本論文基於嵌入式Linux環境製作移動機器人之主要功能為循跡行進。在移動機器人的循跡演算中，可藉由相機及影像處理得出機器人與地面軌跡的誤差量，再計算出左右輪的轉速命令。本移動機器人裝載有九軸感測器以協助機器人在沒有循跡路徑時依然可以依照空間的角度值前進。
本論文亦能針對特定的目標物辨識與按壓動作。藉由相機回傳之影像辨識出目標物所在位置並得到其於影像座標的誤差量與距離，使得移動機器人能夠以本身之機械臂對目標物進行按壓。
本論文同時實現操作者手勢的辨識與跟隨。同樣是基於影像辨識出手勢及其於影像座標的誤差量，使移動機器人能夠對準影像中的目標點，並以手勢之垂直座標為基準保持一定的距離。

關鍵詞：移動機器人、循跡控制、目標物按壓、手勢辨識、跟隨目標物

The main purpose of this thesis is building a mobile robot system, which is based on the embedded Linux environment, to track a curved line. In the mobile robot tracking algorithm, the error between the line on the ground and the robot base can be obtained by image process of camera image, then the robot controller calculates the wheels’ speed command to follow the line as close as possible. This mobile robot is also equipped with a motion sensor to feedback spaced three axes angle values and to assist the robot to move without line information.
The problem of recognition and pushing a specific target is also studied in this thesis. First, the system recognize the target and calculate the error in image coordinate from camera, and then it controls the robot arm installed in the mobile robot base to push the target.
Moreover, this thesis also studies hand gesture recognition and following. The system implementation is also based on image recognition and the following error of coordinate in image, to make mobile robot align to target coordinate and to keep a certain distance with the hand gesture in its vertical coordinate.

Keywords: mobile robot, tracking control, push target, hand gesture recognition, follow target.

[1] Yuh-Rau Wang, Wei-Hung Lin, Ling Yang,” A Fast Hand Motion Detection Based On Fifo,”2017 International Conference on Machine Learning and Cybernetics (ICMLC).
[2] Jisu Kim, Jeonghyun Baek, Euntai Kim“A part-based rotational invariant hand detection,”Proceedings of 2013 International Conference on Fuzzy Theory and Its Application.
[3] Hyung-Suk Lho, Ji-Wook Kwon, Dongkyoung Chwa, and Suk-Kyo Hong”Vision-Based Corridorline Detection Using K-Means Algorithm,” International Conference on Control, Automation and Systems 2007.
[4] Yeoun Jae Kim, Minho Park, Dong-Hyun Lee, Joon-Yong Lee, and Ju-Jang Lee,” Vision-Based Direction Determination of a Mobile Robot in Indoor Environment,” 5th IEEE International Conference on Digital Ecosystems and Technologies (IEEE DEST 2011), 31 May -3 June 2011, Daejeon, Korea.
[5] Haoxiang Lang, Ying Wang and Clarence W. de Silva,”Mobile Robot Localization and Object Pose Estimation Using Optical Encoder, Vision and Laser Sensors,”IEEE International Conference on Automation and Logistics Qingdao, pp. 617-622, 2008.
[6] Shijin C. S. and K. Udayakumar,”Speed Control of Wheeled Mobile Robots using PID with Dynamic and Kinematic Modelling,”in International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS) pp. 1-7, 2017.
[7] Xin Liu, Bin Dai, Hangen He,”Real-time Object Segmentation for Visual Object
Detection in Dynamic Scenes”.
[8] Jagdish Lal Raheja, Radhey Shyam, Umesh Kumar, P Bhanu Prasad,”Real-Time Robotic Hand Control using Hand Gestures,”Second International Conference on Machine Learning and Computing, 2010.
[9] Gang-Zeng Mao, Yi-Leh Wu, Maw-Kae Hor, Cheng-Yuan Tang,”Real-Time Hand Detection and Tracking against Complex Background,”Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, 2009.
[10] 施慶隆、李文猶，機電整合與控制-多軸運動設計與應用、第三版，全華
書局股份有限公司，2015。
[11] 朱廣文，自動車控制結合攝影機與雷射測距儀，國立台灣科技大學，碩士論文，2009。
[12] 黃峻昱，基於嵌入式Linux環境之循跡及遙控移動機器人，國立台灣科技大學，碩士論文，2018。