智慧型運輸系統（ITS）將多種領域的先進科技應用於各種交通系統中，不但能減少事故發生率、交通堵塞、碳排放和空氣汙染，並能提高安全性、可靠度和能源使用效率。為了充分將智慧型運輸系統應用於鐵路運輸，確定列車的即時精準位置至關重要。根據交通部臺灣鐵路管理局鐵路建設作業程序，原有軌道之中心距離（軌道間距）應在 3.7 公尺以上。為了分辨相鄰的兩條軌道，垂直鐵軌方向之平面定位精度應小於軌道間距的一半，亦即是1.85 公尺。全球導航衛星系統（GNSS）是戶外定位需求首先想到的解決方案，然而在陸地上車輛應用環境中，衛星訊號時常受到遮蔽和反射並且進一步降低衛星定位解的精度。因此，必須開發能應用於衛星訊號惡劣環境的解決方案。另一方面，臺灣鐵路管理局現有之車輛偵測感測器（軌道電路和計軸器）只能偵測特定軌道區間內是否有列車佔據，無法滿足精度需求。故本研究提出應用於列車定位系統之多感測器整合系統，並採用擴展卡爾曼濾波器（EKF）和鬆耦合架構（LC）。此演算法整合衛星定位、慣性導航、輪速計、無線射頻辨識（RFID）和圖資輔助方案，以提供無縫式導航應用於多樣場域，包含長隧道、地下化路段等鐵路系統常見場域。本研究的實驗採用具備車道維持輔助（LKA）系統之車輛做為鐵路使用情境之模擬，搭載戰術等級慣性感測元件（IMU）做為測試系統，並選定三處長隧道測試場域以驗證開發演算法。結果顯示圖資輔助方案於三個實驗場域分別減少了21.08 %、34.63 %與21.40 %垂直鐵軌方向的均方根（RMS）誤差，此外本研究提出之多感測器整合系統於垂直鐵軌方向均方根誤差亦小於1.85 公尺，有助於未來智慧型鐵路運輸系統（IRTS）的發展。

The Intelligent Transportation System (ITS) is an advanced application that applies different genre of technologies into all kinds of transportation system. The ITS has the advantages of reducing the accident rate, traffic congestion, carbon emission, air pollution and increasing the safety, reliability, and energy efficiency. It is essential to know the precise position information of the trains for making good use of ITS in the railway. According to the railway construction procedure of Taiwan Railways Administration (TRA), the distance between the centerline of two parallel rail tracks, also called as the track spacing, should not be less than 3.7 meters, and the track spacing of new-build rail tracks should not be less than 4.5 meters. For recognizing the correct driving track, the error should be half of the minimum track spacing, which is 1.85 meters at least. When talking about outdoor positioning, the Global Navigation Satellite System (GNSS) is usually the priority option. However, in the application scenarios of land vehicles, GNSS signals would have difficulty to be tracked continuously because of interference and obstruction. The solutions in GNSS signals hostile environments must be developed. Since the existing train detection system of TRA could not meet the high accuracy requirement, a multi-sensor fusion scheme for train positioning application that applies the Extended Kalman Filter (EKF) in Loosely Coupled (LC) architecture is proposed. This algorithm aims to provide GNSS/INS/Odometer/RFID/map aiding integrated solutions seamlessly, even in long tunnels. In this research, a simulation of rail vehicle operating test is conducted by a land vehicle that applies the Lane Keeping Assist (LKA) system and equipped with a tactical-grade Inertial Measurement Unit (IMU). Three experiments that include long tunnel scenarios are carried out for the performance validation. The result indicates that the map aiding scheme gives the improvement of 21.08 %, 34.63 %, and 21.40 % in the Root Mean Square (RMS) errors of three testing fields. Additionally, the proposed multi-sensor fusion scheme can achieve 1.85 meters in the cross-track direction in terms of RMS error and is beneficial to the future Intelligent Railway Transportation System (IRTS) development.

[1] Adem, G. H., "Static calibration of tactical grade inertial measurements units." Report No. 496, Geodetic Science, 2010.
[2] Aggarwal, P., "MEMS-based integrated navigation." Artech House, 2010.
[3] Aggarwal, P., Bhatt, D., Devabhaktuni, V., & Bhattacharya, P., "Dempster Shafer neural network algorithm for land vehicle navigation application." Information Sciences 253, 26-33, 2013.
[4] Aggarwal, P., Syed, Z., Noureldin, A., & El-Sheimy, N., "MEMS-based integrated navigation." Artech House, 2010.
[5] Albrecht, T., Lüddecke, K., & Zimmermann, J., "A precise and reliable train positioning system and its use for automation of train operation." 2013 IEEE International Conference on Intelligent Rail Transportation Proceedings, pp. 134-139, 2013.
[6] Almagbile, A., Wang, J., & Ding, W., "Evaluating the performances of adaptive Kalman filter methods in GPS/INS integration." Journal of Global Positioning Systems 9, 33-40, 2010.
[7] An, S. H., Lee, B. H. & Shin, D. R., "A Survey of Intelligent Transportation Systems," 2011 Third International Conference on Computational Intelligence, Communication Systems and Networks, pp. 332-337, 2011.
[8] Antoni, M., "Complementarity between Axle Counters and Tracks Circuits." In: Schnieder E., Tarnai G. (eds) FORMS/FORMAT Springer, 2010.
[9] Artese, G., & Trecroci, A., "Calibration of a low-cost MEMS INS sensor for an integrated navigation system." Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci, 877-882, 2008.
[10] Bethel, J. S., Lee, C., & Landgrebe, D. A., "Geometric Registration of Hyperspectral Airborne Pushbroom Data." Proceedings of the ISPRS XIX, 16-23, 2000.
[11] Brown, R.G., & Hwang, P.Y., "Introduction to random signals and applied Kalman filtering." Vol. 3. New York: Wiley, 1992.
[12] Chang, H. W., "Enhanced Portable Navigation for Cycling Applications." University of Calgary, 2014.
[13] Chiang, K. W., Li, Y. H., Hsu, L. T., & Chu, F. Y. "The Design a TDCP-Smoothed GNSS/Odometer Integration Scheme with Vehicular-Motion Constraint and Robust Regression." Remote Sensing, 12(16), 2550, 2020.
[14] Chiang, K. W., Tsai, G. J., Li, Y. H., Li, Y., & El-Sheimy, N. "Navigation Engine Design for Automated Driving Using INS/GNSS/3D LiDAR-SLAM and Integrity Assessment." Remote Sensing, 12(10), 1564, 2020.
[15] Chon, H. D., Jun, S., Jung, H., & An, S. W., "Using RFID for Accurate Positioning." Journal of Global Positioning Systems, Vol. 3, No. 1-2: 32-39, 2004.
[16] Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O., "MonoSLAM: Real-time single camera SLAM." IEEE transactions on pattern analysis and machine intelligence, 29(6), 1052-1067, 2007.
[17] de Bruin, T., Verbert, K., & Babuška, R., "Railway Track Circuit Fault Diagnosis Using Recurrent Neural Networks," in IEEE Transactions on Neural Networks and Learning Systems, pp. 523-533, 2017.
[18] Dissanayake, M. G., Newman, P., Clark, S., Durrant-Whyte, H. F., & Csorba, M., "A solution to the simultaneous localization and map building (SLAM) problem." IEEE Transactions on robotics and automation, 17(3), 229-241, 2001.
[19] El-Sheimy, N., Abdel-Hamid, W., & Lachapelle, G., "An adaptive neuro-fuzzy model for bridging GPS outages in MEMS-IMU/GPS land vehicle navigation," Proceedings of the 17th International Technical Meeting of the Satellite Division of The Institute of Navigation, pp. 1088-1095, 2001.
[20] El-Sheimy, N., Hou, H., & Niu, X., "Analysis and modeling of inertial sensors using Allan variance." IEEE Transactions on instrumentation measurement 57, 140-149, 2008.
[21] Farooq, J., & Soler, J., "Radio Communication for Communications-Based Train Control (CBTC): A Tutorial and Survey," in IEEE Communications Surveys & Tutorials, vol. 19, no. 3, pp. 1377-1402, 2017.
[22] Farrell, J., & Barth, M., "The global positioning system and inertial navigation." Vol. 61. New York, NY, USA:: Mcgraw-hill, 1999.
[23] Gao, J., Petovello, M., & Cannon, M.E., "Integration of steering angle sensor with global positioning system and micro-electro-mechanical systems inertial measurement unit for vehicular positioning." Journal of Intelligent Transportation Systems 12, 159-167, 2008.
[24] Gebre-Egziabher, D., & Gleason, S., "GNSS applications and methods." Artech House. 2009.
[25] Gelb, A., "Applied optimal estimation." MIT press, 1974.
[26] Ghazel, M., "Formalizing a subset of ERTMS/ETCS specifications for verification purposes," Transportation Research Part C: Emerging Technologies, Volume 42, p 60-75, 2014.
[27] Godha, S., "Performance evaluation of low-cost MEMS-based IMU integrated with GPS for land vehicle navigation application," UCGE report 20239, 2006.
[28] Groves, P. D., "Principles of GNSS, inertial, and multisensor integrated navigation systems." Artech house, 2013.
[29] Hartong, M., Goel, R., & Wijesekera, D., "Communications Based Positive Train Control Systems Architecture in the USA." Vehicular Technology Conference, 2006.
[30] Hashemi, M., & Karimi, H. A., "A critical review of real-time map-matching algorithms: Current issues and future directions." Computers, Environment and Urban Systems, Volume 48, 153-165, 2014.
[31] Hashemi, M., & Karimi, H. A., "A weight-based map-matching algorithm for vehicle navigation in complex urban networks." Journal of Intelligent Transportation Systems, 20(6), 573-590, 2016.
[32] Hou, H., "Modeling inertial sensors errors using Allan variance." University of Calgary, Department of Geomatics Engineering, 2004.
[33] Hsu, L. T., "Analysis and modeling GPS NLOS effect in highly urbanized area." GPS solutions, 22(1), 7, 2018.
[34] Hsu, L. T., Tokura, H., Kubo, N., Gu, Y., & Kamijo, S., "Multiple faulty GNSS measurement exclusion based on consistency check in urban canyons." IEEE Sensors Journal, 17(6), 1909-1917, 2017.
[35] Hsu, P. C., "An Automotive-grade INS/HD Maps/Odometer/GNSS Integration Scheme for Lane-level Navigation Application in Urban Area." National Cheng Kung University, 2019.
[36] Hu, G., Gao, S., & Zhong, Y., "A derivative UKF for tightly coupled INS/GPS integrated navigation." ISA transactions 56, 135-144, 2015.
[37] Jiang, Z., "Digital route model aided integrated satellite navigation and low-cost inertial sensors for high-performance positioning on the railways," University College London, 2011.
[38] Julier, S. J., & Durrant-Whyte, H. F., "On the role of process models in autonomous land vehicle navigation systems." IEEE transactions on robotics automation 19, 1-14, 2003.
[39] Kaplan, E., & Hegarty, C., "Understanding GPS: principles and applications," Artech house, 2005.
[40] Lahrech, A., Boucher, C., & Noyer, J. C. "Fusion of GPS and odometer measurements for map-based vehicle navigation." In 2004 IEEE International Conference on Industrial Technology, (Vol. 2, pp. 944-948). IEEE, 2004.
[41] Leick, A., Rapoport, L., & Tatarnikov, D., "GPS satellite surveying." John Wiley & Sons, 2015.
[42] Li, P., Jia, L. M., & Nie, A. X., "Study on railway intelligent transportation system architecture," Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems, pp. 1478-1481, 2003.
[43] Li, Y. H., "Lane-Level Accuracy Navigation Design Based on INS/GNSS/Odometer Semi-Tightly Coupled Integration Scheme with HD Vector Map," National Cheng Kung University, 2020.
[44] Li, Z., Wang, J., Li, B., Gao, J., & Tan, X., "GPS/INS/Odometer integrated system using fuzzy neural network for land vehicle navigation applications." 67, 967-983, 2014.
[45] Liao, J. K., Zhou, Z. M., Tsai, G. J., Duong, T. T., & Chiang, K. W., "The applicability analysis of using smart phones for indoor mobile mapping applications," Proc. of ION GNSS, pp. 510-531, 2014.
[46] Mohamed, A. H., "Optimizing the estimation procedure in INS/GPS integration for kinematic applications." Calgary, 1999.
[47] Nassar, S., "Improving the inertial navigation system (INS) error model for INS and INS/DGPS applications," Department of Geomatics Engineering. University of Calgary, 2003.
[48] Ning, B., Tang, T., Gao, Z., Yan, F., Wang, F. Y., & Zeng, D., "Intelligent Railway Systems in China," in IEEE Intelligent Systems, pp. 80-83, 2006.
[49] Ochieng, W. Y., Quddus, M. A., & Noland, R. B., "Map-matching in complex urban road networks," Centre for Transport Studies Department of Civil and Environmental Engineering, Imperial College London, 2003.
[50] Papoulias, F. A., "Modern Control Systems." Informal Lecture Notes for ME4811. 2001.
[51] Peng, K. Y., Lin, C. A., & Chiang, K. W., "Performance Analysis of An AKF Based Tightly Coupled INS/GNSS Integrated Scheme with NHC For Land Vehicular Applications." Transactions of the Canadian Society for Mechanical Engineering 37, 503-513, 2013.
[52] Quddus, M. A., Ochieng, W. Y., & Noland, R. B., "Current map-matching algorithms for transport applications: State-of-the art and future research directions," Transportation research part c: Emerging technologies, 15(5), 312-328, 2007.
[53] Qureshi, K. N., & Abdullah, A. H., "A Survey on Intelligent Transportation Systems." Middle-East Journal of Scientific Research, 15(5), 629-642, 2013.
[54] Rhudy, M., Gu, Y., Gross, J., & Napolitano, M. R., "Evaluation of matrix square root operations for UKF within a UAV GPS/INS sensor fusion application." International Journal of Navigation Observation, 2012.
[55] Sato, K., Tateshita, H., & Wakabayashi, Y., "Asia Oceania Multi-GNSS Demonstration Campaign." In XXV FIG Congress. Kuala Lumpur, Malaysia, 2014.
[56] Savage, P. G., "Strapdown analytics," Vol. 2, pp. 15-1, Maple Plain, MN: Strapdown Associates, 2000.
[57] Scherzinger, B. M., "Inertial navigator error models for large heading uncertainty. " In Proceedings of Position, Location and Navigation Symposium-PLANS'96, pp. 477-484, 1996.
[58] Schuster, F., Keller, C. G., Rapp, M., Haueis, M., & Curio, C., "Landmark based radar SLAM using graph optimization." In 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC) (pp. 2559-2564). IEEE, 2016.
[59] Shin, E. H., "Estimation techniques for low-cost inertial navigation." UCGE report, 20219, 2005.
[60] Shin, E.-H., "Accuracy improvement of low-cost INS/GPS for land applications." University of Calgary, 2001.
[61] Shin, E.-H., & El-Sheimy, N., "An unscented Kalman filter for in-motion alignment of low-cost IMUs," Position Location and Navigation Symposium, IEEE, pp. 273-279, 2004.
[62] Sukkarieh, S., "Low cost, high integrity, aided inertial navigation systems for autonomous land vehicles." University of Sydney, 2000.
[63] Teunissen, P., Montenbruck, O., "Springer handbook of global navigation satellite systems." Springer, 2017.
[64] Titterton, D., & Weston, J.L., "Strapdown inertial navigation technology. " Vol. 17. IET, 2004.
[65] Torge, W., & Müller, J., "Geodesy." Walter de Gruyter, 2012.
[66] Tsai, G. J., "Seamless Navigation and Mapping Using INS/GNSS/LiDAR SLAM Multi-Fusion Schemes." National Cheng Kung University, 2020.
[67] Yang, Y., "Tightly coupled MEMS INS/GPS integration with INS aided receiver tracking loops." Department of Geomatics Engineering, 2008.
[68] Yen, S. W., van Graas, F., & de Haag, M. U., "Positioning with two satellites and known receiver clock, barometric pressure and radar elevation." GPS solutions 20, 885-899, 2016.
[69] Zafar, N. A., Khan, S. A., & Araki, K., "Towards the safety properties of moving block railway interlocking system," International Journal of Innovative Computing, Information and Control, pp. 5677-5690, 2012.
[70] Zimmermann, A., & Hommel, G., "A train control system case study in model-based real time system design," Proceedings International Parallel and Distributed Processing Symposium, 2003.