The Research of Car Rear-end Warning Model Based on MAS and Behavior

被引：5

作者：

Liang Jun ^{[1
]}

Cheng Xian-yi ^{[1
]}

Chen Xiao-bo ^{[1
]}

机构：

[1] JiangSu Univ, Sch Comp Sci & Commun Engn, Zhenjiang 212013, Peoples R China

来源：

2008 WORKSHOP ON POWER ELECTRONICS AND INTELLIGENT TRANSPORTATION SYSTEM, PROCEEDINGS | 2008年

关键词：

D O I：

10.1109/PEITS.2008.31

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

The distance between vehicles measurement is the only factor in traditional car rear-end alarm system. An alarming model based on MAS(Multi-Agent Systems) and driver's behavior is proposed to address the above problem. It is composed of four different types of agent interface-agent, features-extraction-agent, recognition-agent and alarm-agent) which can either work alone or collaboration through a communication protocol based on the extended KQML. The rear-end alarming algorithm utilize Bayes decision theory to calculate the probability of collision and prevent its occurrence real-time. So autonomy and reliability was enhanced in the proposed system. The effectiveness and robustness of the model have been confirmed by the simulated experiments.

引用

页码：305 / 309

页数：5