预览加载中，请您耐心等待几秒...

快速路车辆跟驰建模与仿真研究（英文）.docx

预览
1/2
2/2

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

快速路车辆跟驰建模与仿真研究（英文） Introduction Vehiclefollowingbehaviorisoneofthemainfactorsthataffectroadtrafficperformanceandsafety.Itreferstohowdriversadjusttheirspeedanddistancefromthevehiclesinfrontoftheminordertomaintainacomfortableandsafetravelingcondition.Thestudyofvehiclefollowingbehaviorhasimplicationsfordevelopingefficientandsafetrafficcontrolsystems,improvingroadsafety,andunderstandingthepsychologicalaspectsofdriving.Inthispaper,wefocusonthemodelingandsimulationoffastroadvehiclefollowingbehavior. Literaturereview Vehiclefollowingmodelsareclassifiedintotwomaincategories:microscopicmodelsandmacroscopicmodels.Microscopicmodelsarebasedonthebehaviorofindividualvehicles,takingintoaccountvehicledynamics,drivercharacteristics,andexternalfactorssuchasroadgeometry,trafficdensity,andweatherconditions.Macroscopicmodels,ontheotherhand,describetrafficflowatanaggregatelevel,usingtrafficdensity,flowrate,andspeedasvariables. Therearenumerousmicroscopicmodelsavailableintheliterature.ThemostwidelyusedmodelsincludetheIntelligentDriverModel(IDM)andtheGeneralMotorsCarFollowingModel(GMC).Thesemodelsconsidertheacceleration,speed,anddistancebetweenvehiclesasthekeyvariablesthatdeterminethedynamicsofvehiclefollowing.Forexample,theIDMmodelassumesthatdriversadjusttheiraccelerationbasedonthedifferencebetweentheirdesiredspeedandthespeedoftheleadvehicle,theirdesiredheadway,andasafetyfactorthatrepresentsthedriver'sreactiontimeandbrakingcapacity.TheGMCmodel,ontheotherhand,assumesthatdriverssettheirspeedbasedontheleadvehicle'sspeedandtheirdesiredheadway,andadjusttheiraccelerationbasedonthedistancebetweenthetwovehicles. Inrecentyears,machinelearningtechniqueshavebeenusedtomodelvehiclefollowingbehavior.Thesetechniquesusedata-drivenapproachestolearnfromactualdrivingbehaviorandpredictfuturetrajectoriesandinteractionsbetweenvehicles.Forexample,DeepReinforcementLearning(DRL)hasbeenusedtomodelvehiclefollowingbehaviorincomplextrafficscenarios.DRLisatypeofartificialintelligencemethodthatusestrial-and-errorlearni