本文旨在使用眼在手之影像系統辨識及定位三維工作空間之物體，並以機械臂影像回授控制完成視覺對正以及物體之抓取與放置等任務。發展之眼在手視覺對正系統之具體內容計有: (1)彩色影像顏色分割並據此偵測三維空間中物體之外形輪廓以及相機與物體之距離與方位角；(2)整合眼在手視覺系統與機械臂反運動學計算達到機械臂影像回授以及(3)計算物體影像特徵以及估測物體於三維空間之姿態並對正目標物體。最後，整合上述之機械臂、平動夾爪和眼在手視覺系統並基於電腦視覺回授完成三維空間物體辨識、量測以及抓取與放置等任務。實驗結果驗證本文所設計之機械臂及影像整合系統的正確性與有效性，整體物體對位控制之位置誤差小於1.2 mm以及角度誤差小於1.5度。

This paper aims to use the eye-in-hand vision system to identify and locate 3D objects in the work space, and the robotic system applies vision feedback control to execute tasks such as visual alignment as well as picking-and-placing objects. The specific functions of the developed vision alignment and control system are as follow: (1) performing color segmentation to obtain effective object segmentation results and to detect the contour of object and the distance and orientation between camera and object; (2) integrating eye-in-hand system and robot inverse kinematics calculation to achieve image feedback control and (3) computing the image feature of the object, estimating the posture of the object in the 3-dimensional space and aligning the target object. Finally, this work integrates the aforementioned robotic arm, flat gripper and eye-in-hand camera system and applies computer vision techniques to perform object identification, measurement, and picking-and-placing tasks. The experimental results have verified the correctness and validity of the proposed robot and vision integrated system with an overall alignment control error of 1.2 mm in positioning and 1.5 degrees in orientation angle.

[1] Teerawat Tongloy and Simon X. Yangt, “An Image-Based Visual Servo Control System Based on an Eye-in-Hand Monocular Camera for Autonomous Robotic Grasping,” Computational Intelligence in Robotics and Automation, pp. 132-136, 2016.
[2] Christopher G. Healey, “A Perceptual Colour Segmentation Algorithm,” University of British Columbia Vancouver, Technical Report, 1996.
[3] Lina Li, De Xu, Xingang Wang, “A Survey on Path Planning Algorithms in Robotic Fibre Placement,” IEEE Control and Decision Conference, pp. 4704-4709, 2015.
[4] S. Y. Chen, “Kalman Filter for Robot Vision: A Survey,” IEEE Transcations on Industrial Electronics, pp. 4409-4420, 2012.
[5] Corneliu Lazar and Adrian Burlacu, “Image-Based Visual Servoling for Manipulation via Predictive Control – A Survey of Some Reslts,” Memoirs of the Scientific Sections of the Romanian Academy, Technical Report, 2016.
[6] Gabriel J. Garcia , Juan A. Corrales, Jorge Pomares and Fernando Torres, “Survey of Visual and Force/Tactile Control of Robots for Physical Interaction in Spain,” Sensor Multidisciplinary Digital Publishing Institute, pp. 9689-9733, 2009.
[7] Ling-Yi Xu, Zhi-Qiang Cao, Peng Zhao, Chao Zhou, “A New Monocular Vision Measurement Method to Estimate 3D Positions of Objects on Floor,” International Journal of Automation and Computing, pp. 159-168, 2017.
[8] Lee Elliot Weiss, “Dynamic Visual Servo Control of Robots : an Adaptive Image-Based Approach,” Carnegie-Mellon University The Robotics Institute, 1984.
[9] Biao Zhang, Emilio J. Gonzalez-Galvan, Jesse Batsche, Steven B. Skaar, Luis A. Raygozab and Ambrocio Loredo, “Precise and Robust Large-Shape Formation using Uncalibrated Vision for a Virtual Mold,” INTECH Computer vision, pp. 111-124, 2008.
[10] Camera-Space Manipulation Steven B. Skaar, William H. Brockman and R. Hanson, “Camera-Space Manipulation,” The International Journal of Robotics Research, pp. 20-32, 1987.
[11] Hanqi Zhuang, “Simultaneous Calibration of a Robot and a Hand-Mounted Camera,” IEEE Transcations on Robotics amd Automation, pp. 649-660, 1995.
[12] Billibon H. Yoshimi and Peter K.Allen, “Active, Uncalibrated Visual Servoing,” IEEE International Conference on Robotics and Automation, pp. 156-161, 1994.
[13] Biao Zhang, Jianjun Wang, Gregory Rossano and Carlos Martinez, “Vision-Guided Robotic Assembly Using Uncalibrated Vision,” IEEE International Conference on Mechatronics and Automation, pp. 1384-1389, 2001.
[14] Chih-Hung Wu, I-Sheng Lin, Ming-Liang Wei, and Tain-Yu Cheng, “Target Position Estimation by Genetic Expression Programming for Mobile Robots with Vision Sensors,” IEEE Transcations on Instrumentation and Measurement, pp. 3218-3230, 2013.
[15] Omar Tahri, Youcef Mezouar, Franc¸ois Chaumette and Peter Corke, “Generic Decoupled Image-Based Visual Servoing for Cameras Obeying the Unified Projection Model,” IEEE Transcations on Robotics, pp. 684-697, 2010.
[16] Pierluigi Cigliano, Vincenzo Lippiello, Fabio Ruggiero and Bruno Siciliano, “Robotic Ball Catching with an Eye-in-Hand Single-Camera System,” IEEE Transcations on Control Systems Technology, pp. 1657-1671, 2015.
[17] Shouren Huang, Yuji Yamakawa, Taku Senoo and Masatoshi Ishikawa, “Realizing Peg-and-Hole Alignment with One Eye-in-Hand High-Speed Camera,” International Conference on Advanced Intelligent Mechatronics, pp. 1127-1132, 2013.
[18] Joss Knight and Ian Rfid, “Automated Alignment of Robotic Pan-Tilt Camera Units Using Vision,” International Journal of Computer Vision, pp. 219-237, 2006.
[19] Zhengke Qin, Peng Wang, Jia Sun, Jinyan Lu, and Hong Qiao, “Precise Robotic Assembly for Large-Scale Objects Based on Automatic Guidance and Alignment,” IEEE Transcations on Instrumentation and Measurement, pp. 1398-1411, 2016.
[20] Te Tang, Hsien-Chung Lin, Yu Zhao, Wenjie Chen and Masayoshi Tomizuka, “Autonomous Alignment of Peg and Hole by Force/Torque Measurement for Robotic Assembly,” IEEE International Conference on Automation Science and Engineering, pp. 162-167, 2016.
[21] Shubham Jain, Prashant Gupta and Vikash Kumar, “A Force-Controlled Portrait Drawing Robot,” IEEE International Conference on Industrial Technology, pp. 3160-3165, 2015.
[22] Zhengyou Zhang, “A Flexible New Technique for Camera Calibration,” IEEE Transcations on Pattern Analysis and Machine Intelligence, pp. 1330 -1334, 2000.
[23] David A. Forsyth and Jean Ponce, Computer Vision a Modern Approach, Pearson Education, 2003.
[24] J. Y. Bouguet, “Camera Calibration Toolbox for MATLAB,” see http://www.vision.caltech.edu/bouguetj, 2003.
[25] 施慶隆、李文猶，機電整合控制--多軸運動設計與應用，第三版，全華圖書
股份有限公司，2015。