近年來移動式機器人已經成為非常熱門的研究領域，也成功展示了許多新奇的概念用來解決人們的問題，像是掃地機器人、娛樂型機器人以及應用最廣泛的工業用機器人。家庭照護是一些醫療資源相對缺乏的國家所提出的一個新興領域，目的是為了提供老年人以及殘障人士更好的居家照顧。然而研究者仍然在尋求一個完善的系統能應付各種不同的情況。由於移動式機器人與環境是密不可分的，因此本論文提出一個自主式移動機器人應用於家庭照護環境，包含視覺監控、建圖與定位以及移動式機器人之路徑規畫之研究。首先，視覺監控系統會監控獨居老人或殘障人士在家中的動作，當目標行為異常時，室內的影像感測器會對未知的環境進行建圖及定位，擷取包括目標、障礙物及移動式機器人之位置，並進一步提供環境參數到移動式機器人。一套改良式Rapidly-exploring Random Tree (RRT) 路徑規畫演算用來找出一條無碰撞的最佳路徑，使移動機器人成功抵達目標後收集所需要的資訊給遠端的醫療中心，以提供進一步的協助。本論文顯示在視覺監控中，針對異常行為之偵測準確度達80%，亦能成功擷取未知環境中目標、障礙物及移動機器人之位置。最後，將環境變數輸入改良之RRT路徑規畫演算法，可以引導移動機器人在沒有任何碰撞發生下，快速抵達目標位置，同時節省64%之運算時間。

The research area of mobile robots has grabbed lots of research interests in recent years and has successfully demonstrated many concepts for solve people’s daily problems such as clean robots, entertainment robots, and the most industrial robots. Home care system has been proposed by some countries with finite medical resources to provide better cares especially to elderly and disabled people. However, the key technologies of an autonomous home care mobile robot are still developing to deal with different situations. This thesis proposed an autonomous home care mobile robot including three parts such as visual monitor, mapping and localization, and path planning on a mobile robot. First, a visual monitor is used to detect abnormal motions of the elderly or disabled person living alone when an emergency occurs. Once an abnormal motion is detected, it triggers the second system, mapping and localization to build up a map of the unknown environment and estimates further environmental parameters such as target position, obstacle positions, and the mobile robot position. After that, an improved Rapidly-exploring Random Tree (RRT) is used to generate an optimal path to help the mobile robot reach the target for providing necessary sensing information to the remote medical center for further assistances. This thesis shows the accuracy of the visual monitor is about 80% for abnormal motion detection and successfully estimates through mapping and localization. Finally, an improved RRT is used to generate a collision-free path to quickly guide the mobile robot to the target position with 64% reduced computation.

[1] M. Kass, Witkin, A., Terzopoilos, D., "Snake: Active Contour Models," International Journal of Computer Vision, pp. 321-331, 1988.
[2] E. H. D. Marr, "Theory of Edge Detection," Proc. of the Royal Society, pp. 187-217, 1980.
[3] P. E. H. R. O. Duda, "Use of the Hough Transformation to Detect Lines and Curves in Pictures," Commun. ACM, 15(1), pp. 11-15, 1972.
[4] J. K. Aggarwal and P. Sangho, "Human Motion: Modeling and Recognition of Actions and Interactions," in Proceedings 2nd International Symposium on 3D Data Processing, Visualization and Transmission, pp. 640-647, 2004.
[5] J. D. S.S. Intille, and A. Bobick, "Real Time Closed World Tracking," in Proceedings IEEE International Conference on Computer Vision, pp. 697-703, 1997.
[6] H. Fujiyoshi and A. J. Lipton, "Real-time Human Motion Analysis by Image Skeletonization," in Proceedings Fourth IEEE Workshop on Applications of Computer Vision, pp. 15-21, 1998.
[7] W. C. F. X. Cheng, and J. Kittler, "Periodic Human Motion Description for Sports Video Databases," ICPR, 2004.
[8] C. L. Chen, "A Vision Approachfor Recognizing Swimmer's Behaviors in Swimming Pool," Master, Graduate Institute of Automation and Control, National Taiwan University of Science and Technology, Taipei, Taiwan, 2009.
[9] Y.-T. Liao, "Slip and Fall Detection using Spatiotemporal Characteristics of Human Object for Video Surveillance System," Master, Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan, 2009.
[10] D. K. S. Ekvall, and P. Jensfelt, "Object Detection and Mapping for Service Robot Tasks," vol. 25, pp. 175-187, 2007.
[11] B. K. T. Kampke, E. Prassler, and M. Strobel, "Robot Position Estimation on a RFID-Tagged Smart Floor," Springer Tracts in Advanced Robotics, vol. 42, pp. 201-211, 2008.
[12] A. C. a. H. Raposo, "Robot Path Planning using SIFT and Sonar Sensor Fusion," in 7th WSEAS International Conference on Robotics, Control & Manufacturing Technology, Hangzhou, China, pp. 251-256, 2007.
[13] T. T. T. Takeshita, and A. Ohya, "A House Cleaning Robot System-Path indication and Position Estimation using Ceiling Camera," presented at the SICE-ICASE International Joint Conference, Korea, 2006.
[14] L. J. A. Yershova, T. Simon, and S. M. LaValle, "Dynamic-domain RRTs: Efficient Exploration by Controlling the Sampling Domain," in IEEE International Conference on Robotics and Automation, Barcelona, pp. 3856-3861, 2005.
[15] M. R. I. Ainsworth, and D. Brujic, "CAD-based Measurement Path Planning for Free-form Shapes using Contact Probes," International Journal of Advanced Manufacturing Technology, vol. 16, pp. 23-31, 2000.
[16] G. K. U. Nagarajan, and R. L. Hollis, "Trajectory Planning and Control of an Underactuated Dynamically Stable Single Spherical Wheeled Mobile Robot," presented at IEEE International Conferencein, Robotics and Automation, 2009.
[17] S. M. S. Takahashi, N. Tsuruta, and T. Morimoto, "A Home Health Care System for Elderly People," in The 7th Korea-Russia International Symposium, pp. 97-102, 2003.
[18] L. M. B. R. Barea, E. Lopez, M. Ocana, D. Schleicher, and A. Leon, "Robotic Assistants for Health Care," in IEEE International Conference on Robotics and Biomimetics, 2009.
[19] J. F. Canny, "Complexity of Robot Motion Planning," Cambridge, MA: MIT Press, 1988.
[20] M. H. O. V. Boor, and A. F. van der Stappen, "The Gaussian Sampling Strategy for Probabilistic Roadmap Planners," in IEEE International Conference on Robotics and Automation, pp. 1018-1023, 1999.
[21] K. E. B. E. Plaku, B. Y. Chen, A. M. Ladd, and L. E. Kavraki, "Sampling-Based Roadmap of Trees for Parallel Motion Planning," in IEEE Transactions on Robotics, vol. 21, pp. 597-608, 2005.
[22] M. B. a. D. Lowe, "Automatic Panoramic Image Stitching using Invariant Features," International Journal of Computer Vision, vol. 74, pp. 59-73, 2007.
[23] D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," International Journal of Computer Vision, vol. 60, pp. 91-110, 2004.
[24] L. Yanfang, W. Yaming, H. Wenqing, and Z. Zuoli, "Automatic image stitching using SIFT," in International Conference on Audio, Language and Image Processing, pp. 568-571, 2008.
[25] M. A. Fischler and R. C. Bolles, "Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography," Communications of the ACM, pp. 381–395, 1981.
[26] R. Szeliski, "Image Alignment and Stitching," pp. 273-292, 2006.
[27] Z. M. J. Xing, and J. Chen, "An Algorithm for Seamless Image Stitching and Its Application," pp. 85-90, 2007.
[28] M. Ghallab, "An Overview of Planning Technology in Robotics," Advances in Artificial Intelligence, pp. 29-49, 2004.
[29] L. K. a. J. C. Latombe, "Randomized Preprocessing of Configuration Space for Path Planning: Articulated Robots," in IEEE International Conference, pp. 1764-1771, 1994.
[30] B. L. J. Barraquand, and J. C. Latombe, "Numerical Potential Field Techniques for Robot Path Planning," in IEEE Transactions on Systems, Man and Cybernetics, , vol. 22, pp. 224-241, 1992.
[31] P. S. L. E. Kavraki, J. C. Latombe, and M. H. Overmars, "Probabilistic Roadmaps for Path Planning in High-dimensional Configuration Spaces," in IEEE Transactions on Robotics and Automation, vol. 12, pp. 566-580, 1996.
[32] J. J. K. J. a. S. M. L. Valle, "RRT-connect: An Efficient Approach to Single-query Path Planning," in IEEE International Conference on Robotics and Automation, San Francisco, CA, USA, pp. 995-1001, 2000.
[33] J. S. M. LaValle and J. J. Kuffner, "Randomized Kinodynamic Planning," in IEEE International Conference on Robotics and Automation, pp. 473-479, 1999.