在本論文當中，我們結合影像(RGB)與深度(Depth)資訊，提出了一種以RGB-D為基礎的自主式戶外履帶機器人，所設計履帶機器人可於日夜間戶外自主式完成偵測、迫近、及上下樓梯的動作。根據室外光線的變化，所開發履帶機器人可自動切換為深度資訊模式、混合影像深度資訊模式、及影像資訊模式。其中，深度資訊可用於環境光線不足時（如夜間或室內）履帶機器人的自主式控制；在室外陽光照射下，紅外線深度感測器資訊將無法正常取得，因此，本論文提出一混合影像與深度資訊的影像處理系統，首先，我們使用Hough建立RGB影像中樓梯邊緣特徵，再配合可取得的深度資訊，建立樓梯深度平面方程式，以完成樓梯距離偵測；在陽光完全直射下，紅外線深度感測器將完全無法取得資訊，履帶機器人將僅使用影像資訊，進行簡單的迫近動作。在RGB影像處理上，我們採用雙邊濾波器來強化樓梯邊緣及平滑影像。最後，經由實驗結果證實所開發之戶外履帶機器人，在戶外陽光及環境的影響下，可自主式地完成戶外連續上下樓梯的任務。

In this thesis, we combine RGB and depth information to develop an autonomous tracked robot for detecting stairs and moving on stairs in outdoor environments. This tracked robot can work not only in daytime but also in nighttime. The robot can detect, approach, climb up and down stairs autonomously. According to the variation of sunlight intensity, the robot switches from depth mode to RGB-D fusion mode or RGB mode by itself. Depth information from IR camera can be used in dark and indoor environments. Under sunlight, however, IR camera cannot work properly. Given the limitation, in this paper we propose an algorithm which is based on RGB-D data fusion. First, we use Hough to detect the features of stairs and then combine useful depth information to acquire needed information. Second, we use color image to approach stairs since IR camera can only obtain RGB data under sunlight. As for image processing, we use bilateral filter to enhance stair features and smooth the image. Finally, through the results of the experiment, we can confirm that the self-made tracked robot can detect, approach and climb up and down stairs continuously and autonomously in outdoor environments even under sunlight.

參考文獻

[1] D. Kurabayashi, S. Koga, T. Arai, J. Ota, H. Asama, and I. Endo, “Local path re-planning for unforeseen obstacle avoidance by an autonomous sweeping robot,” IEEE Trans. on Robotics and Automation, vol. 4, pp. 3153-3158, May 1992.
[2] H. Min, L, Huang, and X, Gan, “Research and Design of Multi-agent Model Structure for Embedded Robot Dog,” IEEE Trans. on WCICA, pp. 3629-3633, July 2012.
[3] M. Merten, A. Bley, C. Schroter, and H. Gross, “A mobile robot platform for socially assistive home-care applications,” Prof. of the Conference on Proceedings of ROBOTIK, May 2012, pp.1-6.
[4] J. Kim, Y. Lee, S. Han, S. kim, G. Lee, H. Ji, H. Choi, and K. Choi, “Autonomous Flight System using Marker Recognition on Drone,” IEEE Trans. on Joint Workshop on Frontiers of Computer Vision, Jan. 2015, pp1-4.
[5] I. Vincent and Q. Sun, “A combined reactive and reinforcement learning controller for an autonomous tracked vehicle,” Robotics and Autonomous Systems, vol. 60, pp. 599-608, 2012.
[6] A. I. Mourikis, N. Trawny, S. I. Roumeliotis, D. M. Helmick, and L. Matthies, “Autonomous stair climbing for tracked vehicles,” International Journal of Robotics Research, vol. 26, no. 7, pp. 737-758, July 2007.
[7] Y. Li, C. Li, and P. Chen, “Research and design of control system for a tracked sar robot under coal mine,” in Proc. IEEE International Conference on Automation and Logistics, Shenyang, Aug. 2009, pp. 1957-1961.
[8] H. H. Zhao, X. G. Duan, and G. Yang, “Kinematics and dynamics modeling of a small mobile robot with tracked locomotion mode,” IEEE International Conference on Robotics and Biomimetic, Dec. 2010, pp. 14-18.
[9] X. Gu, and L. Zhang, “Morphology open opreation in unit-linking pulse coupled neural network for image processing,” Prof. of the International Conference on Signal Processing, vol. 2, Sept. 2004, pp.1597-1600.
[10] T. Schoenemann, J. Kiefer1, S.-Y. Leung, B. Oerzen3, T. Inkinen, and P. Huguenot, “Commutation Process in Gas Circuit Breakers: Close-Operation and Commutation Failure During an Open-Operation,” IEEE Holm Conference on Electrical Contacts Sept. 2004, pp. 53-57.
[11] J. M. Geusebroek, A. W. M. Smeulders, and J. V. D. Weijer, “Fast Anisotropic Gauss Filtering,” IEEE Trans. on Image Processing, vol. 12, no. 8, Aug. 2003.
[12] N. Li, H. Zha, J. Hou, Z. Lei, and H. Fei, “Gauss filter circuit equivalent model of antenna with characteristic modes approach,” IEEE International Conference on Communication Problem-Solving (ICCP), Oct. 2015, pp.450-453.
[13] H. Kishan and C. S. Seelamantula, ” Sure-fast bilateral filters,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar. 2012, pp.1129-1132.
[14] S. Song, and J. Xiao, “Tracking Revisited using RGBD Camera: Unified Benchmark and Baselines,” IEEE International Conference on Computer Vision, Dec. 2013, pp. 233-240.
[15] M. Zhao, C.W. Fu, J. Cai and T. J. Cham, “Real-Time and Temporal-Coherent Foreground Extraction With Commodity RGBD Camera, ” IEEE Journal of Selected Topics in Signal Processing, vol. 9, no. 3, April 2015.
[16] D. Kim, J. Sun, S. M. Oh, J. M. Rehg and A. F. Bobick, “Traversability Classification using Unsupervised On-line Visual Learning for Outdoor Robot Navigation,” IEEE International Conference on Robotics and Automation, May 2006, pp.518-525.
[17] A. Chand and S. I. Yuta, ”Vision and Laser Sensor Data fusion Technique for Target Approaching by Outdoor Mobile Robot ,” IEEE International Conference on Robotics and Biomimetics, Dec. 2010, pp 1624-1629.
[18] I. Vincent and Q. Sun, “A combined reactive and reinforcement learning controller for an autonomous tracked vehicle,” Robotics and Autonomous Systems, vol. 60, pp. 563-576, 2012.
[19] Y. Cong, X. Li, J. Liu, and Y. Tang, “A stairway detection algorithm based on vision for ugv stair climbing,” in Proc. IEEE International Conference on Networking Sensing and Control, Sanya, April 2008, pp. 1806-1811.
[20] S. A. Stoeter and N Papanikolopoulos, “Autonomous Stair-Climbing With Miniature Jumping Robots”, IEEE Trans. on Systems, Man, and cybernetics—part b: cybernetics, vol. 35, no. 2, pp. 313 - 325 April 2005.
[21] A M. Johnson, M T. Hale, G. C. Haynes, and D. E. Koditschek, “Autonomous Legged Hill and Stairwell Ascent,” IEEE Trans. on International Symposium on Safety, Security and Rescue Robotics, pp. 134-142, November 2011.
[22] A. Chand and S. I. Yuta, “Vision and Laser Sensor Data Fusion Technique for Target Approaching by Outdoor Mobile Robot,” IEEE International Conference on Robotics and Biomimetics, China, December 2010, pp.1624-1629.
[23] 曾建凱，應用於樓梯偵測與攀爬之主動式履帶機器人開發，國立臺灣師範大學，碩士論文，一百零二年七月。
[24] 蕭智偉，主動式履帶機器人應用於連續樓梯攀爬與避障策略之研究，國立台灣師範大學，碩士論文，一百零四年七月。
[25] http://www.csim.com.tw/download/SLIM9-340E2-1040402.pdf
[26] http://www.csim.com.tw/download/SLIM9-340E2-1040402.pdf
[27] https://www.asus.com/tw/3D-Sensor/Xtion_PRO_LIVE/
[28] http://coopermaa2nd.blogspot.tw/2012/09/hc-sr04.html
[29] http://ming-shian.blogspot.tw/2013/09/arduino-hc-sr04.html
[30] https://www.realvnc.com/
[31] https://sites.google.com/a/ms.ttu.edu.tw/cse2012dance-robot/yan-jiu-cheng-guo/opencv-ruan-ti-she-ji/qin-shi-yu-peng-zhang
[32] http://eshare.stust.edu.tw/EshareFile/2010_4/2010_4_3b11d57a.pdf
[33] . http://www.aliog.com/27648.html
[34] https://cg2010studio.com/2012/10/14/%E9%9B%99%E9%82%8A%E6%BF%BE%E6%B3%A2%E5%99%A8-bilateral-filter/
[35] https://zh.wikipedia.org/wiki/%E9%AB%98%E6%96%AF%E6%A8%A1%E7%B3%8A
[36] http://chousml.wix.com/takashi-house#!canny/cpp8
[37] http://user.engineering.uiowa.edu/~dip/lecture/Segmentation2.html
[38] http://3.bp.blogspot.com/-awNNpaeW-jg/UMltwaCOxqI/AAAAAAAAq2Y/QYqM9e_spH8/s1600/hough-expl2.png
[39] http://www2.nsysu.edu.tw/physdemo/2012/A1/A1.php
[40] 徐仲帆，智 慧 型 櫥 櫃 於 居 家 環 境 之 應 用， 國立交通大學，碩士論文，九十五年六月。
[41] C. Tomasi and R. Manduch, “Bilateral Filtering for Gray and Color Images,” IEEE International Conference on Computer Vision, Bombay, India, Jan. 1998, pp.839-846.
[42] John Canny, “A Computational Approach to Edge Detection,” IEEE transactions on pattern analysis and machine intelligence, Bombay, Jan.1986, pp.679-698.
[43] Hough, P.V.C., “Method and Means for Recognizing Complex Patterns,” Patent 3,069,654, U.S, Dec.1962.
[44] N. E. Krausz, T. Lenzi, and L. J. Hargrove, “Depth Sensing for Improved Control of Lower Limb Prostheses,” IEEE transactions on biomedical engineering, vol. 62, no. 11, Nov. 2015.