基于人车协同识别的行程轨迹预测  

Travel Trajectory Prediction Based on Human Vehicle Cooperative Recognition

作　　者：郭唐仪 李林蔚[2] 王梓 杨雨薇 彭勃硕 GUO Tangyi;LI Linwei;WANG Zi;YANG Yuwei;PENG Boshuo(Nanjing Research Institute of Static Transportation Technology Industry,Nanjing 210012,China;School of Automation,Nanjing University of Science&Technology,Nanjing 210094,China)

机构地区：[1]南京静态交通技术产业研究院,南京210012 [2]南京理工大学自动化学院,南京210094

出　　处：《现代交通技术》2023年第6期18-23,37,共7页Modern Transportation Technology

基　　金：江苏省交通运输科技与成果转化重大专项(2019Z01)。

摘　　要：为了解决借车出行和行驶路线违规等问题,首先运用人员识别设备和机动车电子标识构建的人车协同识别系统,将驾驶员和车辆相关联;其次根据检测设备在地图上的位置,利用高斯混合模型对人员行程轨迹进行初步预测,辅以航迹推算校正预测轨迹,进一步确定车辆的行程轨迹,实现准确的轨迹预测。In order to solve problems such as borrowing a car to travel and driving route violations,first uses a personvehicle collaborative identification system constructed by person identification equipment and electronic identification of motor vehicles to associate the driver with the vehicle;then,based on the position of the detection equipment on the map,a Gaussian mixture model is used to initially predict the person’s travel trajectory,supplemented by flight estimation to correct the predicted trajectory,further determine the vehicle’s travel trajectory,and implement an accurate trajectory prediction.

关 键 词：人车协同识别 轨迹预测 高斯混合模型 航迹推算 

分 类 号：U491.14[交通运输工程—交通运输规划与管理]