6.1 結論
本論文主要的目標在於使機器人能自主偵測並安全進行抓取任務之方法與 研究。論文中設計一影像伺服控制的演算法可以利用影像取得環境資訊，使其在 執行任務時可以安全的反應並閃避環境中物體，並完成所需執行的任務。本論文 藉由環境中物體平面與攝影機距離的梯度方向不同的特性，將環境切割成數個不 同平面來表示，同時利用所得平面藉由 SURF 的演算法進行比對，經由縮減比對 的區域，可以大大縮減比對的時間，使機器人能即時偵測出環境中的目標物與障 礙物的位置，並經由座標轉換，取得 3D 的資訊。此外，本論文也針對手臂安全 的考量，設計了一套機械手臂的安全行為策略，利用同心圓柱的概念，由物體占 據同心圓柱的層級，來判斷物體對機械手臂在運動中影響的程度，此影響的指數 由內到外來遞減，並利用投影的方式，將環境投影至三個平面上，藉此將空間分 成安全、不確定與為顯三種區域，找出此三種區域與手臂目前位置的相對關係，
定義出手臂往各個方向的安全指數。在規劃路徑上，我們設計是依據手臂可活動 空間的範圍與使手臂移動較短距離來建立 Potential field，在將所得的兩個安全指 數應用於 Potential field 上，使機械手臂能選擇較安全的區域移動，並透過對整 體空間的規劃，改善了 Potential field 只針對區域規劃而產生的 local minima 的問 題。
在實驗的驗證之下，我們可以確認機器手臂能即時避開障礙物，並能引導機 械手臂至目標物所在位置，完成抓取的任務。
6.2 未來展望
本論文在感應器使用方面，由於只使用深度攝影機來取得外界資訊，所觀察 到的環境有限，因此未來可以整合順應性控制的部分，已達到主動避障與被動避 障同時進行，能使機器人對於反應不及或攝影機無法偵查到的碰撞也能做出反 應，如此可以大幅提升機械手臂的安全性與實用性。
對於機器人的應用方面，目前已完成自主安全抓取在環境中指定物品的任 務，若能整合移動平台，使機器人能自主導航至物體擺設的位置，並交付給指定 的人，機器人的功能會更佳的完善，且大大的提升了人類生活的便利性。
此外，由於本論文所使用的機器人為雙臂的設計，將來可以研究雙手臂的協 調合作，不但能擴大手臂工作的範圍，並可以完成更多元的任務。
參考文獻
[1] A. De Luca, A. Albu-Schaffer, S. Haddadin and G. Hirzinger, “Collision Detection and Safe Reaction with the DLR-III Lightweight Manipulator Arm,”
in Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing, China, 2006, pp. 1623-1630.
[2] Lucian Balan and Gary M. Bone, “Real-time 3D Collision Avoidance Method for Safe Human and Robot Coexistence,” in Proc. of International Conference on Intelligent Robots and Systems, Beijing, China, 2006, pp.276-282.
[3] Han-Young Jang, Hadi Moradi, Suyeon Hong, Sukhan Lee, JungHyun Han,
“Spatial Reasoning for Real-time Robotic Manipulation,” in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing, China, 2006, pp. 2632-2637.
[4] Nikolay Jetchev and Marc Toussaint, “Trajectory Prediction in Cluttered Voxel Environments” in Proceedings of IEEE Int. Conf. on Robotics and Automation(ICRA) ,Alaska,USA,2010, pp. 2523-2528.
[5] I. Iossifidis and G. Schoner, “Dynamical Systems for Autonomous Avoidance of Obstacles and Joint-limits for an Redundant Robot Arm” in Proc. of IEEE Int.
Conf. on Intelligent Robot and systems, Beijng, China, 2006, pp. 580-585 [6] H. Reimann, I. Iossifidis and G. Schoner, “Generating Collision Free Reaching
Movements for Redundant Manipulators Using Dynamical Systems” in Proceedings of IEEE Int. Conf. on Intelligent Robot and systems, Taipei, Taiwan, 2010, pp. 5372 – 5379.
[7] D. H. park, H.Hoffmann, P. Pastor and S.Schaal “Movement Reproduction and Obstacle with Dynamic Movement Primitives and Potential Field,” in Proceedings of RAC international Conference ,Daejeon,Korea, 2008, pp. 91-98.
[8] Riccardo Schiavi,Antonio Bicchi and Fabrizio Flacco, “ Integration of Active and Passive Compliance Controlfor Safe Human-Robot Coexistence, ” in Proc.
of IEEE International Conference on Robotics and Automation, Kobe, Japan, 2009, pp.259-264.
[9] S. M. LaValle, “Rapidly-Exploring Random Trees: A New Tool for Path Planning,”Technical Report, Computer Science Dept, Iowa State University, 1998.
[10] J. Bruce and M. Veloso, “Real-time Randomized Path Planning for Robot Navigation,” in Proc. of IEEE/RSJ International Conference on Intelligent Robots and Systems , Lausanne, Switzerland, 2002, pp. 2383-2388.
[11] D. Ferguson, N. Kalra and A. Stentz, “Replanning with RRTs,” in Proc. of IEEE International Conference on Robotics and Automation, Orlando, Florida, pp.
1243-1248, 2006.
[12] L. Jaillet, A.Yershova S. M. LaValle and T. Simeon,“Adaptive Tuning of the Sampling Domain for Dynamic-Domain RRTs,” in Proc. of IEEE International Conference on Intelligent Robots and Systems, 2005, pp.2851-2857.
[13] Dominik Bertram, James Kuffner, Ruediger Dillmann and Tamim Asfour,“ An Integrated Approach to Inverse Kinematics and Path Planning for Redundant Manipulator,”in Proc. of IEEE International Conference on Robotics and Automation, Orlando, FL, 2006, pp.1874-1879.
[14] Bakir Lacevic and Paolo Rocco, “Towards a Complete Safe Path Planning for Robotic Manipulator,”in Proc. of IEEE/RSJ International Conference on Intelligent Robot and Systems, Taipei, Taiwan, 2010, pp.5366-5371.
[15] Dmitry Berenson, Siddhartha S. Srinivasa, Dave Ferguson, Alvaro Collet and James J. Kuffner, “ Manipulation Planning with Workspace Goal Regions, ” in Proc. of IEEE International Conference on Robotics and Automation, Kobe, Japan, 2009, pp.618-624.
[16] Yi-Chih Tsai, and Han-Pang Huang,“Motion Planning of a Dual-Arm Mobile Robot in the Configuration-Time Space, ” in Proc. of IEEE Int. Conf. on Robotics and Automation(ICRA),Louis, USA, 2009, pp.2458-2463.
[17] Kimitoshi Yamazaki, Masayuki Inaba, Takemitsu Mori and Takashi Yamamoto,
“Online Collision and Occlusion Detection Based on 3D Cuboid Maps for a Daily Assistive Robot with a Tilting LRF, ” in Proc. of IEEE International Conference on Mechatronics and Automation(ICMA) , Beijing, China, 2011, pp.
767-772.
[18] http://www.play.com/Games/Xbox360/4-/10296372/Project-Natal/Product.html [19] Rafael C. Gonzalez and Richard E. woods, “Digital Image Processing,” prentice
Hall, 2008.
[20] 張哲豪, “基於立體視覺之移動式機械臂影像伺服設計” 國立交通大學電機 與控制工程學系碩士論文, 2010.
[21] M. Fischler and R. Bolles, “Random Sampling Consensus: a Paradigm for Model Ftting with Application to Image Analysis and Automated Cartography,”
Commun. Assoc. Comp. Mach., 1981, vol. 24, pp. 381-395.
[22] http://en.wikipedia.org/wiki/RANSAC
[23] 許傑巽, “一種機械手臂順應性控制與安全設計, ”國立交通大學電機工程研 究所碩士論文, 2010.
[24] R. P. Paul, “Robot Manipulators: Mathematics, Programming, and Control, the Computer Control of Robot Manipulators,” MIT Press, 1981
[25] 王衍翔, “擬人型雙手臂機器人之機電設計、運動規劃與合作, ” 國立中興大 學電機工程學系碩士論文, 2009.
[26] Min Gyu Park and Min Cheol Lee, “A New Technique to Escape Local Minimum in Artificial Potential field Based Path Planning, ” KSME International Journal, Vol. 17 No.12. pp. 1876-1885, 2003.
[27] Paraskevas Dunias, “Autonomous Robots Using Aritificial Potential fields,”
Technische Universiteit Eindhoven, 1996.