學術產出-學位論文
文章檢視/開啟
書目匯出
-
題名 結合多模控制機制之水下無人載具自主導航系統
Autonomous Navigation for Unmanned Underwater Vehicles Using Multimodal Control Strategies作者 蔡孟哲
Tsai, Meng-Tse貢獻者 廖文宏
Liao, Wen-Hung
蔡孟哲
Tsai, Meng-Tse關鍵詞 水下無人載具
自主水下導航
AprilTag
線段偵測
光流法
UUV
autonomous underwater navigation
AprilTag
line detection
optical flow日期 2022 上傳時間 1-八月-2022 18:13:59 (UTC+8) 摘要 隨著時間的推移，自動化工程越來越被重視；透過無人載具結合自動化控制技術，可有效降低人力成本並節省大量時間，加上近年來由於軟硬體技術的進步，純視覺導航系統變得有開發價值。與陸上、空中環境進行導航任務不同，水下進行導航會面臨到下面幾個問題：包含水下色差、濁度、懸浮物導致影像品質不佳，且不同水域在水色上有相當的差異；由於水下無法使用GPS，所以較難進行路徑分析；另外因海水色差、折射的關係，所以較難透過第三方視角來進行觀測；最後水下水流多變，需即時調整無人載具之位姿才可完成導航任務，所以發展可靠、具有定位功能的導航系統有其必要性。本論文主要的貢獻有三，首先本論文提出一款階層式多模架構的導航演算法，以因應不同水質環境中之導航任務，此階層式多模架構是由AprilTag、線段偵測、光流法所組成；其次本論文亦透過無人載具之多鏡頭協作來增強系統之穩定性，使其可在水下順利完成導航任務；最後、透過定義「引導以及控制規則」限制並調整無人載具之移動，使其可在水流的影響下保持穩定的導航。為驗證本系統之可靠性以及穩定性，本論文透過自行搭建模擬環境進行單元測試，並於多種仿真的水下場景進行整合測試，驗證結果顯示本架構可於各種場景順利、穩定的運行，最後也針對實際水下場景進行驗證，確立了本系統在現實中運行的可能性。
Autonomous navigation has been actively investigated and developed in recent years. By empowering unmanned vehicles with automatic controls, labor cost can be reduced effectively and a lot of time can be saved. In particular, vision-based navigation system has been the focus of many researches due to the advances in sensor technology.Unlike the ground and aerial navigation tasks, underwater vehicles usually face the following problems: underwater chromatic aberration, turbidity, and suspended objects that cause poor image quality. Since GPS cannot be used underwater, localization and path analysis are more challenging. Additionally, observing through third-person view is also difficult because of refraction. Finally, as waterflows are ever-changing, real-time control is needed. To sum up, the need to develop a reliable navigation system with positioning function is evident.There are three main contributions in this thesis. First, we design a hierarchical multimodal control algorithm to perform navigation tasks in different underwater environments. The multimodal system is composed of AprilTag, line detection, and optical flow. Second, this thesis also enhances the stability of the system through the collaboration of unmanned vehicle’s multi-cameras. Third, by devising "guidance and control rules" to limit and adjust the movement of the unmanned vehicle, we can maintain more stable navigation.To verify the reliability and stability of the system, this research conducts a number of unit tests in simulated environments. Integration tests on various simulated underwater scenes are then performed. Experimental results clearly indicate that the proposed framework can run smoothly and stably in various scenes. At last, we conducted multiple tests in real underwater environments to validate the feasibility of the proposed control schemes in real world.參考文獻 [1] Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015). ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE transactions on robotics, 31(5), 1147-1163.[2] Engel, J., Koltun, V., & Cremers, D. (2017). Direct sparse odometry. IEEE transactions on pattern analysis and machine intelligence, 40(3), 611-625.[3] Olson, E. (2011, May). AprilTag: A robust and flexible visual fiducial system. In 2011 IEEE international conference on robotics and automation (pp. 3400-3407). IEEE.[4] Ang, K. H., Chong, G., & Li, Y. (2005). PID control system analysis, design, and technology. IEEE transactions on control systems technology, 13(4), 559-576.[5] Human Interface Technology Lab, ARToolKit, http://www.hitl.washington.edu/artoolkit/, Last visited on Jan 2022[6] Fiala, M. (2005, June). ARTag, a fiducial marker system using digital techniques. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR`05) (Vol. 2, pp. 590-596). IEEE.[7] Mohan, A., Woo, G., Hiura, S., Smithwick, Q., & Raskar, R. (2009). Bokode: imperceptible visual tags for camera based interaction from a distance. In ACM SIGGRAPH 2009 papers (pp. 1-8).[8] Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011, November). ORB: An efficient alternative to SIFT or SURF. In 2011 International conference on computer vision (pp. 2564-2571). Ieee.[9] Lowe, D. G. (1999, September). Object recognition from local scale-invariant features. In Proceedings of the seventh IEEE international conference on computer vision (Vol. 2, pp. 1150-1157). Ieee.[10] Lucas, B. D., & Kanade, T. (1981, April). An iterative image registration technique with an application to stereo vision.[11] Ismail, A. H., Ramli, H. R., Ahmad, M. H., & Marhaban, M. H. (2009, October). Vision-based system for line following mobile robot. In 2009 IEEE Symposium on Industrial Electronics & Applications (Vol. 2, pp. 642-645). IEEE.[12] Li, Y., Wu, X., Shin, D., Wang, W., Bai, J., He, Q., ... & Zheng, W. (2012, December). An improved line following optimization algorithm for mobile robot. In 2012 7th International Conference on Computing and Convergence Technology (ICCCT) (pp. 84-87). IEEE.[13] Hartley, R., Kamgar-Parsi, B., & Narber, C. (2018). Using roads for autonomous air vehicle guidance. IEEE Transactions on Intelligent Transportation Systems, 19(12), 3840-3849.[14] Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. (2010). Contour detection and hierarchical image segmentation. IEEE transactions on pattern analysis and machine intelligence, 33(5), 898-916.[15] Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International journal of computer vision, 59(2), 167-181.[16] Noshahri, H., & Kharrati, H. (2014, June). PID controller design for unmanned aerial vehicle using genetic algorithm. In 2014 IEEE 23rd International Symposium on Industrial Electronics (ISIE) (pp. 213-217). IEEE.[17] Sangyam, T., Laohapiengsak, P., Chongcharoen, W., & Nilkhamhang, I. (2010, August). Path tracking of UAV using self-tuning PID controller based on fuzzy logic. In Proceedings of SICE annual conference 2010 (pp. 1265-1269). IEEE.[18] Zhang, T., & Gao, J. X. (2010, May). Multi-sensor data fusion approach for terrain match navigation of autonomous underwater vehicles. In 2010 The 2nd International Conference on Industrial Mechatronics and Automation (Vol. 1, pp. 130-133). IEEE.[19] Hidalgo, F. (2020, October). ORBSLAM2 and Point Cloud Processing towards Autonomous Underwater Robot Navigation. In Global Oceans 2020: Singapore–US Gulf Coast (pp. 1-4). IEEE.[20] Park, J., & Kim, J. (2016, November). High-precision underwater navigation using model-referenced pose estimation with monocular vision. In 2016 IEEE/OES Autonomous Underwater Vehicles (AUV) (pp. 138-143). IEEE.[21] Panetta, K., Kezebou, L., Oludare, V., & Agaian, S. (2021). Comprehensive underwater object tracking benchmark dataset and underwater image enhancement with GAN. IEEE Journal of Oceanic Engineering.[22] Du, D., Wen, L., Zhu, P., Fan, H., Hu, Q., Ling, H., ... & Zhao, Z. (2020, August). VisDrone-CC2020: The vision meets drone crowd counting challenge results. In European Conference on Computer Vision (pp. 675-691). Springer, Cham.[23] Centelles, D., Soriano, A., Martí, J. V., Marin, R., & Sanz, P. J. (2019, June). UWSim-NET: An open-source framework for experimentation in communications for underwater robotics. In OCEANS 2019-Marseille (pp. 1-8). IEEE.[24] Manhães, M. M. M., Scherer, S. A., Voss, M., Douat, L. R., & Rauschenbach, T. (2016, September). UUV simulator: A gazebo-based package for underwater intervention and multi-robot simulation. In OCEANS 2016 MTS/IEEE Monterey (pp. 1-8). IEEE.[25] Suzuki, S. (1985). Topological structural analysis of digitized binary images by border following. Computer vision, graphics, and image processing, 30(1), 32-46.[26] THUNDER TIGER, Seadragon 8-Axis, https://www.ttrobotix.com/zh-tw/products/detail/927.html, 2019 描述 碩士
國立政治大學
資訊科學系
109753112資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109753112 資料類型 thesis dc.contributor.advisor 廖文宏 zh_TW dc.contributor.advisor Liao, Wen-Hung en_US dc.contributor.author (作者) 蔡孟哲 zh_TW dc.contributor.author (作者) Tsai, Meng-Tse en_US dc.creator (作者) 蔡孟哲 zh_TW dc.creator (作者) Tsai, Meng-Tse en_US dc.date (日期) 2022 en_US dc.date.accessioned 1-八月-2022 18:13:59 (UTC+8) - dc.date.available 1-八月-2022 18:13:59 (UTC+8) - dc.date.issued (上傳時間) 1-八月-2022 18:13:59 (UTC+8) - dc.identifier (其他 識別碼) G0109753112 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/141186 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系 zh_TW dc.description (描述) 109753112 zh_TW dc.description.abstract (摘要) 隨著時間的推移，自動化工程越來越被重視；透過無人載具結合自動化控制技術，可有效降低人力成本並節省大量時間，加上近年來由於軟硬體技術的進步，純視覺導航系統變得有開發價值。與陸上、空中環境進行導航任務不同，水下進行導航會面臨到下面幾個問題：包含水下色差、濁度、懸浮物導致影像品質不佳，且不同水域在水色上有相當的差異；由於水下無法使用GPS，所以較難進行路徑分析；另外因海水色差、折射的關係，所以較難透過第三方視角來進行觀測；最後水下水流多變，需即時調整無人載具之位姿才可完成導航任務，所以發展可靠、具有定位功能的導航系統有其必要性。本論文主要的貢獻有三，首先本論文提出一款階層式多模架構的導航演算法，以因應不同水質環境中之導航任務，此階層式多模架構是由AprilTag、線段偵測、光流法所組成；其次本論文亦透過無人載具之多鏡頭協作來增強系統之穩定性，使其可在水下順利完成導航任務；最後、透過定義「引導以及控制規則」限制並調整無人載具之移動，使其可在水流的影響下保持穩定的導航。為驗證本系統之可靠性以及穩定性，本論文透過自行搭建模擬環境進行單元測試，並於多種仿真的水下場景進行整合測試，驗證結果顯示本架構可於各種場景順利、穩定的運行，最後也針對實際水下場景進行驗證，確立了本系統在現實中運行的可能性。 zh_TW dc.description.abstract (摘要) Autonomous navigation has been actively investigated and developed in recent years. By empowering unmanned vehicles with automatic controls, labor cost can be reduced effectively and a lot of time can be saved. In particular, vision-based navigation system has been the focus of many researches due to the advances in sensor technology.Unlike the ground and aerial navigation tasks, underwater vehicles usually face the following problems: underwater chromatic aberration, turbidity, and suspended objects that cause poor image quality. Since GPS cannot be used underwater, localization and path analysis are more challenging. Additionally, observing through third-person view is also difficult because of refraction. Finally, as waterflows are ever-changing, real-time control is needed. To sum up, the need to develop a reliable navigation system with positioning function is evident.There are three main contributions in this thesis. First, we design a hierarchical multimodal control algorithm to perform navigation tasks in different underwater environments. The multimodal system is composed of AprilTag, line detection, and optical flow. Second, this thesis also enhances the stability of the system through the collaboration of unmanned vehicle’s multi-cameras. Third, by devising "guidance and control rules" to limit and adjust the movement of the unmanned vehicle, we can maintain more stable navigation.To verify the reliability and stability of the system, this research conducts a number of unit tests in simulated environments. Integration tests on various simulated underwater scenes are then performed. Experimental results clearly indicate that the proposed framework can run smoothly and stably in various scenes. At last, we conducted multiple tests in real underwater environments to validate the feasibility of the proposed control schemes in real world. en_US dc.description.tableofcontents 謝辭 I摘要 IIABSTRACT III目錄 IV表目錄 VII圖目錄 IX第一章 緒論 11.1 研究背景與動機 11.2 研究目的 21.3 論文架構 3第二章 技術背景與相關研究 42.1 視覺基準標籤 42.2 特徵比對 92.2.1 ORB 102.2.2 光流法 112.3 線段偵測 122.4 PID控制器 132.5 水下載具自主導航之背景與突破 152.5.1 小結 17第三章 研究方法與單元測試成果 183.1 系統之架構分析及說明 183.1.1 多模決策機制 193.1.2 AprilTag子系統 203.1.3 線段偵測子系統 213.1.4 光流法子系統 213.1.5 多鏡頭決策機制 223.1.6 載具控制機制與視覺化模組 233.2 陸上與水上場景分析 243.3 AprilTag可行性測試 263.3.1 種類測試 273.3.2 遮蔽測試 293.3.3 曲度測試 313.3.4 傾斜角度測試 323.3.5 水下模擬之距離測試 333.4 模擬環境 343.5 誤差計算標準 383.6 AprilTag水下載具測試 393.6.1 距離對AprilTag之影響 393.6.2 AprilTag挑選標籤機制 403.7 線段跟隨水下載具測試 423.8 光流法水下載具測試 423.9 其他單元測試 433.9.1 PID控制器測試結果 443.9.2 像素修正演算法測試結果 453.9.3 多模整合測試 463.9.4 (Weighted) Moving Average & Moving Median測試結果 473.9.5 指令傳送頻率測試結果 50第四章 模擬場景整合測試結果 514.1 模擬場景測試 514.2 沉船場景測試 514.3 湖泊場景測試 534.4 港灣場景測試 55第五章 實機測試結果 585.1 水下無人載具之規格 585.2 AprilTag 懸停測試 595.2.1 平行鏡頭懸停 595.2.2 斜45度角鏡頭懸停 605.3 AprilTag 跟隨測試 615.3.1 平行鏡頭跟隨 625.3.2 斜45度角鏡頭跟隨 635.3.3 多鏡頭模式協作跟隨 635.4 線段偵測測試 645.5 光流法測試 65第六章 結論與未來工作 67參考文獻 68 zh_TW dc.format.extent 5201209 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109753112 en_US dc.subject (關鍵詞) 水下無人載具 zh_TW dc.subject (關鍵詞) 自主水下導航 zh_TW dc.subject (關鍵詞) AprilTag zh_TW dc.subject (關鍵詞) 線段偵測 zh_TW dc.subject (關鍵詞) 光流法 zh_TW dc.subject (關鍵詞) UUV en_US dc.subject (關鍵詞) autonomous underwater navigation en_US dc.subject (關鍵詞) AprilTag en_US dc.subject (關鍵詞) line detection en_US dc.subject (關鍵詞) optical flow en_US dc.title (題名) 結合多模控制機制之水下無人載具自主導航系統 zh_TW dc.title (題名) Autonomous Navigation for Unmanned Underwater Vehicles Using Multimodal Control Strategies en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] Mur-Artal, R., Montiel, J. M. M., & Tardos, J. D. (2015). ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE transactions on robotics, 31(5), 1147-1163.[2] Engel, J., Koltun, V., & Cremers, D. (2017). Direct sparse odometry. IEEE transactions on pattern analysis and machine intelligence, 40(3), 611-625.[3] Olson, E. (2011, May). AprilTag: A robust and flexible visual fiducial system. In 2011 IEEE international conference on robotics and automation (pp. 3400-3407). IEEE.[4] Ang, K. H., Chong, G., & Li, Y. (2005). PID control system analysis, design, and technology. IEEE transactions on control systems technology, 13(4), 559-576.[5] Human Interface Technology Lab, ARToolKit, http://www.hitl.washington.edu/artoolkit/, Last visited on Jan 2022[6] Fiala, M. (2005, June). ARTag, a fiducial marker system using digital techniques. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR`05) (Vol. 2, pp. 590-596). IEEE.[7] Mohan, A., Woo, G., Hiura, S., Smithwick, Q., & Raskar, R. (2009). Bokode: imperceptible visual tags for camera based interaction from a distance. In ACM SIGGRAPH 2009 papers (pp. 1-8).[8] Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011, November). ORB: An efficient alternative to SIFT or SURF. In 2011 International conference on computer vision (pp. 2564-2571). Ieee.[9] Lowe, D. G. (1999, September). Object recognition from local scale-invariant features. In Proceedings of the seventh IEEE international conference on computer vision (Vol. 2, pp. 1150-1157). Ieee.[10] Lucas, B. D., & Kanade, T. (1981, April). An iterative image registration technique with an application to stereo vision.[11] Ismail, A. H., Ramli, H. R., Ahmad, M. H., & Marhaban, M. H. (2009, October). Vision-based system for line following mobile robot. In 2009 IEEE Symposium on Industrial Electronics & Applications (Vol. 2, pp. 642-645). IEEE.[12] Li, Y., Wu, X., Shin, D., Wang, W., Bai, J., He, Q., ... & Zheng, W. (2012, December). An improved line following optimization algorithm for mobile robot. In 2012 7th International Conference on Computing and Convergence Technology (ICCCT) (pp. 84-87). IEEE.[13] Hartley, R., Kamgar-Parsi, B., & Narber, C. (2018). Using roads for autonomous air vehicle guidance. IEEE Transactions on Intelligent Transportation Systems, 19(12), 3840-3849.[14] Arbelaez, P., Maire, M., Fowlkes, C., & Malik, J. (2010). Contour detection and hierarchical image segmentation. IEEE transactions on pattern analysis and machine intelligence, 33(5), 898-916.[15] Felzenszwalb, P. F., & Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International journal of computer vision, 59(2), 167-181.[16] Noshahri, H., & Kharrati, H. (2014, June). PID controller design for unmanned aerial vehicle using genetic algorithm. In 2014 IEEE 23rd International Symposium on Industrial Electronics (ISIE) (pp. 213-217). IEEE.[17] Sangyam, T., Laohapiengsak, P., Chongcharoen, W., & Nilkhamhang, I. (2010, August). Path tracking of UAV using self-tuning PID controller based on fuzzy logic. In Proceedings of SICE annual conference 2010 (pp. 1265-1269). IEEE.[18] Zhang, T., & Gao, J. X. (2010, May). Multi-sensor data fusion approach for terrain match navigation of autonomous underwater vehicles. In 2010 The 2nd International Conference on Industrial Mechatronics and Automation (Vol. 1, pp. 130-133). IEEE.[19] Hidalgo, F. (2020, October). ORBSLAM2 and Point Cloud Processing towards Autonomous Underwater Robot Navigation. In Global Oceans 2020: Singapore–US Gulf Coast (pp. 1-4). IEEE.[20] Park, J., & Kim, J. (2016, November). High-precision underwater navigation using model-referenced pose estimation with monocular vision. In 2016 IEEE/OES Autonomous Underwater Vehicles (AUV) (pp. 138-143). IEEE.[21] Panetta, K., Kezebou, L., Oludare, V., & Agaian, S. (2021). Comprehensive underwater object tracking benchmark dataset and underwater image enhancement with GAN. IEEE Journal of Oceanic Engineering.[22] Du, D., Wen, L., Zhu, P., Fan, H., Hu, Q., Ling, H., ... & Zhao, Z. (2020, August). VisDrone-CC2020: The vision meets drone crowd counting challenge results. In European Conference on Computer Vision (pp. 675-691). Springer, Cham.[23] Centelles, D., Soriano, A., Martí, J. V., Marin, R., & Sanz, P. J. (2019, June). UWSim-NET: An open-source framework for experimentation in communications for underwater robotics. In OCEANS 2019-Marseille (pp. 1-8). IEEE.[24] Manhães, M. M. M., Scherer, S. A., Voss, M., Douat, L. R., & Rauschenbach, T. (2016, September). UUV simulator: A gazebo-based package for underwater intervention and multi-robot simulation. In OCEANS 2016 MTS/IEEE Monterey (pp. 1-8). IEEE.[25] Suzuki, S. (1985). Topological structural analysis of digitized binary images by border following. Computer vision, graphics, and image processing, 30(1), 32-46.[26] THUNDER TIGER, Seadragon 8-Axis, https://www.ttrobotix.com/zh-tw/products/detail/927.html, 2019 zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202200839 en_US
