A Fuzzy Logic-Based Framework for Route Choice in Vehicle Navigation Systems

作     者：YANG Qun,\ ZHAO Ya\|nanITS research center, Northern Jiaotong University, Beijing 100044, China 

出 版 物：《Systems Science and Systems Engineering》 (系统科学与系统工程学报（英文版）)

年 卷 期：2000年第10卷第4期

页      面：467-474页

核心收录：

学科分类：07[理学] 070104[理学-应用数学] 0701[理学-数学] 

主　　题：vehicle navigation systems intelligent transportation systems fuzzy logic 

摘      要：Vehicle Navigation Systems (VNS) is an important component of Intelligent Transportation Systems (ITS). These Systems are designed to assist drivers in making pre trip and enroute travel choice decisions, and typically, they must provide route choice, route guidance and other related services. Although there have been a lot of existed systems in the market, and most of them used lots of contemporary technologies, they are believed short of ″true intelligence″, because they paid little attention to the subjective issues in driver′s route choice behavior, such as travel objectives and personal preferences, etc. \;However, the VNS is designed for its users, and the successful implementation of VNS is largely dependent on the driver′s acceptance. If the driver feels that the VNS can′t give him (her) a satisfactory choice, he (she) will not use it, then, the marketing value of VNS will decline. And on the whole, the transport benefit that is mainly gained by the wide use of ITS will lost. \;Supported by the research project of ″Beijing Intelligent Urban Transportation Systems″, this paper presents a conceptual model to deal with this problem. We first defined the driver′s objective as a linguistic statement that has a set of attributes. These attributes are then treated as the fuzzy sets on the universal of all the existed routes. By determining each attribute′s membership function and assign driver dependent perception to these attributes, we can change the multi criteria route choice problem into a fuzzy logic based decision making problem. Then, to meet the demands of dynamic real time route selection, we use a limited routes set for choice and can swiftly get a satisfactory solution that we think is the driver′s actually needs.