隨著科技不斷進步與電動車逐漸在市場中成為主流，自駕車技術的發展已成為勢不可擋的趨勢。然而，在發展初期，面對尚未完全自駕車化的交通環境，自駕車的辨識、決策與導航定位等功能就成為了首要之重。其中的導航定位又更顯重要，若沒有精確的車輛導航定位，再好的辨識與決策都將難以發揮功能。
常見應用於自駕車的定位技術包含使用 GNSS 接收機、IMU 慣性感測元件與輪速計來完成慣性導航系統(INS)。在一般天線信號良好的情況下，INS系統可達到一定程度的定位要求，但若面臨長時間的信號遮蔽，INS 系統將逐漸累積誤差，最後導致定位系統發散。為了補足這點，將有較好的三維空間感知感測器光達(LiDAR)與高精度點雲地圖結合，可補足 INS 的缺點。最後使用擴展式卡爾曼濾波器進行感測器融合，可達到更好的準確性與強健性。
然而，以上作法通常是針對相對平坦且點雲特徵明確的都市情境下實作，對於本論文所實驗之高爾夫球場來說，大量地形起伏與特徵不明確的球場點雲，在使用傳統架構作法時將不易達到自駕車層級的定位需求。因此，本論文提出使用 INS 慣性系統與光達感測器於建立點雲地圖時的定位補償架構，進而得到一個相對接近且正確的點雲圖資，最後再使用慣性導航系統、光達以及補償後之點雲圖來做感測器融合，進而得到可符合自駕車需求的定位解。

As technology continues to advance and electric vehicles gradually become mainstream in the market, the development of autonomous driving technology has become an unstoppable trend. In the early stages of development, facing a complicated traffic environment, recognition, decision-making, and navigation of autonomous vehicles have become a top priority. Among them, navigation and localization are particularly crucial because even with excellent perception and decision-making capabilities, their functionality will be limited without accurate vehicle navigation and localization.
Common positioning technologies used in autonomous driving include of GNSS receivers, IMU inertial sensing components, and vehicle wheel speed sensors. Under normal circumstances with good antenna signal, the INS (Inertial Navigation System) can achieve a certain level of positioning requirements. However, if the GNSS signal is interfered, the INS system will gradually accumulate errors, ultimately leading to the divergence of the positioning solution. To address this situation, combining LiDAR with high-precision point cloud maps, which have better three-dimensional space perception sensors, can make up for the shortcomings of INS. In addition, using Kalman filters to perform sensor fusion can achieve better accuracy and robustness.
Existing approaches are typically implemented in urban scenarios with relatively flat terrain and clear point cloud features. For the golf course experimented in this thesis, which is noted by significant terrain variations and unclear point cloud features, it is challenging to achieve the level of positioning required for autonomous driving using conventional approaches. Therefore, this thesis proposes an INS-based compensation framework for positioning for the construction of point cloud maps using LiDAR sensors. This framework aims to obtain a relatively accurate and consistent point cloud map, which is then utilized in sensor fusion with the INS system, LiDAR data, and the compensated point cloud map, to provide a positioning solution that meets the requirements of autonomous driving.

[1] Besl, P. J., & McKay, N. D. "A Method for Registration of 3-D Shapes," in Sensor Fusion IV: Control Paradigms and Data Structures, 1992.
[2] Biber, P., & Straßer, W. "The Normal Distributions Transform: A New Approach to Laser Scan Matching," in Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003)(Cat. No. 03CH37453), 2003.
[3] Calonder, M., Lepetit, V., Strecha, C., & Fua, P. "Brief: Binary Robust Independent Elementary Features," in Computer Vision–ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV 11, 2010.
[4] Campos, C., Montiel, J. M., & Tardós, J. D. "Inertial-Only Optimization for Visual-Inertial Initialization," in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020.
[5] Durrant-Whyte, H., & Bailey, T. "Simultaneous Localization and Mapping: part I". IEEE robotics & automation magazine, 13(2), 99-110. 2006.
[6] "E-Z-GO®." Textron Specialized Vehicles Inc. (2023). Retrieved June 27 from https://ezgo.txtsv.com/
[7] Elhousni, M., & Huang, X. "A Survey on 3D Lidar Localization for Autonomous Vehicles," in 2020 IEEE Intelligent Vehicles Symposium (IV), 2020.
[8] "EZGO: FREEDOM® RXV® ELiTE™." Textron Specialized Vehicles Inc. 2020.
[9] Falco, G., Pini, M., & Marucco, G. "Loose and Tight GNSS/INS Integrations: Comparison of Performance Assessed in Real Urban Scenarios". Sensors, 17(2), 255. 2017.
[10] Hun, L. C., Yeng, O. L., Sze, L. T., & Chet, K. V. "Kalman Filtering and its Real-Time Applications". Real-time Systems. 2016.
[11] Ji, K., Chen, H., Di, H., Gong, J., Xiong, G., Qi, J., & Yi, T. "CPFG-SLAM: A Robust Simultaneous Localization and Mapping Based on LIDAR in Off-Road Environment," in 2018 IEEE Intelligent Vehicles Symposium (IV), 2018.
[12] Juang, J. C. "Satellite Navigation, in Mandarin," Chuan Hwa Book Co. 2012.
[13] Julier, S. J., & Uhlmann, J. K. "Unscented Filtering and Nonlinear Estimation," In Proceedings of the IEEE, 2004.
[14] Kalman, R. E. "A New Approach to Linear Filtering and Prediction Problems". Journal of basic Engineering, 82, 35-45. 1960.
[15] "KCU GEN1 Technical Reference: Powertrain & Chassis Control Unit." KopherBit Co., Ltd. 2022.
[16] Kim, M., Zhou, M., Lee, S., & Lee, H. "Development of an Autonomous Mobile Robot in the Outdoor Environments with a Comparative Survey of LiDAR SLAM," in 2022 22nd International Conference on Control, Automation and Systems (ICCAS), 2022.
[17] "Kopher Bit." KopherBit Co., Ltd. (2023). Retrieved June 27 from https://kopherbit.com/
[18] Leonard, J. J., & Durrant-Whyte, H. F. "Simultaneous Map Building and Localization for an Autonomous Mobile Robot," in IROS, 1991.
[19] Lu, W., Wan, G., Zhou, Y., Fu, X., Yuan, P., & Song, S. "DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration," in IEEE ICCV, 2019.
[20] Macario Barros, A., Michel, M., Moline, Y., Corre, G., & Carrel, F. "A Comprehensive Survey of Visual SLAM Algorithms". Robotics, 11(1), 24. 2022.
[21] Magnusson, M. "The Three-Dimensional Normal-Distributions Transform-An Efficient Representation for Registration". Surface Analysis, and Loop Detection. 2009.
[22] Magnusson, M., Lilienthal, A., & Duckett, T. "Scan Registration for Autonomous Mining Vehicles Using 3D‐NDT". Journal of Field Robotics, 24(10), 803-827. 2007.
[23] Merzlyakov, A., & Macenski, S. "A Comparison of Modern General-Purpose Visual SLAM Approaches," in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.
[24] Mur-Artal, R., & Tardós, J. D. "ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras". IEEE transactions on robotics, 33(5), 1255-1262. 2017.
[25] Nüchter, A., Lingemann, K., Hertzberg, J., & Surmann, H. "6D SLAM—3D Mapping Outdoor Environments". Journal of Field Robotics, 24(8‐9), 699-722. 2007.
[26] "Neousys Technology." Neousys Technology America, Inc. (2023). Retrieved June 27 from https://www.neousys-tech.com/
[27] "Neousys Technology ICP : Nuvo-5095GC." Neousys Technology America, Inc. 2020.
[28] Newcombe, R. A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohi, P., Shotton, J., Hodges, S., & Fitzgibbon, A. "Kinectfusion: Real-Time Dense Surface Mapping and Tracking," in 2011 10th IEEE International Symposium on Mixed and Augmented Reality, 2011.
[29] Newton, I. "Philosophiae Naturalis Principia Mathematica," (Vol. 1) G. Brookman. 1833.
[30] "NovAtel." NovAtel. (2023). Retrieved June 27 from https://novatel.com/
[31] "Novatel GNSS-502 : High-Performance Antenna for Terrestrial Applications." NovAtel. https://novatel.com/products/gps-gnss-antennas/vexxis-series-antennas/vexxis-gnss-500-series-antennas 2023.
[32] "Novatel OEM7720 : Dual-Antenna, Multi-Frequency, GNSSreceiver Delivers Robust Heading and Positioning." NovAtel. https://novatel.com/products/receivers/gnss-gps-receiver-boards/oem7720 2023.
[33] Qi, C. R., Su, H., Mo, K., & Guibas, L. J. "Pointnet: Deep Learning on Point Sets for 3D Classification and Segmentation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
[34] "Robosense." Suteng Innovation Technology Co., Ltd. (2023). Retrieved June 27 from https://www.robosense.ai/en
[35] "Robosense: RS-LiDAR-M1 User Guide." Suteng Innovation Technology Co., Ltd. https://www.robosense.ai/en 2021.
[36] "ROS.org." ROS. (2023). Retrieved June 27 from https://www.ros.org/
[37] Rosten, E., & Drummond, T. "Machine Learning for High-Speed Corner Detection," in Computer Vision–ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part I 9, 2006.
[38] Sebastian Thrun, Wolfram Burgard, & Fox, D. "The Limitations of the Beam Model," In Probabilistic Robotics (pp. 168) The MIT Press. 2005.
[39] "Single Axis Programmable Compensation Control Driver V1.23." Extion Co., Ltd. 2022.
[40] Smith, G. "Newton’s Philosophiae Naturalis Principia Mathematica". 2007.
[41] Titterton, D., & Weston, J. L. "Strapdown Inertial Navigation Technology," (Vol. 17) IET. 2004.
[42] "u-blox." u-blox. (2023). Retrieved June 27 from https://www.u-blox.com/en
[43] Wan, E. A., & Van Der Merwe, R. "The Unscented Kalman Filter for Nonlinear Estimation," in Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No. 00EX373), 2000.
[44] "ZED-F9K-01A Module: High Precision Dead Reckoning with Integrated IMU Sensors." u-blox. 2023.
[45] "ZED-F9K-01A: High Precision Automotive DR GNSS Receiver Automotive Grade." u-blox. 2023.
[46] Zhang, J., & Singh, S. "LOAM: Lidar Odometry and Mapping in Real-Time," in Robotics: Science and Systems, 2014.