An Autonomous Overtaking Maneuver Based on Relative Position Information  

作　　者：Meihong Zhang Tingting Zhang Liuqing Yang Hongguang Xu Qinyu Zhang 

机构地区：[1]Harbin Institute of Technology(Shenzhen),Shenzhen 518055,Chin [2]Shenzhen Peng Cheng Laboratory(PCL),Shenzhen 518055,China

出　　处：《Journal of Communications and Information Networks》2019年第2期101-110,共10页通信与信息网络学报（英文）

基　　金：supported by the Natural Science Foundation of China(under Grant No.91638204 and 61771159);Guangdong Natural Science Foundation under Grant No.2017A030313392;Shenzhen Fundamental Research Project under Grant No.JCYJ20170811153639780。

摘　　要：Reliable and efficient overtaking maneuvers are important and challenging for autonomous vehicles.Higher precision position information is thus required,rather than that traditional global navigation satellite systems can provide.In this paper,we try to perform reliable autonomous overtaking controls of vehicles,mainly based on the“relative”position information,including the distance,angle and velocity between vehicles,which can be achieved by on-board radars.To reduce the complexity of maneuvers,a fuzzy inference system is applied to analyze the driving behavior of the preceding vehicle based on the obtained consecutive relative position information.An output of“safe”or“dangerous”will be sent to the decision part based on reinforcement learning frameworks.Various overtaking maneuvers including“conservative”and“aggressive”can be obtained accordingly.Furthermore,we propose another overtaking strategy that vehicles can share their maneuver information during overtaking process via wireless links.Numeric results validate our analysis,and can provide meaningful performance benchmarks for practical system implementations.

关 键 词：autonomous driving relative position information fuzzy inference reinforcement learning overtaking control 

分 类 号：TN9[电子电信—信息与通信工程]