Mobile robot fuzzy control optimization using genetic algorithm

被引：21

作者：

Ming, L

Guan, ZL

Yang, SZ

机构：

[1] Sch. of Mech. Sci. and Engineering, Huazhong Univ. of Sci. and Technol., Wuhan

来源：

ARTIFICIAL INTELLIGENCE IN ENGINEERING | 1996年 / 10卷 / 04期

基金：

中国国家自然科学基金;

关键词：

fuzzy logic; genetic algorithm; mobile robot; obstacle avoidance; evolution; intelligent control;

D O I：

10.1016/0954-1810(96)00006-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A general method for optimizing the behavior of fuzzy control systems that receive sensory information from a robot is presented. Fuzzy control systems use a set of fuzzy variables. The fuzzy membership functions that define these variables perform a bind of packing of information from the sensors. These fuzzy membership functions have an unfixed shape and a set of unfixed points that may be adjusted to obtain a good performance of the control system. Genetic algorithms are a search technique analogous to natural genetics. The DPE (dynamic parameter encoding) algorithm is a mechanism that is more adaptable for controlling the mapping from fixed-length binary genes to real values. Genetic information encoding and the implemented genetic algorithms are used to adjusted the fuzzy membership functions associated with the linguistic labels that define the fuzzy variables of a rule-based control system. The control system designed allows a mobile semiautonomous robot to avoid unexpected obstacles in a partially unknown environment. Copyright (C) 1996 Elsevier Science Ltd.

引用

页码：293 / 298

页数：6