本論文針對人形機器人之機械手臂，提出一個靜態避障之路徑規劃法。本論文先用RGB-D攝影機擷取機器人工作區的深度影像，再將其轉換成點雲資訊，並對工作區的障礙物進行物件分割，進而得到各個障礙物的位置資訊。然後，本論文使用快速搜索隨機樹(Rapidly-exploring Random Trees, RRT) 作為基礎的路徑搜索，雖然RRT在高維空間具有極高的搜索效率來快速地找到路徑，但其易產生冗餘且崎嶇的路徑。因此本論文使用直線濾波器移除不必要的路徑點來去除迂迴路徑。為了避免馬達因為路徑震盪而造成損耗，本論文使用非均勻B樣(Non-Uniform Rational B-Spline, NURBS)曲線平滑所找到的路徑，並根據障礙物的遠近改變NURBS內的權重值。最後再藉由本論文所推導的運動學來控制機械手臂的末端點，使其跟隨規劃出來的路徑移動。從模擬與實驗結果中可得知，本論文所提出之方法確實可以讓機械手臂之末端點沿著所規劃的路徑移動，並且在不碰撞到障礙物的情況下移動到終點。

In this thesis, a path planning method of static obstacle avoidance is proposed for a humanoid robot arm. The depth image of the work area of robot is first captured by RGB-D camera and then converted into point cloud information. The obstacles in the work area are segmented into objects and the position of each obstacle is obtained. Then, Rapidly-exploring Random Trees (RRT) is used as a basic path search algorithm. Although RRT can find a path quickly in a high-dimensional space with high search efficiency, it tends to produce redundant and rugged path. Therefore, Line of Sight Filter is used to remove unnecessary path points to remove detour path. In order to avoid the loss of the motor due to the path oscillation, Non-Uniform Rational B-Spline (NURBS) curve is used to smooth the found path and the weight values in NURBS are changed according to the obstacle's distance. Finally, the end-effector of the robot arm is controlled based on the derived kinematics so that it can move along the planned path. From the simulation and experimental results, we can see that the proposed method can really let the end-effector of the robot arm move along the planned path and move to the end point without colliding with obstacles.

目錄
目錄	I
圖目錄	IV
表目錄	VIII
第一章 緒論	1
1.1	研究背景	1
1.2	研究目的	3
1.3	論文架構	3
第二章 實驗平台與系統的介紹	4
2.1	前言	4
2.2	人形機器人機構介紹	4
2.3	硬體元件	8
2.3.1	RGB-D深度攝影機	8
2.3.2	工業電腦IPC	10
2.4	系統架構	11
第三章 點雲處理	13
3.1	前言	13
3.2	RANSAC平面分割	15
3.3	Euclidean Cluster物件分割	17
3.3.1	3D K-d tree	18
3.3.2	3D K-d tree的建立	18
3.3.3	鄰近點的搜尋	20
3.4	座標轉換矩陣	21
第四章 路徑規劃	23
4.1	前言	23
4.2	RRT	25
4.3	直線濾波器	28
4.4	曲線擬合	29
4.5	NURBS曲線	30
4.6	NURBS之避障權重	31
第五章 運動控制	33
5.1	前言	33
5.2	正向運動學	35
5.3	逆向運動學	36
5.3.1	尤拉角旋轉矩陣	37
5.3.2	位置逆運動學	38
5.3.3	姿態逆運動學	40
第六章 實驗結果	42
第七章 結論與未來展望	47
7.1	結論	47
7.2	未來展望	48
參考文獻	49


 
圖目錄
圖2.1、大型人形機器人的外觀實體圖	5
圖2.2、大型人形機器人的機構設計圖	6
圖2.3、人形機器人之自由度設計圖：(a)頭部、(b)腰部、(c)手部	7
圖2.4、RGB-D深度攝影機RealSense ZR300之實體圖	9
圖2.5、攝影機平台圖	9
圖2.6、工業電腦實體圖	10
圖2.7、機器人系統模組圖	11
圖2.8、ROS系統節點圖	12
圖3.1、深度攝影機RealSense ZR300擷取工作區之影像的原始點雲圖	14
圖3.2、點雲處理之三大步驟流程圖	15
圖3.3、RANSAC示範圖	15
圖3.4、去除桌面後之點雲圖	16
圖3.5、Euclidean Cluster物件分割之後的點雲圖	18
圖3.6、找到根節點圖	19
圖3.7、完成3D K-d tree的建立範例圖	20
圖3.8、3D K-d tree搜索範例圖	21
圖3.9、攝影機與機器人相對位置圖	22
圖4.1、2DA*移動方向受限示意圖	24
圖4.2、原始RRT之示意圖	27
圖4.3、基於機率P之RRT找到路徑之示意圖	28
圖4.4、直線濾波器修改RRT的路徑之示意圖	29
圖4.5、直線濾波器修改RRT的路徑之MATLAB模擬圖	29
圖4.6、NURBS不同權重示意圖	32
圖4.7、距離與權重對應圖	32
圖5.1、人形機器人之左手臂的馬達配置圖	34
圖5.2、機械手臂之肩膀球型關節圖	37
圖6.1、實驗場景圖	42
圖6.2、實驗場景之模擬圖	43
圖6.3、基於機率P之RRT找到路徑之示意圖	45
圖6.4、手臂之末端點在真實場景下實際移動過程的分解圖	46

 
表目錄
表2.1、馬達規格	8
表2.2、RGB-D深度攝影機RealSense ZR300之規格	9
表2.3、工業電腦規格	10
表3.1、RANSAC尋找最大平面	16
表3.2、Euclidean Cluster 物件分割	17
表3.3、建立3D K-d tree	19
表3.4、鄰近點的搜尋	20
表4.1、常用之路徑規劃演算法與其特性	23
表4.2、3個演算法之比較	25
表4.3、第一版的RRT (1998)	25
表4.4、原始RRT的Extend函數(1998)	25
表4.5、基於機率P之RRT的Extend函數(1999)	26
表5.1、六自由度機械手臂之DH連桿表的參數說明	34
表5.2、六自由度機械手臂之DH連桿參數表	35
表6.1、障礙物於攝影機座標系的位置	44
表6.2、障礙物於機械手臂座標系的位置	44

[1]	P.E. Hart, N.J. Nilsson, and B. Raphael, “A formal basis for the heuristic determination of minimum cost paths in graphs,” IEEE Transactions on Systems Science and Cybernetics, vol. ssc-4, No.2, pp.100-107, 1968. 
[2]	N. Lei and Z. Guobin, “An improved real 3D A* algorithm for difficult path finding situation,” The International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences, Vol. XXXVII, Part B4, pp.927-930, 2008.
[3]	C.J. Yu, Y.H. Chen, and C.C. Wong, “Path planning method design for mobile robots,” SICE Annual Conference, pp.1681-1686, 2011.
[4]	O. Khatib, “Real-time obstacle avoidance for manipulators and mobile robots,” IEEE International Conference on Robotics and Automation, pp.500-505, 1985.
[5]	L.E. Kavraki, P. Svestka, J.-C. Latombe, and M.H. Overmars, “Probabilistic roadmaps for path planning in high-dimensional configuration spaces,” IEEE Transactions on Robotics and Automation, vol. 12, no.4, pp. 566-580, 1996.
[6]	S.M. LaValle and J.J. Kuffner, “Rapidly-exploring random trees: A new tool for path planning,” Technical Report, Computer Science Department, Iowa State University, 1998.
[7]	E. Koyuncu, N.K. Ure, and G. Inalhan, “A probabilistic algorithm for mode based motion planning of agile air vehicles in complex environments,” The International Federation of Automatic Control, pp.2661-2668, 2008.
[8]	S. Jalel, M. Naouai, A. Hamouda, and M. Jebabli, “NURBS parameterization: A new method of parameterization using the correlation relationship between nodes,” Mexican Conference on Pattern Recognition, pp. 216-225, 2012.
[9]	S. Jalel, P. Marthon, and A. Hamouda, “Optimum path planning for mobile robots in static environments using graph modelling and NURBS curves,” International Conference on Signal Processing, Robotics and Automation, pp. 216-221, 2013.
[10]	S. Jalel, P. Marthon, and A. Hamouda, “A new path generation algorithm based on accurate NURBS curves,” International Journal of Advanced Robotic Systems, pp.1-14, 2016.
[11]	Robotis PRO: http://www.robotis.us/dynamixel-pro/
[12]	RealSense ZR300: https://www.google.com.tw/url?sa=t&rct=j&q=&es rc=s&source=web&cd=1&cad=rja&uact=8&ved=0ahUKEwj5hI3cnPXYAhUDv7wKHaLoA8QQFggmMAA&url=https%3A%2F%2Fclick.intel.com%2Fintelr-realsensetm-development-kit-featuring-the-zr300.html&usg=AOvVaw0w1yZ9QCeJ43ZMK2hRGSye 
[13]	ROS: https://www.ros.org/
[14]	PCL: http://pointclouds.org/
[15]	RANSAC: https://zh.wikipedia.org/wiki/%E9%9A%A8%E6%A9%9F %E6%8A%BD%E6%A8%A3%E4%B8%80%E8%87%B4
[16]	S.M. LaValle and J.J. Kuffner, “RRT-connect: An efficient approach to single-query path planning,” IEEE International Conference on Robotics and Automation, pp. 995-1001, 2000.
[17]	S.M. LaValle and J.J. Kuffner, “Randomized kinodynamic planning,” IEEE International Conference on Robotics and Automation, pp. 473-479, 1999.
[18]	A. Stentz, “Optimal and efficient path planning for partially-known environments,” IEEE International Conference on Robotics and Automation, pp.3310-3317, 1994.
[19]	M.A. Ali, H.A. Park, and C.S.G. Lee, “Closed-form inverse kinematic joint solution for humanoid robots,” IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 704-709, 2010.
[20]	R. O’Flaherty, P. Vieira, M. Grey, P. Oh, A. Bobick, M. Egerstedt, and M. Stilman, “Kinematics and inverse kinematics for the humanoid robot HUBO2+,” Georgia Institute of Technology, Technical Report, pp. 704-709, 2010.
[21]	賴宥澄，具多任務執行之七自由度冗餘機械手臂的系統開發及運動控制，淡江大學電機工程學系碩士論文(指導教授：翁慶昌)，2016。
[22]	T. Asfour and R. Dillmann, “Human-like motion of a humanoid robot arm based on a closed-form solution of the inverse kinematics problem,” IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.1407-1412, 2003.
[23]	T. Zhao, J. Yuan, M.-y. Zhao, and D.-l. Tan, “Research on the kinematics and dynamics of a 7-DOF arm of humanoid robot,” IEEE International Conference on Robotics and Biomimetics, pp. 1553-1558, 2006.