在機器人的環境感知中，常使用格點佔據式地圖 ( Occupancy Grid Map ) 來描述對於環境感知的不確定性。在其映射演算法中使用了二元貝氏濾波器 ( Binary Bayes Filter ) 來過濾感測器中雜訊干擾，並進一步採用「機率」來描述每個格點被障礙物佔據的可能性。
本論文使用行動機器人 U-Bot 搭配 Kinect 作為三維感測器來實現三維格點佔據地圖。使用二元貝氏濾波器需要反感知模型 ( Inverse Sensor Model )，本論文提出適合 Kinect 的反感知模型。Kinect 除了提供物體的深度資料，同時也提供物體的色彩訊息，因此本論文進一步提出顏色資訊的更新方式來描述環境的色彩訊息。論文中更將三維彩色格點佔據映射 ( 3D Occupancy Color Grid Mapping ) 演算法實作在機器人作業系統 ( Robot Operating System, ROS ) 的分散式處理架構中。最後的實驗結果顯示機器人能繪製出可用的室內環境三維地圖，達成預期的目標。本論文之成果將以影片呈現在YouTube: http://youtu.be/CMf5Snmz48I。

In the area of robot mapping, a classical method is the occupancy grid mapping algorithm, which account the measurement uncertainty. Occupancy grid mapping explains the probability of occupancy state of a grid by an ‘occupancy probability’, and uses binary Bayes filter to process sensor noise. This thesis builds the system by the Microsoft Kinect and the U-Bot mobile robot. The binary Bayes filter needs an inverse sensor model. We propose the inverse sensor model witch is applicable to Kinect. Kinect captures depth and color information image simultaneously, so we propose a color filter to describe the color information in the environment. We implemented the 3D occupancy color grid mapping by the robot operating system ( ROS ), which is a framework devoted to large-scale integrative robotics research. The results of the experiments demonstrate that we proposed system can successfully build the 3D color grid map in an indoor environment. The experimental scenario are presented by the video at YouTube: http://youtu.be/CMf5Snmz48I .

論文審定書 i
致謝 iv
摘要 vi
Abstract vii
目錄 viii
圖目錄 xii
表目錄 xiv
符號定義表 xv
第一章 緒論 1
1.1 研究背景與動機 1
1.2 相關文獻 2
1.2.1 數據式地圖 4
1.2.2 拓樸式地圖 5
1.3 論文架構 5
第二章 格點佔據式建圖演算法 7
2.1 二元貝氏濾波器 ( Binary Bayes Filter ) 7
2.2 反感知模型 ( Inverse Sensor Model ) 9
2.2.1 光線投射 ( Ray-Casting ) 12
2.3 演算法流程 13
2.4 夾擠策略 ( Clamping Policy ) 16
第三章 研究方法 18
3.1 彩色格點的更新策略 18
3.2 適用於Kinect的反感知模型 20
3.3 格點中的狀態 23
3.4 感測值座標轉換 24
3.5 地圖資料結構 25
3.5.1 紅黑樹 ( Red-Block Tree ) 27
3.5.2 三維座標轉換索引值 29
第四章 軟硬體系統設計 31
4.1 軟硬體架構 31
4.2 感測器：Kinect 32
4.3 行動機器人：U-Bot 34
4.4 機器人作業系統 ( Robot Operating System, ROS) 36
4.5 三維彩色格點建圖演算法在ROS中的分散式處理架構 39
4.6 流程圖 41
第五章 實驗結果與分析 43
5.1 實驗一：近距離測量 43
5.1.1 實驗環境 44
5.1.2 實驗結果 44
5.2 實驗二：移動並測量 46
5.2.1 實驗環境：由近至遠 46
5.2.2 實驗結果：由近至遠 47
5.2.3 實驗環境：由遠至近 48
5.2.4 實驗結果：由遠至近 49
5.3 實驗三：顏色誤差比較 ( 由近至遠 ) 50
5.3.1 實驗環境 50
5.3.2 實驗結果 51
5.4 實驗四：顏色誤差比較 ( 由遠至近 ) 55
5.4.1 實驗環境 55
5.4.2 實驗結果 56
5.4 實驗五：室內環境建圖 59
5.5.1 實驗環境 59
5.5.2 實驗結果 60
5.6 結論 62
第六章 結論與未來展望 64
6.1 結論 64
6.2 未來展望 64
參考資料 66

[1] S. Ronland, R. N. Illah “Introduction to Autonomous Mobile Robots”. The MIT Press, 2004.
[2] S. Elfes, “Using Occupancy Grids for Mobile Robot Perception and Navigation,” Computer , vol. 22, No.6, pp.46-57, 1989.
[3] S. Thrun, W. Burgard, D. Fox. “Probabilistic Robotics”. The MIT Press, September 2005, ch. 9.
[4] “ROS," [Online]. Available: http://www.ros.org/. [Accessed 15 06 2015].
[5] 機械與系統研究所, U-Bot 軟體使用手冊, 工業技術研究院, 2008.
[6] 機械與系統研究所, U-Bot 操作維護使用手冊, 工業技術研究院, 2008.
[7] Y. Roth-Tabak, R. Jain “Building an Environment Model Using Depth Information,” Computer , vol. 22, No.6, pp.85-90, 1989.
[8] A. S. S. Anderson, S. M. Rosiery, M. G. G. Luiz, “Current Advancements in Stereo Vision”, InTech, July 2012, ch.9.
[9] H. P. Moravec, A. Elfes. “High Resolution Maps from Wide Angle Sonar,” In Proceedings of the 1985 IEEE International Conference on Robotics and Automation, pp.116–121, 1985.
[10] D. Hähnel, W. Burgard, S. Thrun, “Learning Compact 3D Models of Indoor and Outdoor Environments with a Mobile Robot”, Robotics and Autonomous Systems, vol. 44, no. 1, pp. 15-27, Jul. 2003.
[11] R. Chatila, J.-P. Laumond. “Position Referencing and Consistent World Modeling for Mobile Robots,” In Proceedings of the 1985 IEEE International Conference on Robotics and Automation, vol. 2, pp. 138-154,1985.
[12] P. Henry, M. Krainin, E. Herbst, X. Ren, D. Fox, “RGB-D Mapping: Using Kinect-Style Depth Cameras for Dense 3D Modeling of Indoor Environments,” Int. J. Robot. Res., vol. 31, no. 5, pp. 647–663, Apr. 2012.
[13] F. Endres, J. Hess, J. Sturm, D. Cremers, W. Burgard, “3D Mapping with an RGB-D Camera,” IEEE Transactions on Robotics and Automation, vol.30, No.1, pp.177-187, 2014.
[14] N. Ouerhani, A. Bur, H. Hügli, “Visual Attention-Based Robot Self-Localization,” In Proceedings of European Conference on Mobile Robot (ECMR 2005) , pp. 8–13, Sep. 2005.
[15] J. O. Wetherbie, C. E. Smith, “Large-Scale Feature Identification for Indoor Topological Mapping,” In Proceedings of the 2001 IEEE International Conference on Systems, Man, and Cybermetics, vol.5, pp. 2852-2857, Oct. 2011.
[16] D. Kortenkamp, T. Weymouth, “Topological Mapping for Mobile Robots Using a Combination of Sonar and Vision Sensing,” In Proceedings of the Twelfth National Conference on Artificial Intelligence, AAAI Press/MIT Press, pp. 979–984, July 1994.
[17] J. Amanatides, A. Woo, “A Fast Voxel Traversal Algorithm for Ray Tracing,” In Proceedings of Eurographics, Amsterdam, The Netherlands,1987.
[18] J. Brenham, “Ambiguities in Incremental Line Rastering,” IEEE Computer Graphics and Applications, vol.7, No.5, pp.31-43, 1987.
[19] M. Yguel, O. Aycard, C. Laugier, “Update Policy of Dense Maps: Efficient Algorithms and Sparse Representation,” In Proceedings of the 6th International Conference on Field and Service Robotics, vol. 42, pp. 23–33, 2007.
[20] A. Hornung, K. M. Wurm, M. Bennewitz, C. Stachniss, W. Burgard, “OctoMap:An Efficient Probabilistic 3D Mapping Framework Based on Octrees”, Autonomous Robots, vol. 34, No.3, pp.189-206, 2013.
[21] L. J. Guibas, R. Sedgewick, “A Dichromatic Framework for Balanced Trees,” In Proceedings of the 19th Annual Symposium on Foundations of Computer Science, MI, USA, pp.8-21, 1978.
[22] K. Khoshelham, S. O. Elberink, “Accuracy and Resolution of Kinect Depth Data for Indoor Mapping Applications,” Sensors, vol.12, No.2, pp. 1437-1454, 2012.
[23] “MRPT," [Online]. Available: http:// http://www.mrpt.org/. [Accessed 15 07 2015].
[24] “Microsoft Kinect,” [Online]. Available: http://www.xbox.com/zh-TW/Kinect [Accessed 30 07 2015].
[25] “OpenKinect,” [Online]. Available: http://openkinect.org/wiki/Main_Page [Accessed 30 07 2015].