隨著自動化產業的發展，一種新的工業模式誕生了，傳統的人力資源逐漸被機器所取代。世界經濟論壇（WEF）在“2018年就業未來報告”中指出，世界正在經歷一場「職場革命」，這意味著機器將在未來發揮更重要的作用。為了因應上述的情況，這篇論文主要將情境限縮在輸送帶的生產線上，目的在開發一款應用於產線升級的關鍵系統裝置，透過此裝置可使產線機器人聰明自主的夾取並分類物件。為達成智慧夾爪系統之核心目標，此嵌入式視覺自適應夾爪，結合了夾爪與相機感測器在同一個模組當中，這讓夾爪不是瞎子摸象，而是簡單的辨識物體的形狀、方位與位置，再透過正逆向運動學，進行抓取作業。
在本研究中，提出及驗證了使用嵌入式視覺自適應夾爪系統在輸送機上進行物體識別和追蹤的方法，這些方法主要應用在需要自動分類物體的生產線上。由於相機坐標與夾爪坐標相同，因此本研究所提出的嵌入式電腦視覺系統(eye-in-hand)提供以下優勢：（1）避免遮擋（2）直觀地操作（3）能獲得不同角度的圖像（4）更容易校準相機。同時，當相機太靠近物體時，本研究所提出的方法也能透過嵌入式電腦視覺系統(eye-in-hand)的配置，解決物體超出視野外的問題。此外，在這項研究中，亦建立嵌入式視覺自適應夾爪所需之追蹤演算法。結果指出，經過一段時間後，整體系統可精準地計算並預測輸送帶等速運作的速度，並使機器人和物體之間的跟蹤誤差在誤差可容忍的範圍內。

With the development of Automation industry, a new industrial model has been born, and traditional human resources have gradually been replaced by machines. The World Economic Forum (WEF) pointed out in “The Future of Jobs Report 2018” that the world is experiencing a "workplace revolution", which means that machine will play a more important role in the future. In response to this situation, in this research, methods and systems for object recognition and tracking on a conveyor using eye-in-hand gripper are proposed and validated, which are useful in production line for automatic object classification. The proposed eye-in-hand configuration is the most suitable for camera and gripper application because the camera coordinate is the same as the gripper coordinate. The main advantages of the eye-in-hand configuration addressed in this research are as follow: (1) occlusion avoidance (2) intuitive teleoperation (3) image from different angles (4) simple calibration. The proposed method resolves the out of view sight problem with eye-on-hand configuration when the camera is too close to the object. In this research, the eye-in-hand robotic gripper is established and integrated with a tracking system to chase target object. Results show that the speed of the conveyor can be calculated and predicted by the system. The tracking error between the robot and the object is found to be small within tolerance after a period of time.

[1]W.-C. Chang, "Robotic assembly of smartphone back shells with eye-in-hand visual servoing," Robotics and Computer-Integrated Manufacturing, vol. 50, pp. 102-113, 2018.
[2]J. Pomares, I. Perea, G. J. García, C. A. Jara, J. A. Corrales, and F. Torres, "A multi-sensorial hybrid control for robotic manipulation in human-robot workspaces," Sensors, vol. 11, no. 10, pp. 9839-9862, 2011.
[3]P. Cigliano, V. Lippiello, F. Ruggiero, and B. Siciliano, "Robotic Ball Catching with an Eye-in-Hand Single-Camera System," IEEE Transactions on Control Systems Technology, vol. 23, no. 5, pp. 1657-1671, 2015.
[4]R. Barth, J. Hemming, and E. J. van Henten, "Design of an eye-in-hand sensing and servo control framework for harvesting robotics in dense vegetation," Biosystems Engineering, vol. 146, pp. 71-84, 2016/06/01/ 2016.
[5]H. Wang, D. Guo, H. Xu, W. Chen, T. Liu, and K. K. Leang, "Eye-in-hand tracking control of a free-floating space manipulator," IEEE Transactions on Aerospace and Electronic Systems, vol. 53, no. 4, pp. 1855-1865, 2017.
[6]P. R. Florence, L. Manuelli, and R. Tedrake, "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation," arXiv preprint arXiv:1806.08756, 2018.
[7]S. Yu, J. Lee, B. Park, and K. Kim, "Design of a gripper system for tendon-driven telemanipulators considering semi-automatic spring mechanism and eye-in-hand camera system," Journal of Mechanical Science and Technology, vol. 31, no. 3, pp. 1437-1446, 2017.
[8]C.-L. Shih and Y. Lee, "A Simple Robotic Eye-In-Hand Camera Positioning and Alignment Control Method Based on Parallelogram Features," Robotics, vol. 7, no. 2, p. 31, 2018.
[9]ROBOTIQ. Wrist Camera. Available: https://robotiq.com/products/wrist-camera?ref=nav_product_new_button
[10]FESTO. ExoHand. Available: https://www.festo.com/group/en/cms/10233.htm
[11]E. Brown et al., "Universal robotic gripper based on the jamming of granular material," Proceedings of the National Academy of Sciences, vol. 107, no. 44, pp. 18809-18814, 2010.
[12]K. Hsiao, P. Nangeroni, M. Huber, A. Saxena, and A. Y. Ng, "Reactive grasping using optical proximity sensors," in Robotics and Automation, 2009. ICRA'09. IEEE International Conference on, 2009, pp. 2098-2105: IEEE.
[13]ROBOTIQ. 3-Finger Adaptive Robot Gripper. Available: https://robotiq.com/products/3-finger-adaptive-robot-gripper?301=%2Fproducts%2Findustrial-robot-hand%2F
[14]Z. Zhang, "A flexible new technique for camera calibration," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1330-1334, 2000.
[15]N. Otsu, "A threshold selection method from gray-level histograms," IEEE transactions on systems, man, and cybernetics, vol. 9, no. 1, pp. 62-66, 1979.
[16]Wikipedia. HSL和HSV色彩空間. Available: https://zh.wikipedia.org/wiki/HSL%E5%92%8CHSV%E8%89%B2%E5%BD%A9%E7%A9%BA%E9%97%B4
[17]OpenCV. Canny Edge Detection. Available: https://docs.opencv.org/3.1.0/da/d22/tutorial_py_canny.html
[18]L. A. Cheng and J. J. Chang, "Design of a Multiple Degrees of Freedom Robotic Gripper for Adaptive Compliant Actuation," in 2018 International Conference on System Science and Engineering (ICSSE), 2018, pp. 1-6.
[19]OpenCV. Camera Calibration. Available: https://docs.opencv.org/3.4/dc/dbb/tutorial_py_calibration.html
[20]R. S. Andersen, "Kinematics of a UR5," 2018.