本研究主要目的為開發出一套能使全自主機器人在室內環境能夠更快速執行導航運動的快速道路建置系統。本研究中，機器人以RGB-D SLAM為主要定位方法，運用RGB-D攝影機所取得之影像，以SURF演算法取得偵測特徵點，建置出環境中的3D模型，並作為定位的依據。本研究使用以ROS系統所編寫的程式可進行快速簡潔的快速道路建構。在室內建構了快速道路當機器人的移動目標設定後可加速室內導航的速度，並提高導航移動中的穩定性。RGB-D SLAM 的精確度常因攝影機拍攝角度或是環境特徵多寡影響定位的穩定度。本系統設計了一個可適應定位不穩定的定位優化方法，可有效並穩定的控制機器人移動速度。本系統的導航目標除了可在地圖中指定位置之外，也可以搭配物件搜索系統進行即時的搜尋物件導航。本論文研發之導航系統平台，除了可搭配RGB-D SLAM定位技術之外，也可搭配其他例如Lidar SLAM、RGB SLAM、甚至是以深度學習為基礎的定位方法。

The main purpose of this research is to develop a highway implementation to be used in navigation system that enables autonomous mobile robot to perform navigation task more quickly in indoor environments. In this research, the robot uses RGB-D SLAM as the main localization method. The image acquired by the RGB-D camera is used to obtain the detection feature points by the SURF algorithm and establish the 3D model of the work environment. This research develops a ROS-compatible program for fast and simple highway construction and implementation. When the robot's moving target is set, the highway system is used to accelerate the speed of indoor navigation and improve the stability to navigation movement. The accuracy of RGB-D SLAM often affects the stability of localization due to camera angle or environmental feature. The system design with a localization optimization method that can adapt to unstable localization, which can effectively and stably control the speed of the robot. In addition to specifying the location in the map, the navigation target can also be used with the object search system for instant object-searching navigation. The navigation system developed in this research, in addition to RGB-D SLAM localization methods, can also be combined with other positioning methods such as Lidar SLAM, RGB SLAM, and localization methods based on deep learning techniques.

1. Smith, Randall C., and Peter Cheeseman. "On the representation and estimation of spatial uncertainty." The international journal of Robotics Research 5.4 (1986): 56-68.
2. Leonard, John J., and Hugh F. Durrant-Whyte. "Simultaneous map building and localization for an autonomous mobile robot." Proceedings IROS'91: IEEE/RSJ International Workshop on Intelligent Robots and Systems' 91. Ieee, 1991.
3. Davison, Andrew J., et al. "MonoSLAM: Real-time single camera SLAM." IEEE Transactions on Pattern Analysis & Machine Intelligence 6 (2007): 1052-1067.
4. Klein, Georg, and David Murray. "Parallel tracking and mapping for small AR workspaces." Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality. IEEE Computer Society, 2007.
5. Mur-Artal, Raul, Jose Maria Martinez Montiel, and Juan D. Tardos. "ORB-SLAM: a versatile and accurate monocular SLAM system." IEEE transactions on robotics 31.5 (2015): 1147-1163.
6. Labbé, Mathieu, and François Michaud. "Memory management for real-time appearance-based loop closure detection." 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2011.
7. Labbe, Mathieu, and Francois Michaud. "Appearance-based loop closure detection for online large-scale and long-term operation." IEEE Transactions on Robotics 29.3 (2013): 734-745.
8. Labbe, Mathieu, and François Michaud. "Online global loop closure detection for large-scale multi-session graph-based SLAM." 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2014.
9. Labbé, Mathieu, and François Michaud. "Long-term online multi-session graph-based SPLAM with memory management." Autonomous Robots 42.6 (2018): 1133-1150.
10. Ryo, Tsubota, Noguchi Noboru, and Mizushima Akira. "Automatic guidance with a laser scanner for a robot tractor in an orchard." Proceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE. 2004.
11. 朱廣文，自走車控制結合攝影機與雷射測距儀，國立台灣科技大學電機工程研究所碩士論文，民國98年。
12. Ismail, A. H., et al. "Vision-based system for line following mobile robot." 2009 IEEE Symposium on Industrial Electronics & Applications. Vol. 2. IEEE, 2009.
13. Pratama, Pandu Sandi, et al. "Positioning and obstacle avoidance of automatic guided vehicle in partially known environment." International Journal of Control, Automation and Systems 14.6 (2016): 1572-1581.

14. Bačík, Ján, et al. "Pathfinder–development of automated guided vehicle for hospital logistics." IEEE Access 5 (2017): 26892-26900.
15. 王旒军, et al. "RGB-D SLAM 综述." 导航定位与授时 6 (2017): 2.
16. 戴克斯特拉演算法，取自https://zh.wikipedia.org/wiki/%E6%88%B4%E5%85%8B%E6%96%AF%E7%89%B9%E6%8B%89%E7%AE%97%E6%B3%95
17. A星演算法，取自
https://zh.wikipedia.org/wiki/A*%E6%90%9C%E5%B0%8B%E6%BC%94%E7%AE%97%E6%B3%95
18. LaValle, Steven M. "Rapidly-exploring random trees: A new tool for path planning." (1998).
19. Stentz, Anthony. "Optimal and efficient path planning for partially known environments." Intelligent Unmanned Ground Vehicles. Springer, Boston, MA, 1997. 203-220.
20. Stentz, Anthony. "The focussed D^* algorithm for real-time replanning." IJCAI. Vol. 95. 1995.