本論文實現一基於機器人作業系統(Robot Operating System)之跨樓層自主式導航服務型機器人，使機器人能夠於多樓層之間進行導航任務，其功能包括建置地圖、定位、路徑規劃、以及樓層辨識。建置地圖方面使用了Gmapping，配合雷射測距儀可以建置所需的二維平面地圖。定位使用了「自適應蒙地卡羅定位法」(Adaptive Monte Carlo Localization, AMCL)，配合雷射測距儀所接收到的環境資訊，可以計算出機器人在地圖上的所在位置，同時使用所得到的定位結果，讓機器人達到良好的行走效果。路徑規劃使用了「改良型A*路徑規劃」，讓機器人規劃出一條避開地圖上障礙物的路徑，以安全到達目的地。由於需要在多樓層之間進行導航任務，所以本文也提出了一個以深度卷積神經網路設計的決策系統，用於辨識樓層及讀取該樓層的地圖資訊，透過訓練大量的樓層場景圖片資料，得到的訓練模型能夠辨識出當前樓層。為了驗證此導航系統之效能及可行性，本論文中在擁有多樓層的室內環境中進行實驗，由實驗結果得知，本論文提出之導航以及樓層辨識系統能於多樓層之間有效地進行導航任務。

In this thesis, an autonomous cross-floor robot is implemented based on robot operating system (ROS) with functionalities including path planning, mapping, localization, and scene recognition. Various navigation techniques are used in this thesis, where 2D maps of the environment that the robot needs are built by the Gmapping algorithm, Adaptive Monte Carlo Localization algorithm is utilized in localization, and an improved A* algorithm is utilized to do path planning avoid obstacles on the path. Since the robot needs to perform navigation task in a multi-floor environment, a decision system based on deep convolution neural network is designed to recognize the floors by training with a lot of scene images. Finally, to validate the feasibility of the proposed method, real-world experiments of this proposed system are conducted.

[1] R. C. Ruo and C. C. Lai, “Enriched Indoor Map Construction Based on Multisensor Fusion Approach for Intelligent Service Robot,” IEEE Transactions on Industrial Electronics, vol. 59, no. 1, pp. 3135-3145, Aug. 2012.
[2] R. S. Kulikov, A. A. Chugunov, D. V. Tsaregorodcev, N. I. Petukhov, and I. R. Indrikov, “Two-dimension positioning solution of high accuracy navigation and orientation for service robots,” 2019 International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), Moscow, Russia, March 2009.
[3] E. J. Jung and B. J. Yi, “Study on Intelligent Human Tracking Algorithms with Application to Omni-Directional Service Robots,” 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Jeju, Korea, Oct. 2013, pp. 80-81.
[4] S. W. Hsiao and C. N. Wu, “A KE, DSM and ISM Based Approach for Patrol Robot Development,” 2018 International Conference on Control and Robots (ICCR), Hong Kong, China, Sep. 2018, pp. 30-34.
[5] M. Tresanchez, T. Palleja, M. Teixido, and J. Palacin, “Estimating a room size using encoders and collision detectors: application to a cleaning mobile robot,” 2007 IEEE International Symposium on Intelligent Signal Processing, Alcala de Henares, Spain, Oct. 2007.
[6] G. H. Kuo, C. Y. Cheng, and C. J. Wu, “Design and Implementation of a Remote Monitoring Cleaning Robot,” 2014 CACS International Automatic Control Conference (CACS 2014), Kaohsiung, Taiwan, Nov. 2014, pp. 281-286.
[7] Y. Wakita, H. Tanaka, and Y. Matsumoto, “Projection Function and Hand Pointer for User-Interface of Daily Service Robot,” 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), Macau, China, Dec. 2017, pp. 2218-2224.

[8] Y. C. Lee and S. H. Park, “Localization Method for Mobile Robots Moving on Stairs,” 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), San Diego, CA, USA, Oct. 2014, pp. 4014-4020.
[9] Y. C. Lee and J. Kim, “Multi-Floor Localization Method for Mobile Robots Using Elevator,” 2016 16th International Conference on Control, Automation and Systems (ICCAS), Gyeongju, South Korea, Oct. 2016, pp. 869-872.
[10] E. W. Dijkstra, “A Note on Two Problems in Connexion with Graphs,” Numerische Mathematlk, vol. 23, no. 1, pp. 269-271, 1959.
[11] O. Takahashi and R. J. Schilling, “Motion Planning in a Plane Using Generalized Voronoi Diagrams,” IEEE Transactions on Robotics and Automation, vol. 5, no. 2, pp. 143-150, Apr. 1989.
[12] S. Thrun, W. Burgard, and D. Fox, “Probabilistic Robotics,” MIT Press, 2005.
[13] F. Dellaert, D. Fox, W. Burgard and S. Thrun, “Monte Carlo Localization for Mobile Robots,” Proceedings 1999 IEEE International Conference on Robotics and Automation, Detroit, MI, USA, May 1999, pp. 1322-1328.
[14] P. Barsocchi, S. Lenzi, and S. Chessa, “A Novel Approach to Indoor Rssi Localization by Automatic Calibration bf the Wireless Propagation Model,” VTC Spring 2009 - IEEE 69th Vehicular Technology Conference, Barcelona, Spain, Apr. 2009, pp. 1-5.
[15] V. Nair and G. Hinton, “Rectified Linear Units Improve Restricted Boltzmann Machines,” International Conference on Machine Learning, Haifa, June 2010, pp. 807-814.
[16] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recognition,” Proceedings of the IEEE., vol. 86, no. 11, pp. 2278-2324, 1998.
[17] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems, 2012, pp. 1106-1114.

[18] K. Simonyan, A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” In. Neural Information Processing Systems, Montreal, Dec. 2015.
[19] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, June 2016, pp. 779-788.
[20] J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, July 2017, pp. 6517-6525.
[21] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.Y. Fu, and A.C. Berg, “SSD: Single Shot MultiBox Detector,” Proceedings of the European Conference on Computer Vision (ECCV), 2016.
[22] D. Fox, “KLD-Sampling: Adaptive Particle Filters,” NIPS'01 Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic, Jan. 2001, pp. 713-720.
[23] https://www.udoo.org/
[24] https://www.gigabyte.com/tw/Mini-PcBarebone/GB-BXi5H-4200-rev-10#sp
[25] https://www.hokuyo-aut.jp/
[26] https://www.logitech.com/zh-tw/product/hd-pro-webcam-c920?crid=34
[27] http://www.aimtouch.com/monitor_cn.php
[28] https://www.edimax.com/edimax/tw/
[29] K.-Y. Wei, C.-C. Hsu, W.-Y. Wang and I-H. Lee, “Mobile Robot Navigation System Using Distributed Computing System Based on ROS Architecture,” World Congress of International Fuzzy Systems Association and International Conference on Soft Computing and Intelligent Systems, Japan, 2017.