基于模糊推理的换道决策与仿真验证

Lane Change Decision and Simulation Verification Based on Fuzzy Reasoning

换道决策是汽车换道过程中的重要环节,合理的决策模型可以有效减少由于车辆危险换道行为所引发的交通事故。为使换道模型能适应动态交通道路环境,以美国交通部联邦公路管理局NGSIM项目采集的实时数据为依据,提取车辆换道时交互车辆的相对距离、车速等相关特征参数并分析,基于模糊推理理论建立车辆换道动态决策模型;通过搭建的Prescan与MATLAB/Simulink联合仿真平台,采用NGSIM实测数据对换道决策模型进行验证。结果表明,基于模糊推理的二元决策换道模型准确率达到85%,能准确判断换道时机,可为智能车换道提供理论基础。

Lane change decision making is an important part in the lane change process of a vehicle.Reasonable decision model can effectively reduce traffic accidents caused by dangerous lane change behavior of vehicles.In order to enable the lane change model to adapt to dynamic traffic road environments,based on the real-time data collected by the NGSIM project of the Federal Highway Administration of the United States Department of Transportation,the relative distance,speed and other relevant characteristic parameters of interactive vehicles during lane change were extracted and analyzed.The dynamic decision model of vehicle lane changing was established based on fuzzy reasoning theory.Through the established Prescan and MATLAB/Simulink co-simulation platform,the NGSIM measured data was used to verify the lane change decision model.The results show that the accuracy of the binary decision lane change model based on fuzzy reasoning reaches 85%and can accurately determine the lane change timing,which can provide a theoretical basis for lane change of intelligent vehicle.