近幾年，機器人漸漸從工廠進入生活中。由於能自主移動的機器人可以提升人員生產效率，因此移動機器人更是被普遍的使用。隨著硬體技術的進步，提高LIDAR及深度相機的效能並降低所需成本，機器人可透過搭載這些設備，使定位與移動能夠更加精確。
本篇論文透過結合2D LIDAR、RGBD相機及相關安全裝置，搭載在TurtleBot3 Burger上實作AMR機器人。2D LIDAR的資料為SLAM及路徑規劃的輸入，建置2D地圖及偵測是否有障礙物使機器人能夠閃避；RGBD相機作為VSLAM的輸入，建置3D地圖、地標資料庫，顯示機器人在3維空間中的移動軌跡及驗證機器人是否有移動到達正確地點。在VSLAM演算法中，加入物件偵測和OCR技術，從影像中提取具有語意的資料。3D地圖及地標資料庫，能提供使用者較具有意義的資訊。地標資料庫可用來與機器人移動時取得的影像進行SURF特徵與SSIM相似度比較，驗證是否有移動到達正確地點，以提升機器人在移動的準確度。
以Arduino與相關的感測器實作狀態燈、防墜、電量偵測及警告語音，作為機器人的安全裝置，使機器人在運作過程中可以達到更高的安全性。

In recent years, robots have gradually entered life from the factory. Since robots that can move autonomously can improve the productivity of personnel, mobile robots are even more commonly used. With the advancement of hardware technology, improving the performance of LIDAR and depth cameras and reducing the required cost, robots can be equipped with these devices to make positioning and movement more accurate.
This thesis implements an AMR robot on TurtleBot3 Burger by combining 2D LIDAR, RGBD camera and related safety devices. The data of 2D LIDAR is the input of SLAM and path planning, build 2D map and detect whether there are obstacles so that the robot can dodge; RGBD camera is used as the input of VSLAM, build 3D map, landmark database, show trajectory of the robot in 3D space and verify whether the robot has moved to the correct place. In the VSLAM algorithm, object detection and OCR technology are added to extract semantic data from the image. The 3D map and landmark database can provide users with more meaningful information. The landmark database can be used to compare the similarity of SURF features and SSIM with the images obtained when the robot is moving, to verify whether there is movement to the correct place, to improve the accuracy of the robot's movement.
The state lights, anti-falling, power detection, and warning voice implemented by Arduino and related sensors are used as the safety device of the robot so that the robot can make higher safety during operation.

[1] E. A. Oyekanlu et al., "A Review of Recent Advances in Automated Guided Vehicle Technologies: Integration Challenges and Research Areas for 5G-Based Smart Manufacturing Applications," IEEE Access, vol. 8, pp. 202312-202353, 2020.
[2] M. Quigley et al., "ROS: an open-source Robot Operating System," in ICRA workshop on open source software, 2009, vol. 3, no. 3.2: Kobe, Japan, p. 5.
[3] ROS Introduction [Online]. Available: http://wiki.ros.org/ROS/Introduction.
[4] S. Kohlbrecher, O. Von Stryk, J. Meyer, and U. Klingauf, "A flexible and scalable SLAM system with full 3D motion estimation," in 2011 IEEE international symposium on safety, security, and rescue robotics, 2011: IEEE, pp. 155-160.
[5] G. Grisetti, C. Stachniss, and W. Burgard, "Improved techniques for grid mapping with rao-blackwellized particle filters," IEEE transactions on Robotics, vol. 23, no. 1, pp. 34-46, 2007.
[6] E. B. Olson, "Real-time correlative scan matching," in 2009 IEEE International Conference on Robotics and Automation, 2009: IEEE, pp. 4387-4393.
[7] K. Konolige, G. Grisetti, R. Kümmerle, W. Burgard, B. Limketkai, and R. Vincent, "Efficient sparse pose adjustment for 2D mapping," in 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2010: IEEE, pp. 22-29.
[8] W. Hess, D. Kohler, H. Rapp, and D. Andor, "Real-time loop closure in 2D LIDAR SLAM," in 2016 IEEE International Conference on Robotics and Automation (ICRA), 2016: IEEE, pp. 1271-1278.
[9] Z. Xuexi, L. Guokun, F. Genping, X. Dongliang, and L. Shiliu, "SLAM algorithm analysis of mobile robot based on lidar," in 2019 Chinese Control Conference (CCC), 2019: IEEE, pp. 4739-4745.
[10] D. Shen, Y. Huang, Y. Wang, and C. Zhao, "Research and implementation of SLAM based on LIDAR for four-wheeled mobile robot," in 2018 IEEE International Conference of Intelligent Robotic and Control Engineering (IRCE), 2018: IEEE, pp. 19-23.
[11] H. Gao, X. Zhang, J. Wen, J. Yuan, and Y. Fang, "Autonomous indoor exploration via polygon map construction and graph-based SLAM using directional endpoint features," IEEE Transactions on Automation Science and Engineering, vol. 16, no. 4, pp. 1531-1542, 2018.
[12] D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International journal of computer vision, vol. 60, no. 2, pp. 91-110, 2004.
[13] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, "Speeded-up robust features (SURF)," Computer vision and image understanding, vol. 110, no. 3, pp. 346-359, 2008.
[14] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, "ORB: An efficient alternative to SIFT or SURF," in 2011 International conference on computer vision, 2011: Ieee, pp. 2564-2571.
[15] M. Calonder, V. Lepetit, C. Strecha, and P. Fua, "Brief: Binary robust independent elementary features," in European conference on computer vision, 2010: Springer, pp. 778-792.
[16] Z. Li et al., "Learning the depths of moving people by watching frozen people," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4521-4530.
[17] F. Wang and Z. Zhao, "A survey of iterative closest point algorithm," in 2017 Chinese Automation Congress (CAC), 2017: IEEE, pp. 4395-4399.
[18] A. Rosinol, M. Abate, Y. Chang, and L. Carlone, "Kimera: an open-source library for real-time metric-semantic localization and mapping," in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020: IEEE, pp. 1689-1696.
[19] G. Klein and D. Murray, "Improving the agility of keyframe-based SLAM," in European conference on computer vision, 2008: Springer, pp. 802-815.
[20] G. Klein and D. Murray, "Parallel tracking and mapping for small AR workspaces," in 2007 6th IEEE and ACM international symposium on mixed and augmented reality, 2007: IEEE, pp. 225-234.
[21] J. Engel, T. Schöps, and D. Cremers, "LSD-SLAM: Large-scale direct monocular SLAM," in European conference on computer vision, 2014: Springer, pp. 834-849.
[22] R. Mur-Artal, J. M. M. Montiel, and J. D. Tardos, "ORB-SLAM: a versatile and accurate monocular SLAM system," IEEE transactions on robotics, vol. 31, no. 5, pp. 1147-1163, 2015.
[23] C. Forster, M. Pizzoli, and D. Scaramuzza, "SVO: Fast semi-direct monocular visual odometry," in 2014 IEEE international conference on robotics and automation (ICRA), 2014: IEEE, pp. 15-22.
[24] R. Mur-Artal and J. D. Tardós, "Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras," IEEE Transactions on Robotics, vol. 33, no. 5, pp. 1255-1262, 2017.
[25] D. T. Savaria and R. Balasubramanian, "V-SLAM: Vision-based simultaneous localization and map building for an autonomous mobile robot," in 2010 IEEE Conference on Multisensor Fusion and Integration, 2010: IEEE, pp. 1-6.
[26] F. Steinbrücker, J. Sturm, and D. Cremers, "Real-time visual odometry from dense RGB-D images," in 2011 IEEE international conference on computer vision workshops (ICCV Workshops), 2011: IEEE, pp. 719-722.
[27] C. Kerl, J. Sturm, and D. Cremers, "Dense visual SLAM for RGB-D cameras," in 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013: IEEE, pp. 2100-2106.
[28] L. Goncalves et al., "A visual front-end for simultaneous localization and mapping," in Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005: IEEE, pp. 44-49.
[29] N. Karlsson, E. Di Bernardo, J. Ostrowski, L. Goncalves, P. Pirjanian, and M. E. Munich, "The vSLAM algorithm for robust localization and mapping," in Proceedings of the 2005 IEEE international conference on robotics and automation, 2005: IEEE, pp. 24-29.
[30] E. Karami, S. Prasad, and M. Shehata, "Image matching using SIFT, SURF, BRIEF and ORB: performance comparison for distorted images," arXiv preprint arXiv:1710.02726, 2017.
[31] RVIZ [Online]. Available: http://wiki.ros.org/rviz#Overview.
[32] Intel REALSENSE SDK [Online]. Available: https://github.com/IntelRealSense/librealsense.
[33] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788.
[34] J. Redmon and A. Farhadi, "YOLO9000: better, faster, stronger," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7263-7271.
[35] J. Redmon and A. Farhadi, "Yolov3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.
[36] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "Yolov4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020.
[37] Open Images Dataset V4 [Online]. Available: https://storage.googleapis.com/openimages/web/factsfigures_v4.html.
[38] F. S. Bashiri, E. LaRose, P. Peissig, and A. P. Tafti, "MCIndoor20000: A fully-labeled image dataset to advance indoor objects detection," Data in brief, vol. 17, pp. 71-75, 2018.
[39] Navigation Stack [Online]. Available: http://wiki.ros.org/navigation.
[40] TurtleBot3 [Online]. Available: https://emanual.robotis.com/docs/en/platform/turtlebot3/overview/.