随着无人驾驶相关技术产业的快速推进，智能车已经成为当前学术界和工业界的研究热点，作为智能车发展基础和核心的高精度定位技术得到了长足发展。目前应用最广泛的智能车定位方式是全球导航卫星系统、惯性导航系统等，此外基于视觉和激光的定位技术也取得了长足进步，结合高精地图，提高了智能车定位精度。同时在智能交通系统进一步发展的背景下，利用车对车信息交互（Vehicle-to-Vehicle, V2V）的多智能车协同定位技术步入了研究人员的视野。协同定位技术可充分利用定位场景中的多源信息，实现了信息互补，极大提高了传感器数据的有效利用率，提高了整个定位系统的定位精度和鲁棒性。根据相关研究背景，本文面向智能车的定位问题，开展了基于高精地图的多智能车协同定位方法研究。本文主要研究工作如下：

1）研究基于孪生网络的特征层高精地图构建与表征方法。该方法将三维激光点云表征为二维点云极化图形式，同时构建了孪生网络对点云极化图之间的相似性进行建模，将其转换为基于孪生网络场景编码的相似概率计算，提高了地图匹配的效率和准确率。并且以其主干网络提取的场景编码为基础，结合点云极化图以及全局位姿，构建了激光极化地图，即特征层高精地图，为智能车定位提供先验信息参考。

2）研究基于直方图滤波的智能车自定位方法。该方法利用特征层高精地图实现智能车自定位。在节点级定位中，通过直方图滤波计算最优匹配地图节点，将状态定义为多个待匹配的地图节点，其中状态转移通过匀速运动模型获得，观测概率通过待定位节点与地图节点的孪生网络场景编码特征以及SURF（Speeded-Up Robust Features）点特征获得，有效提高了地图节点匹配的准确率。在度量级定位中，利用GICP（Generalized Iterative Closet Point）算法配准三维点云，实现智能车全局位置计算。

3）研究基于时空图模型的多智能车协同定位方法。该方法将协同定位环境下车辆位置的最优状态估计问题转化为时空图模型构建与优化问题。时空图模型的节点即各个时刻每辆车的位置，边的类型即约束的种类，包括自定位观测、车-车位置观测、车道层高精地图观测和帧间位置观测。并针对协同定位中的通讯和数据处理时延问题，利用时延补偿加以优化。在求解过程中，利用滑窗限制时空图模型规模，引入Huber核函数减少由异常值导致的错误边对整体优化效果的影响。并采用LM（Levenberg-Marquardt）法求解目标函数实现对感知区域中的车辆位置最优状态估计，实现多智能车协同定位。

[1] 李克强, 戴一凡, 李升波, 等.智能网联汽车(ICV)技术的发展现状及趋势[J]. 汽车安全与节能学报, 2017, 8(01): 1-14.

[2] 刘思源. 车联网自适应协同定位技术的研究[D]. 上海交通大学, 2019.

[3] 孙宁. 基于多源信息融合的智能汽车环境感知技术研究[D]. 镇江: 江苏大学, 2018.

[4] Tariq Z B, Cheema D M, Kamran M Z, et al. Non-GPS Positioning Systems: A Survey[J]. ACM Computing Surveys, 2017, 50(04): 1-34.

[5] Yang Z, Li Z, Liu Z, et al. Improved Robust and Adaptive Filter Based on Non-holonomic Constraints for RTK/INS Integrated Navigation[J]. Measurement Science and Technology, 2021, 32(10): 105110-105122.

[6] Zhou Z, Hu Z Z, Li N, et al. Road-pulse: Pavement Vibration Features from Accelerator to Enhance Intelligent Vehicle Localization[C]//2021 IEEE Intelligent Vehicles Symposium(IV). IEEE, 2021: 940-946.

[7] Wang C, Huang H, Ji Y, et al. Vehicle Localization at An Intersection Using A Traffic Light Map[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 20(04): 1432-1441.

[8] Kuutti S, Fallah S, Katsaros K, et al. A Survey of The State-of-the-art Localization Techniques and Their Potentials for Autonomous Vehicle Applications[J]. IEEE Internet of Things Journal, 2018, 5(02): 829-846.

[9] Shan T, Englot B, Meyers D, et al. LIO-SAM: Tightly-coupled LiDAR Inertial Odometry via Smoothing and Mapping[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). IEEE, 2020: 5135-5142.

[10] Kim C, Jo K, Cho S, et al. Optimal Smoothing Based Mapping Process of Road Surface Marking in Urban Canyon Environment[C]//2017 14th Workshop on Positioning, Navigation and Communications(WPNC). IEEE, 2017: 1-6.

[11] 陈龙, 刘坤华, 周宝定, 等. 多智能体协同高精地图构建关键技术研究[J]. 测绘学报, 2021, 50(11): 1447-1456.

[12] Schwarzbach P, Michler A, Tauscher P, et al. An Empirical Study on V2X Enhanced Low-cost GNSS Cooperative Positioning in Urban Environments[J]. Sensors, 2019, 19(23): 5201-5226.

[13] 焦朋朋, 杨紫煜, 洪玮琪, 等. 车路协同下车队避让紧急车辆的换道引导方法[J]. 中国公路学报, 2021, 34(07): 95-104.

[14] 缪立新, 王发平. V2X车联网关键技术研究及应用综述[J]. 汽车工程学报, 2020, 10(01): 1-12.

[15] Xu L, Zhuang W, Yin G, et al. Geometry-based Cooperative Localization for Connected Vehicle Subject to Temporary Loss of GNSS Signals[J]. IEEE Sensors Journal, 2021, 21(20): 23527-23536.

[16] Chu X, Lu Z, Gesbert D, et al. Vehicle Localization via Cooperative Channel Mapping[J]. IEEE Transactions on Vehicular Technology, 2021, 70(06): 5719-5733.

[17] 王栋民, 赵冬青, 向民志, 等. 车载分散式协同定位算法性能分析[J]. 测绘科学技术学报, 2021, 38(02): 130-135.

[18] 张宝成, 柯成, 查九平, 等. 非差非组合PPP-RTK: 模型算法、终端样机与实测结果[J]. 测绘学报, 2022, 51(08): 1725-1735.

[19] Li X, Ge M, Dai X, et al. Accuracy and Reliability of Multi-GNSS Real-time Precise Positioning: GPS, GLONASS, BeiDou, and Galileo[J]. Journal of Geodesy, 2015, 89(06): 607-635.

[20] 王一军, 杨杰, 余明杨. 北斗导航系统移动基准站差分定位算法[J]. 国防科技大学学报, 2017, 39(05): 45-49.

[21] Gao W, Pan S, Gao C, et al. Tightly Combined GPS and GLONASS for RTK Positioning with Consideration of Differential Inter-system Phase Bias[J]. Measurement Science and Technology, 2019, 30(05): 1-8.

[22] He H, Li J, Yang Y, et al. Performance Assessment of Single-and Dual-frequency BeiDou/GPS Single-epoch Kinematic Positioning[J]. GPS Solutions, 2014, 18(03): 393-403.

[23] Bai S, Lai J, Lyu P, et al. Improved Preintegration Method for GNSS/IMU/In-vehicle Sensors Navigation Using Graph Optimization[J]. IEEE Transactions on Vehicular Technology, 2021, 70(11): 11446-11457.

[24] 董毅, 王鼎杰, 吴杰. 载波相位时间差分辅助的SINS/GNSS紧组合导航方法[J]. 中国惯性技术学报, 2021, 29(04).

[25] Stoll H, Zimmer P, Hartmann F, et al. GPS-independent Localization for Off-road Vehicles Using Ultra-wideband(UWB)[C]//2017 IEEE 20th International Conference on Intelligent Transportation Systems(ITSC). IEEE, 2017: 1-6.

[26] 王睿, 赵方, 彭金华, 等. 基于WiFi和蓝牙融合的室内定位算法[J]. 计算机研究与发展, 2011(02): 28-33.

[27] Guo X, Elikplim N R, Ansari N, et al. Robust WiFi Localization by Fusing Derivative Fingerprints of RSS and Multiple Classifiers[J]. IEEE Transactions on Industrial Informatics, 2019, 16(05): 3177-3186.

[28] Soltanaghaei E, Kalyanaraman A, Whitehouse K. Multipath Triangulation: Decimeter-Level WiFi Localization and Orientation with A Single Unaided Receiver[C]//The 16th Annual International Conference on Mobile Systems, Applications, and Services(MobiSys). Association for Computing Machinery, 2018: 376-388.

[29] Poulose A, Emeršič Ž, Eyobu O S, et al. An Accurate Indoor User Position Estimator for Multiple Anchor UWB Localization[C]//2020 International Conference on Information and Communication Technology Convergence(ICTC). IEEE, 2020: 478-482.

[30] Kimoto R, Ishida S, Yamamoto T, et al. MuCHLoc: Indoor Zigbee Localization System Utilizing Inter-Channel Characteristics[J]. Sensors, 2019, 19(07): 1645-1661.

[31] Monica S, Bergenti F. Hybrid Indoor Localization Using WiFi and UWB Technologies[J]. Electronics, 2019, 8(03): 334-347.

[32] Klein G, Murray D. Parallel Tracking and Mapping for Small AR Workspaces[C]//2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality(ISMAR). IEEE, 2007: 225-234.

[33] Engel J, Schöps T, Cremers D. LSD-SLAM: Large-scale Direct Monocular SLAM[C]//2014 13th European Conference on Computer Vision(ECCV). Springer, 2014: 834-849.

[34] 蔡英凤, 陆子恒, 李祎承, 等. 基于多传感器融合的紧耦合SLAM系统[J]. 汽车工程, 2022, 44(03): 350-361.

[35] Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM: A Versatile and Accurate Monocular SLAM System[J]. IEEE Transactions on Robotics. 2015, 31(05): 1147-1163.

[36] Shen S, Mulgaonkar Y, Michael N, et al. Initialization-free Monocular Visual-inertial State Estimation with Application to Autonomous MAVs[C]//The 14th International Symposium on Experimental Robotics(ISER). Springer, 2016: 211-227.

[37] Qin T, Li P, Shen S. VINS-MONO: A Robust and Versatile Monocular Visual-inertial State Estimator[J]. IEEE Transactions on Robotics, 2018, 34(04): 1004-1020.

[38] Besl P J, Mckay N D. Method for Registration of 3-D Shapes[C]//Sensor Fusion IV: Control Paradigms and Data Structures. Spie, 1992, 1611: 586-606.

[39] Chen Y, Medioni G. Object Modelling by Registration of Multiple Range Images[J]. Image and Vision Computing, 1992, 10(03): 145-155.

[40] Segal A, Haehnel D, Thrun S. Generalized-ICP[C]//Robotics: Science and Systems(RSS). Robotics: Science and Systems Foundation, 2009, 2(04): 435-442.

[41] Magnusson M, Lilienthal A, Duckett T. Scan Registration for Autonomous Mining Vehicles Using 3D-NDT[J]. Journal of Field Robotics, 2007, 24(10): 803-827.

[42] Biber P, Straßer W. The Normal Distributions Transform: A New Approach to Laser Scan Matching[C]//2003 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). IEEE, 2003, 3: 2743-2748.

[43] Zhang J, Singh S. Low-drift and Real-time LiDAR Odometry and Mapping[J]. Autonomous Robots, 2017, 41(02): 401-416.

[44] Zhang J, Singh S. LOAM: LiDAR Odometry and Mapping in Real-time[C]// Robotics: Science and Systems(RSS). Robotics: Science and Systems Foundation, 2014, 2(09): 1-9.

[45] Shan T, Englot B. LeGo-LOAM: Lightweight and Ground-optimized LiDAR Odometry and Mapping on Variable Terrain[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). IEEE, 2018: 4758-4765.

[46] Ma W C, Tartavull I, Bârsan I A, et al. Exploiting Sparse Semantic HD Maps for Self-driving Vehicle Localization[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). IEEE, 2019: 5304-5311.

[47] Wang H, Xue C, Zhou Y, et al. Visual Semantic Localization Based on HD Map for Autonomous Vehicles in Urban Scenarios[C]//2021 IEEE International Conference on Robotics and Automation(ICRA). IEEE, 2021: 11255-11261.

[48] 李祎承, 胡钊政, 胡月志, 等. 基于GPS与图像融合的智能车辆高精度定位算法[J]. 交通运输系统工程与信息, 2017, 17(03): 112-119.

[49] Yang G Y G, Becker J, Stewart C V. Estimating The Location of A Camera with Respect to A 3D Model[C]//The 6th International Conference on 3-D Digital Imaging and Modeling(3DIM). IEEE, 2007: 159-166.

[50] Lowe D G. Distinctive Image Features from Scale-invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(02): 91-110.

[51] Garcia-Fidalgo E, Ortiz A. Probabilistic Appearance-based Mapping and Localization Using Visual Features[C]//Iberian Conference on Pattern Recognition and Image Analysis(IbPRIA). Springer, 2013: 277-285.

[52] Bay H, Ess A, Tuytelaars T, et al. Speeded-up Robust Features(SURF)[J]. Computer Vision and Image Understanding, 2008, 110(03): 346-359.

[53] Wang J, Zha H, Cipolla R. Coarse-to-fine Vision-based Localization by Indexing Scale-Invariant Features[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B(Cybernetics), 2006, 36(02): 413-422.

[54] 崔文靓, 王玉静, 康守强, 等. 基于改进YOLOv3算法的公路车道线检测方法[J]. 自动化学报, 2022, 45: 1-9.

[55] Strudel R, Garcia R, Laptev I, et al. Segmenter: Transformer for Semantic Segmentation[C]//The IEEE/CVF International Conference on Computer Vision(ICCV). IEEE, 2021: 7262-7272.

[56] Xiao Z, Yang D, Wen T, et al. Monocular Localization with Vector HD Map(MLVHM): A Low-cost Method for Commercial Ivs[J]. Sensors, 2020, 20(07): 1870-1893.

[57] Wen T, Jiang K, Wijaya B, et al. TM³Loc: Tightly-coupled Monocular Map Matching for High Precision Vehicle Localization[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 20268-20281.

[58] Koide K, Miura J, Menegatti E. A Portable Three-dimensional LiDAR-based System for Long-term and Wide-area People Behavior Measurement[J]. International Journal of Advanced Robotic Systems, 2019, 16(02): 1-16.

[59] Yoneda K, Tehrani H, Ogawa T, et al. LiDAR Scan Feature for Localization with Highly Precise 3-D Map[C]//2014 IEEE Intelligent Vehicles Symposium(IV). IEEE, 2014: 1345-1350.

[60] Elfes A. Using Occupancy Grids for Mobile Robot Perception and Navigation[J]. Computer, 1989, 22(06): 46-57.

[61] Weiss T, Kaempchen N, Dietmayer K. Precise Ego-localization in Urban Areas Using Laserscanner and High Accuracy Feature Maps[C]//2005 IEEE Intelligent Vehicles Symposium(IV). IEEE, 2005: 284-289.

[62] Wolcott R W, Eustice R M. Fast LiDAR Localization Using Multiresolution Gaussian Mixture Maps[C]//2015 IEEE International Conference on Robotics and Automation(ICRA). IEEE, 2015: 2814-2821.

[63] Wiest J, Deusch H, Nuss D, et al. Localization Based on Region Descriptors in Grid Maps[C]//2014 IEEE Intelligent Vehicles Symposium(IV). IEEE, 2014: 793-799.

[64] Zhang C, Liu L, Xue Z, et al. Robust LiDAR Localization on An HD Vector Map without A Separate Localization Layer[C]//2021 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). IEEE, 2021: 5536-5543.

[65] Ghallabi F, El-Haj-Shhade G, Mittet M A, et al. LiDAR-based Road Signs Detection for Vehicle Localization in An HD Map[C]//2019 IEEE Intelligent Vehicles Symposium(IV). IEEE, 2019: 1484-1490.

[66] Yin H, Wang Y, Ding X, et al. 3D LiDAR-based Global Localization Using Siamese Neural Network[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(04): 1380-1392.

[67] Chen X, Läbe T, Milioto A, et al. OverlapNet: A Siamese Network for Computing LiDAR Scan Similarity with Applications to Loop Closing and Localization[J]. Autonomous Robots, 2022, 46(01): 61-81.

[68] Kim G, Kim A. Scan Context: Egocentric Spatial Descriptor for Place Recognition within 3D Point Cloud Map[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). IEEE, 2018: 4802-4809.

[69] Tao Q, Hu Z, Zhou Z, et al. SeqPolar: Sequence Matching of Polarized LiDAR Map with HMM for Intelligent Vehicle Localization[J]. IEEE Transactions on Vehicular Technology, 2022, 71(7): 7071-7083.

[70] 孙宁, 闫梦如, 倪捷, 等. 基于GRI的多车协同定位研究[J]. 汽车工程, 2018, 40(04): 488-493.

[71] 段续庭, 田大新, 王云鹏. 基于V2X通信网络的车辆协同定位增强方法[J]. 汽车工程, 2018, 40(08): 947-951.

[72] Ammous M, Valaee S. Cooperative Positioning in Vehicular Networks Using Angle of Arrival Estimation Through mmWave[C]//2020 IEEE Global Communications Conference(GLOBECOM). IEEE, 2020: 1-6.

[73] Ma Z, Sun S. Research on Vehicle-road Co-location Method Oriented to Network Slicing Service and Traffic Video[J]. Sustainability, 2021, 13(10): 5334-5348.

[74] 王玖玲, 吴韶波, 张媛利, 等. 利用V2X增强GPS的协同车辆定位方法[J]. 系统仿真学报, 2019, 31(12): 2901-2906.

[75] Gulati D, Zhang F, Clarke D, et al. Graph-based Cooperative Localization Using Symmetric Measurement Equations[J]. Sensors, 2017, 17(06): 1422-1437.

[76] 罗文慧, 董宝田, 王泽胜. 基于车路协同的车辆定位算法研究[J]. 西南交通大学学报, 2018, 53(05): 1072-1077.

[77] Zhang G, Ng H F, Wen W, et al. 3D Mapping Database Aided GNSS Based Collaborative Positioning Using Factor Graph Optimization[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(10): 6175-6187.

[78] Koch G, Zemel R, Salakhutdinov R. Siamese Neural Networks for One-shot Image Recognition[C]//ICML Deep Learning Workshop. 2015, 2(1).

[79] Ye Y, Fu L, Li B. Object Detection and Tracking Using Multi-layer Laser for Autonomous Urban Driving[C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems(ITSC). IEEE, 2016: 259-264.