成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	蔡栒 Tsai, Syun
論文名稱：	雷達-視覺運動估計與向量地圖輔助之鬆耦合 INS/GNSS 地面載具慣性導航演算法 Radar–Visual Ego-Motion and Vector-Map Aiding in Loosely-Coupled INS/GNSS Land-Vehicle Navigation
指導教授：	江凱偉 Chiang, Kai-Wei
學位類別：	博士 Doctor
系所名稱：	工學院 - 測量及空間資訊學系 Department of Geomatics
論文出版年：	2026
畢業學年度：	114
語文別：	英文
論文頁數：	245
中文關鍵詞：	慣性導航系統、單目視覺里程計、毫米波雷達、動態估計、高精向量地圖
外文關鍵詞：	INS/GNSS integrated system, Monocular visual odometry, FMCW radar, ego-motion estimation, HD vector map
相關次數：	點閱：4 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

精準、連續的定位是自動駕駛和智慧交通的基礎，然而其所依賴的衛星訊號卻恰好在車輛運行的環境（如城市峽谷、隧道和多層停車場）中容易受到遮蔽，在這些場景下，單靠低成本的慣性感測器無法彌補訊號遮蔽的問題。本論文透過融合低成本的單目攝影機和調頻連續波 (FMCW) 雷達——這兩者是駕駛輔助車輛上已配備的感測器——作為 INS/GNSS 導航系統的外部輔助觀測，在 GNSS 訊號長時間衰減的情況下維持定位能力。為了確保系統層級的穩健性與可驗證性，本設計刻意採用鬆耦合 (loosely-coupled) 架構：一個級聯架構的雷達-視覺運動估計器，將雷達的都卜勒速度與單目視覺里程計融合，轉換為具備尺度資訊的速度輔助，提供給誤差狀態卡爾曼濾波器 (Error-State Kalman Filter)。在此架構中，由雷達（而非 IMU）來估計視覺里程計的尺度，使得視覺通道在統計上能與慣性測量保持獨立；而系統外層則將視覺點雲與高精向量地圖進行參照對齊。若單憑雷達速度，車輛角速率的可觀測性較弱——這導致單純依靠雷達輔助反而會略微降低導航航向精度——然而，慣性導航系統 (INS) 的先驗資訊能正規化雷達的求解過程，並透過錯誤偵測機制剔除異常的雷達回波；同時，視覺通道提供了直接的偏航角觀測，進而恢復並提升了航向精度。作為一種透過外部觀測得到的車輛運動約制，雷達-視覺速度輔助能有效限制長時間訊號中斷下的慣性漂移：在低成本的微機電系統 (MEMS) 平台上，歷經 270 s 的立體停車場訊號中斷後，未經輔助的慣性解算會漂移超過一公里；然而，此輔助方法結合非完整約制 (non-holonomic constraint) 可將水平誤差控制在 3.68 m 內——與車輛自身的輪速里程計 (3.00 m) 相差不到一公尺。此外，不同於輪速里程計與該約束條件，雷達無需依賴任何車輛模型、亦無需接取車輛內部訊號即可限制漂移，這對於那些難以建立清晰運動學模型的平台來說極具吸引力。最後，本文在模擬環境中驗證了基於速度輔助的都卜勒解模糊 (Doppler disambiguation) 方法，並證明了將視覺點雲與向量地圖匹配作為絕對位置參考是具備可行性的。

Accurate, continuous positioning is the enabling layer beneath autonomous driving and intelligent transportation, yet the satellite signal it depends on is blocked in exactly the places where vehicles operate—urban canyons, tunnels, and multi-storey car parks—where a low-cost inertial sensor cannot bridge the outage alone. This dissertation maintains positioning through such prolonged GNSS degradation by fusing a monocular camera and a low-cost FMCW radar, sensors already present on driver-assistance vehicles, as aiding for an INS/GNSS navigator. The design is deliberately loosely-coupled for system-level robustness and verifiability: a cascaded radar–visual ego-motion estimator fuses the radar Doppler velocity with monocular visual odometry into a single scaled velocity aid for an error-state Kalman filter, with the radar—not the IMU—anchoring the metric scale of the visual odometry so that the visual channel remains statistically independent of the inertial measurement, and an outer layer references the visual point-cloud to a high-definition vector map. The vehicle yaw rate is only weakly observable from the radar velocity alone—so that raw radar aiding slightly degrades the navigation heading—while an INS prior regularizes the radar solve and rejects spurious returns through fault detection and exclusion, and the visual channel supplies a direct yaw observation that instead recovers and improves the heading. Acting as a measured vehicle-motion constraint, the radar–visual velocity aid bounds the inertial drift over prolonged outages: on a low-cost MEMS platform across a 270 s parking-tower outage, the unaided inertial solution drifts to over a kilometre, whereas the aid combined with the non-holonomic constraint holds the horizontal error to 3.68 m—within a metre of the vehicle's own wheel odometry (3.00 m). Unlike both wheel odometry and the constraint, it assuming no vehicle model and requiring no vehicle integration, which makes it attractive for platforms whose kinematics resist clean modelling. A velocity-aided Doppler disambiguation is validated in simulation, and the visual point-cloud to vector-map matching is shown to be feasible as an absolute position reference.

摘要 i
Abstract iii
誌謝 v
Table of Contents vii
List of Tables x
List of Figures xii
Abbreviations, List of Symbols and Nomenclature xvii
Chapter 1. Introduction 1
1. Background 1
2. Motivation and problem statement 3
3. Scope and objectives 8
4. Contributions 9
5. Dissertation outline 12
Chapter 2. Fundamentals of Inertial Navigation and Kalman Filtering 13
1. Introduction to Navigation System 13
1.1. Coordinate Frames 14
1.2. Global Navigation Satellite System 22
1.3. Inertial Navigation System 28
2. Fundamentals of Inertial Navigation System 29
2.1. INS Mechanization 30
2.2. Inertial Sensors 39
2.3. Inertial Navigation Fusion Schemes 44
3. Introduction to Kalman Filtering 49
3.1. Bayes Filter 50
3.2. Kalman Filter 52
3.3. Extended Kalman Filter 53
3.4. Error State Extended Kalman Filter 55
4. INS error dynamics 58
5. Kalman Filter design 60
5.1. System model 60
5.2. Measurement update 62
5.3. Filter recursion 62
6. Accuracy Improvement in Inertial Navigation System 63
6.1. External Measurement Update 63
6.2. Motion Constraint 64
Chapter 3. Fundamentals of Millimeter Wave Radar and Visual Odometry 67
1. Introduction to FMCW Radar 67
2. The Chirp Signal 68
3. FMCW Radar Measurements 70
3.1. Range Measurements 71
3.2. Velocity Measurements 73
3.3. Range-Doppler 2D FFT Processing 75
3.4. Angle of Arrival Measurements 76
3.5. Range-Angle Spatial FFT Processing 78
4. Radar Ego-Motion Estimation and Odometry 79
5. Limitations of the FMCW Radar 80
6. Introduction to Visual Odometry 81
7. Feature-Based Visual Odometry 87
8. Direct Methods: From Dense to Sparse 88
9. Why Direct Sparse Odometry 90
10. Limitations of Visual Odometry and the Motivation for Sensor Fusion 92
Chapter 4. Methodology 93
1. Time Synchronization 94
1.1. Clock Discipline of the Microcontroller to GNSS 95
1.2. Sensor-Level Triggering and Timestamping 98
2. Radar Doppler Velocity Measurement Model 100
2.1. Radar Velocity Observation Model in Body Frame 100
2.2. Rigid-Body Kinematics Expansion 103
2.3. Standard Design Matrix Form 104
3. Monocular Visual Odometry Observation Model in Body Frame 104
3.1. Visual Velocity, Angular Velocity, and Scale Ambiguity 105
3.2. Kinematic Transformation to Body Frame 105
4. Doppler Motion Compensation 107
5. Radar–Visual Ego-Motion Estimator 109
5.1. Radar Doppler Residual 110
5.2. Visual Odometry Residual Formulation 110
5.3. Regularized Weighted Least-Squares Solution 112
5.4. Robust Estimation and Angular Weighting 113
5.5. Posterior Covariance and Hand-off 114
6. Visual Point-Cloud to Vector-Map Matching 115
6.1. Vector Map Preprocessing 117
6.2. Lane Feature Extraction and Masking 117
6.3. Prior Placement and Multi-Frame Accumulation 118
6.4. ICP Residual Refinement 119
6.5. Correction Output and Semantics 120
7. System Integration Overview 121
Chapter 5. Experiments and Results 124
1. Experimental setup 125
1.1. Experiment Platform 125
1.2. Test Systems 126
1.3. Reference System 131
1.4. Camera Calibration 132
2. Experimental Scenes 133
2.1. Simulations 133
2.2. Road Tests 136
3. Accuracy Evaluation Indices 140
4. Velocity-aided Doppler Disambiguation 142
5. Radar Lever-arm and Yaw-rate Observability 145
6. Radar–Visual Ego-motion Estimator 148
6.1. Ego-motion Estimator Accuracy 149
6.2. Indoor versus Outdoor Measurement Geometry 151
6.3. Aided INS versus Motion Constraint 153
6.4. Aided INS versus Wheel Odometry 164
7. Visual Point-cloud to Vector-map Matching 166
8. Discussion 172
Chapter 6. Conclusion 180
1. Conclusion 180
2. Recommendations and Future Work 182
References 184
Appendix A. Rotation Representations 190
A.1. Euler Angles 190
A.2. Direction Cosine Matrix 191
A.3. Quaternions 191
A.4. Rotation vectors 193
A.5. Quick Comparison Table 194
Appendix B. Jacobian Matrices of the INS Error Dynamics 196
B.1. Position Error Dynamics 196
B.2. Velocity Error Dynamics 197
B.3. Attitude Error Dynamics 197
Appendix C. The Psi-Angle Error Model 198
C.1. Matrix Representation 199
Appendix D. Road-Test Accuracy Statistics 203
D.1. Open-sky (Road) 204
D.2. GNSS Outage (Outlet) 208
D.3. Long GNSS Outage (Hai-An) 212
D.4. GNSS-hostage (Tai 39) 216
D.5. High-speed (Tai 39) 220
                                    

[1] Nader Abdelaziz and Ahmed El-Rabbany. An integrated ins/lidar slam navigation system for gnss-challenging environments. Sensors, 22(12), 2022.
[2] Nader J. Abu-Alrub and Nathir A. Rawashdeh. Radar odometry for autonomous ground vehicles: A survey of methods and datasets. IEEE Transactions on Intelligent Vehicles, 9(3):4275–4291, 2024.
[3] Daniel Adolfsson, Martin Magnusson, Anas Alhashimi, Achim J. Lilienthal, and Henrik Andreasson. CFEAR radarodometry — conservative filtering for efficient and accurate radar odometry. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5462–5469, 2021.
[4] Sigurd M. Albrektsen and Tor Arne Johansen. User-configurable timing and navigation for UAVs. Sensors, 18(8):2468, 2018.
[5] Tim Bailey and Hugh Durrant-Whyte. Simultaneous localization and mapping (SLAM): part II. IEEE Robotics & Automation Magazine, 13(3):108–117, 2006.
[6] Paul J. Besl and Neil D. McKay. A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):239–256, 1992.
[7] Igal Bilik, Oren Longman, Shahar Villeval, and Joseph Tabrikian. The rise of radar for autonomous vehicles: Signal processing solutions and future research directions. IEEE Signal Processing Magazine, 36(5):20–31, 2019.
[8] Keenan Burnett, Yuchen Wu, David J. Yoon, Angela P. Schoellig, and Timothy D. Barfoot. Are we ready for radar to replace LiDAR in all-weather mapping and localization? IEEE Robotics and Automation Letters, 7(4):10328–10335, 2022.
[9] Cesar Cadena et al. Past, present, and future of simultaneous localization and mapping. IEEE Transactions on robotics, 32(6):1309–1332, 2016.
[10] Carlos Campos, Richard Elvira, Juan J Gómez Rodríguez, José M M Montiel, and Juan D Tardós. Orb-slam3: An accurate open-source library for visual, visual-inertial, and multimap slam. IEEE Transactions on Robotics, 37(6):1874–1890, 2021.
[11] Sarah H. Cen and Paul Newman. Precise ego-motion estimation with millimeter-wave radar under diverse and challenging conditions. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages 6045–6052, 2018.
[12] Kai-Wei Chiang, Dinh Thuan Le, Thanh Trung Duong, and Rui Sun. The performance analysis of INS/GNSS/V-SLAM integration scheme using smartphone sensors for land vehicle navigation applications in GNSS-challenging environments. Remote Sensing, 12(11):1732, 2020.
[13] Kai-Wei Chiang, Surachet Srinara, Yu-Ting Chiu, Syun Tsai, Meng-Lun Tsai, Chalermchon Satirapod, Naser El-Sheimy, and Mengchi Ai. Creation and verification of high-definition point cloud maps for autonomous vehicle navigation. IEEE Internet of Things Journal, 11(23):37582–37598, 2024.
[14] Kai-Wei Chiang, Surachet Srinara, Syun Tsai, Cheng-Xian Lin, and Meng-Lun Tsai. High-definition-map-based LiDAR localization through dynamic time-synchronized normal distribution transform scan matching. IEEE Transactions on Vehicular Technology, 72(6):7011–7023, 2023.
[15] Kai-Wei Chiang, Guang-Je Tsai, Yu-Hua Li, You Li, and Naser El-Sheimy. Navigation engine design for automated driving using ins/gnss/3d lidar-slam and integrity assessment. Remote Sensing, 12(10), 2020.
[16] Kai-Wei Chiang, Chi-Kuei Wang, Jung-Hong Hong, Pei-Ling Li, Chin-Sung Yang, Meng-Lun Tsai, Jeffrey Lee, and Sean Lin. Verification and validation procedure for high-definition maps in Taiwan. Urban Informatics, 1(1), 2022.
[17] Hoang Viet Do, Bo Sung Ko, Yong Hun Kim, and Jin Woo Song. CREVE: An acceleration-based constraint approach for robust radar ego-velocity estimation. arXiv preprint arXiv:2409.16847, 2024.
[18] Christopher Doer and Gert F. Trommer. An EKF based approach to radar inertial odometry. In Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), pages 152–159, 2020.
[19] Hugh Durrant-Whyte and Tim Bailey. Simultaneous localization and mapping: part I. IEEE Robotics & Automation Magazine, 13(2):99–110, 2006.
[20] Naser El-Sheimy, Haiying Hou, and Xiaoji Niu. Analysis and modeling of inertial sensors using Allan variance. IEEE Transactions on Instrumentation and Measurement, 57(1):140–149, 2008.
[21] Naser El-Sheimy and Ahmed Youssef. Inertial sensors technologies for navigation applications: state of the art and future trends. Satellite Navigation, 1(1), 2020.
[22] Jakob Engel, Vladlen Koltun, and Daniel Cremers. Direct sparse odometry. IEEE TPAMI, 40(3):611–625, 2018.
[23] Jakob Engel, Thomas Schöps, and Daniel Cremers. Lsd-slam: Large-scale direct monocular slam. In ECCV, pages 834–849, 2014.
[24] Gianluca Falco, Marco Pini, and Gianluca Marucco. Loose and tight GNSS/INS integrations: Comparison of performance assessed in real urban scenarios. Sensors, 17(2):255, 2017.
[25] Christian Forster, Luca Carlone, Frank Dellaert, and Davide Scaramuzza. On-manifold preintegration for real-time visual-inertial odometry. IEEE Transactions on Robotics, 33(1):1–21, 2017.
[26] Xiang Gao, Rui Wang, Nikolaus Demmel, and Daniel Cremers. Ldso: Direct sparse odometry with loop closure. In IROS, pages 2198–2204, 2018.
[27] Arthur Gelb. Applied Optimal Estimation. The MIT Press, 1974.
[28] Patrick Geneva, Kevin Eckenhoff, Yulin Yang, and Guoquan Huang. Lips: Lidar-inertial 3d plane slam. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018.
[29] Paul D. Groves. Principles of GNSS, Inertial, and Multisensor Integrated Navigation Systems. Artech House, second edition, 2013.
[30] Lei He, Zhe Jin, and Zhenhai Gao. De-skewing lidar scan for refinement of local mapping. Sensors, 20(7), 2020. deskewing lidar with high frequency IMU.
[31] Erick P. Herrera-Granda, Juan C. Torres-Cantero, Andrés Rosales, and Diego H. Peluffo-Ordóñez. A comparison of monocular visual slam and visual odometry methods applied to 3d reconstruction. Applied Sciences, 13(15), 2023.
[32] Cesar Iovescu and Sandeep Rao. The fundamentals of millimeter wave radar sensors. White Paper SPYY005A, Texas Instruments, 2017.
[33] Zaher Zak M Kassas, Mahdi Maaref, Joshua J Morales, Joe J Khalife, and Kimia Shamei. Robust vehicular localization and map matching in urban environments through imu, gnss, and cellular signals. IEEE Intelligent Transportation Systems Magazine, 12(3):36–52, 2020.
[34] Shinpei Kato, Eijiro Takeuchi, Yoshio Ishiguro, Yoshiki Ninomiya, Kazuya Takeda, and Tsuyoshi Hamada. An open approach to autonomous vehicles. IEEE Micro, 35(6):60–68, 2015.
[35] Dominik Kellner, Michael Barjenbruch, Jens Klappstein, Jürgen Dickmann, and Klaus Dietmayer. Instantaneous ego-motion estimation using Doppler radar. In Proceedings of the 16th International IEEE Conference on Intelligent Transportation Systems (ITSC), pages 869–874, 2013.
[36] Stefan Leutenegger. Okvis2: Realtime scalable visual-inertial slam with loop closure, 2022.
[37] Stefan Leutenegger, Simon Lynen, Michael Bosse, Roland Siegwart, and Paul Furgale. Keyframe-based visual-inertial odometry using nonlinear optimization. The International Journal of Robotics Research, 34(3):314–334, 2015.
[38] Yandong Li, Fei Liu, Jixian Zhang, Jian Wang, Houzeng Han, and Chunting Hao. A binocular vision/imu msckf localization method considering dynamic initialization and loopback detection. IEEE Sensors Journal, 25(1):1286–1303, 2025.
[39] Jiarong Lin and Fu Zhang. Loam livox: A fast, robust, high-precision lidar odometry and mapping package for lidars of small fov. In 2020 IEEE International Conference on Robotics and Automation (ICRA), pages 3126–3131. IEEE, 2020.
[40] Gary A. McGraw, Paul D. Groves, and Benjamin W. Ashman. Robust positioning in the presence of multipath and NLOS GNSS signals. In Position, Navigation, and Timing Technologies in the 21st Century, pages 551–589. Wiley-IEEE Press, 2020.
[41] Raul Mur-Artal, JMM Montiel, and Juan D Tardos. Orb-slam: a versatile and accurate monocular slam system. IEEE transactions on robotics, 31(5):1147–1163, 2015.
[42] K. Muravyev, A. Melekhin, et al. Open-source LiDAR Time Synchronization System by Mimicking GNSS-Clock. In 2022 IEEE International Symposium on Precision Clock Synchronization for Measurement, Control, and Communication (ISPCS). IEEE, 2022.
[43] Richard A Newcombe et al. Dtam: Dense tracking and mapping in real-time. In ICCV, pages 2320–2327, 2011.
[44] S. K. M. Nielsen et al. Sub-microsecond Time Synchronization for Network-Connected Microcontrollers. In 2024 IEEE International Conference on Consumer Electronics (ICCE). IEEE, 2024.
[45] Morten Nissov, Nikhil Khedekar, and Kostas Alexis. Simultaneous Triggering and Synchronization of Sensors and Onboard Computers. arXiv preprint arXiv:2507.05717, 2025.
[46] David Nistér. An efficient solution to the five-point relative pose problem. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(6):756–770, 2004.
[47] Fabian Poggenhans, Jan-Hendrik Pauls, Johannes Janosovits, Stefan Orf, Maximilian Naumann, Florian Kuhnt, and Matthias Mayr. Lanelet2: A high-definition map framework for the future of automated driving. In Proceedings of the 21st International IEEE Conference on Intelligent Transportation Systems (ITSC), pages 1672–1679, 2018.
[48] Chao Qin, Haoyang Ye, Christian E. Pranata, Jun Han, Shuyang Zhang, and Ming Liu. Lins: A lidar-inertial state estimator for robust and efficient navigation. In 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020.
[49] Tong Qin, Peiliang Li, and Shaojie Shen. Vins-mono: A robust and versatile monocular visual-inertial state estimator. IEEE Transactions on Robotics, 34(4):1004–1020, 2018.
[50] Sandeep Rao. Introduction to mmWave sensing: FMCW radars. Texas Instruments mmWave Training Series, 2017.
[51] Oleg S. Salychev. Inertial Systems in Navigation and Geophysics. Bauman MSTU Press, 1998.
[52] Davide Scaramuzza and Friedrich Fraundorfer. Visual odometry [tutorial]. IEEE robotics and automation magazine, 18(4):80–92, 2011.
[53] Tixiao Shan and Brendan Englot. Lego-loam: Lightweight and ground-optimized lidar odometry and mapping on variable terrain. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018.
[54] Tixiao Shan, Brendan Englot, Drew Meyers, Wei Wang, Carlo Ratti, and Daniela Rus. Lio-sam: Tightly-coupled lidar inertial odometry via smoothing and mapping. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5135–5142, 2020.
[55] Eun-Hwan Shin. Accuracy improvement of low cost ins/gps for land applications. Master's thesis, University of Calgary, Calgary, Canada, 2001. UCalgary PRISM.
[56] Eun-Hwan Shin. Estimation techniques for low-cost inertial navigation. PhD thesis, University of Calgary, Calgary, Canada, 2005.
[57] Surachet Srinara, Syun Tsai, Cheng-Xian Lin, Meng-Lun Tsai, and Kai-Wei Chiang. Reliable evaluation of navigation states estimation for automated driving systems. In 2022 IEEE Intelligent Vehicles Symposium (IV), pages 1765–1773, 2022.
[58] Andrea Tagliabue, Jesus Tordesillas, Xiaoyi Cai, Angel Santamaria-Navarro, Jonathan P. How, Luca Carlone, and Ali-Akbar Agha-Mohammadi. LION: Lidar-Inertial Observability-Aware Navigator for Vision-Denied Environments, page 380–390. Springer Proceedings in Advanced Robotics. Springer International Publishing, 2021.
[59] Texas Instruments. AN-2006 synchronizing a DP83640 PTP Master to a GPS Receiver. Technical Report SNOA548A, Texas Instruments, 2008.
[60] David Titterton and John Weston. Strapdown Inertial Navigation Technology. Institution of Engineering and Technology, second edition, 2004.
[61] Jordan Tunnell. Toward improving vehicle fuel economy with ADAS. SAE International Journal of Connected and Automated Vehicles, 1:81–92, 2018.
[62] Shinji Umeyama. Least-squares estimation of transformation parameters between two point patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(4):376–380, 1991.
[63] Lukas von Stumberg and Daniel Cremers. Dm-vio: Delayed marginalization visual-inertial odometry. IEEE Robotics and Automation Letters, 7(2):1408–1415, 2022.
[64] Yueqi Wang, Tangyou Liu, Licheng Feng, Jinze Wang, Yang Yang, Jianjun Bao, Binghao Li, and Liao Wu. Hardware-based time synchronization for a multi-sensor system. In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 4600–4607, 2024.
[65] Kento Yabuuchi. YabLoc: Open source visual localization for self-driving vehicles. GitHub repository, integrated into Autoware, 2023. Accessed 2026-07-02.
[66] Ji Zhang and Sanjiv Singh. Loam: Lidar odometry and mapping in real-time. In Robotics: Science and Systems, volume 2, pages 1–9. Berkeley, CA, 2014.
[67] Jun Zhang, He Zhuge, Zhenyu Wu, Guang Peng, Mingxing Wen, Yiyao Liu, and Danwei Wang. 4DRadarSLAM: A 4D imaging radar SLAM system for large-scale environments based on pose graph optimization. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages 8333–8340, 2023.
[68] Shibo Zhao, Hengrui Zhang, Peng Wang, Lucas Nogueira, and Sebastian Scherer. Super odometry: Imu-centric lidar-visual-inertial estimator for challenging environments. In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 8729–8736, 2021.
[69] 盧霈汝. 結合 INS/GNSS/單目視覺與高精地圖之直接地理洞察（DGC）導航系統開發. 碩士論文, 國立成功大學, 2025.
[70] 許嘉. 慣性導航核心之自駕車多感測器定位模組：結合全球衛星導航、慣性感測器、單目相機與高精向量地圖. 碩士論文, 國立成功大學, 2026.

簡易檢索 / 詳目顯示

相關論文