基于InEKF和深度学习的车辆定位研究  

Research on vehicle localization based on InEKF and deep learning

作　　者：郭戈 林皓栋 刘佳庚 李增勃 GUO Ge;LIN Hao-dong;LIU Jia-geng;LI Zeng-bo(State Key Laboratory of Synthetical Automation for Process Industries,Northeastern University,Shenyang 110819,China;College of Information Science and Engineering,Northeastern University,Shenyang 110819,China;School of Control Engineering,Northeastern University at Qinhuangdao,Qinhuangdao 066004,China)

机构地区：[1]东北大学流程工业综合自动化国家重点实验室,沈阳110819 [2]东北大学信息科学与工程学院,沈阳110819 [3]东北大学秦皇岛分校控制工程学院,河北秦皇岛066004

出　　处：《控制与决策》2024年第12期4037-4044,共8页Control and Decision

基　　金：国家自然科学基金项目(62173079,U1808205);2024年河北省硕士在读研究生创新能力培养项目(CXZZSS2024180)。

摘　　要：研究一种利用不变拓展卡尔曼滤波器(invariant extended Kalman filter,InEKF)和深度学习的车辆定位方案.首先,通过引入轮速计测量模型,构建基于自编码器的深度神经网络,并重构车辆速度真值;然后,基于InEKF推导以SE(3)为状态量的滤波算法,使用该算法融合多源信息以估计车辆位置.实验结果表明,与现有先进方法相比,所提出车辆定位系统可在城市环境下显著提高定位精度.A vehicle positioning scheme using the invariant extended Kalman filter(InEKF)and deep learning is studied.Firstly,by introducing the wheel speedometer measurement model,a deep neural network based on autoencoder is constructed,and the true value of vehicle speed is reconstructed.Then,based on the InEKF,a filtering algorithm with SE(3)as the state quantity is derived,and the algorithm is used to fuse multi-source information to estimate the vehicle position.Experimental results show that compared with the existing advanced methods,the proposed vehicle positioning system can significantly improve the positioning accuracy in urban environment.

关 键 词：车辆定位 多源融合 深度学习 轮速计模型 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]