現代都市大樓林立，機器人若擁有能在建築物內跨樓層移動的能力，就能夠為人類提供更多的服務。很多辦公建築物具有電梯設備，因此能操作並搭乘電梯是機器人能夠跨樓層的一種方式；同時為了保持機器人能夠穩定在建築物內移動而不迷失位置與方向，機器人需要能夠定位自身的位置，以克服經過長距離的移動後被累積放大的位置誤差。而相機在現代各種應用型或娛樂型機器人中也已經幾乎是必備的感測設備，假使能夠讓機器人像人類一樣記住周圍環境及可行走路徑，行走時像人類利用視覺進行判斷與定位，則可減少許多冗餘及昂貴的感測設備，讓智慧型機器人能更加親民可得。
本研究開發了一具擁有單目相機及機械手臂的輪型自走機器人，為了能夠在建築物內完成跨樓層送件任務，使用了單目相機作為視覺感測器，在同樓層的移動時利用相機的畫面進行影像處理，計算自身的定位以降低移動上產生的累積誤差；藉由校正機器人的移動路徑，使機器人在建築物內能穩定行走至目的地；透過辨識電梯面板上的按鈕、計算按鈕位置後，驅使機械手臂使機器人能夠自行操作並搭乘電梯，以達到跨樓層移動。為了方便使用者使用此機器人，製作了一個手機應用程式作為輸入介面，在介面上輸入目的地後，觸發機器人主程式開始運作，機器人完成送件任務後回到起點。

There are a lot of buildings in a city. Robots is helpful for human if they have the ability to move across floors. Elevator is a common equipment in an office building. Therefore, one solution to move across floors is to manipulate and take the elevator. In addition, after a long-distance movement, the error of the position and the orientation of the robot will be accumulated. In order to keep moving in a building stably and not to lose its position and orientation, a robot must have the ability to localize itself. Camera has been almost a necessary sensing equipment for various modern robots. If a robot can remember the surroundings and the passable path, make decisions and localize itself just like human with vision, much redundant expense of sensors can be reduced. It will make intelligent robots more available and affordable.
In this study, the robot, equipped with a monocular camera, a robotic arm and wheels, is developed to complete delivering tasks across floors in a building. The error, accumulated while the robot is moving in a floor, can be reduced by calculating the ego-position via image processing technique on acquired images. Correcting the trajectory of robot can provide stabilized movement to destination. To manipulate the elevator autonomously for crossing floors, the robotic arm is drove after the computer recognizes the button on the panel and calculates its position. A mobile application is developed as user interface of the robot to make it easy to be used by user. Entering destinations on the app triggers the main program of the robot. The robot will be back to the starting point after finishing delivering tasks.

Bailey, T., & Durrant-Whyte, H. (2006). Simultaneous localization and mapping (SLAM): Part II. IEEE robotics & automation magazine, 13(3), 108-117.
Bay, H., Tuytelaars, T., & Van Gool, L. (2006). Surf: Speeded up robust features. Paper presented at the European conference on computer vision.
Calonder, M., Lepetit, V., Strecha, C., & Fua, P. (2010). Brief: Binary robust independent elementary features. Paper presented at the European conference on computer vision.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O. (2007). MonoSLAM: Real-time single camera SLAM. IEEE Transactions on Pattern Analysis & Machine Intelligence(6), 1052-1067.
Durrant-Whyte, H., & Bailey, T. (2006). Simultaneous localization and mapping: part I. IEEE robotics & automation magazine, 13(2), 99-110.
Fuentes-Pacheco, J., Ruiz-Ascencio, J., & Rendón-Mancha, J. M. (2015). Visual simultaneous localization and mapping: a survey. Artificial Intelligence Review, 43(1), 55-81. doi:10.1007/s10462-012-9365-8
Gao, X.-S., Hou, X.-R., Tang, J., & Cheng, H.-F. (2003). Complete solution classification for the perspective-three-point problem. IEEE transactions on pattern analysis and machine intelligence, 25(8), 930-943.
Gálvez-López, D., & Tardos, J. D. (2012). Bags of binary words for fast place recognition in image sequences. IEEE Transactions on Robotics, 28(5), 1188-1197.
Golub, G. H., & Van Loan, C. F. (2012). Matrix computations (Vol. 3): JHU Press.
Hartley, R., & Zisserman, A. (2003). Multiple view geometry in computer vision: Cambridge university press.
Kang, J.-G., An, S.-Y., & Oh, S.-Y. (2007). Navigation strategy for the service robot in the elevator environment. Paper presented at the Control, Automation and Systems, 2007. ICCAS'07. International Conference on.
Klein, G., & Murray, D. (2007). Parallel tracking and mapping for small AR workspaces. Paper presented at the Mixed and Augmented Reality, 2007. ISMAR 2007. 6th IEEE and ACM International Symposium on.
Lepetit, V., Moreno-Noguer, F., & Fua, P. (2009). Epnp: An accurate o (n) solution to the pnp problem. International journal of computer vision, 81(2), 155.
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2), 91-110.
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.
Mur-Artal, R., Montiel, J. M. M., Tardos, J. D., & Gálvez-López, D. (2015). GitHub - raulmur/ORB_SLAM: A Versatile and Accurate Monocular SLAM. Retrieved from https://github.com/raulmur/ORB_SLAM
Mur-Artal, R., & Tardós, J. D. (2014). Fast relocalisation and loop closing in keyframe-based SLAM. Paper presented at the Robotics and Automation (ICRA), 2014 IEEE International Conference on.
OpenCV: Camera Calibration and 3D Reconstruction. Retrieved from https://docs.opencv.org/3.2.0/d9/d0c/group__calib3d.html
Penate-Sanchez, A., Andrade-Cetto, J., & Moreno-Noguer, F. (2013). Exhaustive linearization for robust camera pose and focal length estimation. IEEE transactions on pattern analysis and machine intelligence, 35(10), 2387-2400.
Rosten, E., & Drummond, T. (2006). Machine learning for high-speed corner detection. Paper presented at the European conference on computer vision.
Rosten, E., Porter, R., & Drummond, T. (2010). Faster and better: A machine learning approach to corner detection. IEEE transactions on pattern analysis and machine intelligence, 32(1), 105-119.
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011). ORB: An efficient alternative to SIFT or SURF. Paper presented at the Computer Vision (ICCV), 2011 IEEE international conference on.
Simmons, R., Goldberg, D., Goode, A., Montemerlo, M., Roy, N., Schultz, A. C., . . . Maxwell, B. (2003). Grace: An autonomous robot for the AAAI robot challenge. Retrieved from
Sinha, S. N., Frahm, J.-M., Pollefeys, M., & Genc, Y. (2006). GPU-based video feature tracking and matching. Paper presented at the EDGE, Workshop on Edge Computing Using New Commodity Architectures.
Thrun, S., Fox, D., Burgard, W., & Dellaert, F. (2000). Robust Monte Carlo localization for mobile robots. Retrieved from
Triggs, B., McLauchlan, P. F., Hartley, R. I., & Fitzgibbon, A. W. (1999). Bundle adjustment—a modern synthesis. Paper presented at the International workshop on vision algorithms.
Zhang, Z. (2000). A flexible new technique for camera calibration. IEEE transactions on pattern analysis and machine intelligence, 22.
洪于峻. (2017). 可跨樓層遞送物件之模組化載具建造. 成功大學工程科學系學位論文, 1-69.
袁聖翔. (2013). 即時影像辨識之跨樓層物料收發機器人. 成功大學工程科學系學位論文, 1-51.
陳漢忠. (2009). 智慧型搭乘電梯機器人; An Intelligent Robot With the Ability to Take Elevators. 國立中央大學圖書館,
曾宣僑. (2009). 具人機互動能力之服務型機器人. 成功大學工程科學系學位論文, 1-63.