1
]}

Tsuchiya, T ^{[1
]}

机构：

[1] Muroran Inst Technol, Muroran, Hokkaido 0508585, Japan

来源：

SOFT COMPUTING IN INDUSTRIAL APPLICATIONS | 2000年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a new method of building maps of workspace for autonomous mobile robots using self-organizing neural networks. By this method, the topological maps of the workspace can be self-organized from the relative distance data between a robot and walls on the workspace only using ultrasonic distance sensors. However, when the shape of the workspace is complicated, an unsuitable map with dead nodes or dead links may be generated. In this paper, we consider the cause of the problem, and we propose a new building maps algorithm which consists of two learning stages.

引用

页码：181 / 190

页数：10