移動式機械手臂主要由移動平台、機械手臂及視覺系統所組成，是一套具彈性的搬運系統，相當適合使用於少量多樣的生產線上。其不僅節省人力，在工件運送及上下料亦提供高可靠度與效率。

　　移動式機械手臂往來各工作站搬運物料時，移動平台利用其導航控制系統將機械手臂驅動至各工作站，由於移動平台的定位誤差與地面不平坦等因素，移動式機械手臂到站後，移動平台與工作站之間，有著無法避免的位置與方位誤差。因此，本研究使用一未經校準之眼在手視覺系統，在不需特殊打光的條件下，提出以視覺導引，行為基礎看而後動的控制策略，提供影像資訊引導機械手臂抓取放置在工作平台上的工件。值得注意的是，在此不需要估測出工件相對於機械手臂端接器的姿態，或是影像特徵變化量與端接器位移量的關係。在所設計的類神經模糊控制器中，此控制策略使用事先定義的六個影像特徵。每一影像特徵透過模糊規則直覺式地決定相對於攝影機座標的一個自由度運動，此即所設計之行為。這些行為經過整合便可執行機械手臂之夾取任務。

　　在論文最後，使用所提出的控制策略引導機械手臂之端接器，接近並抓取工作站上不同位置與方位的工件。實驗結果顯示，機械手臂能夠在不平坦地面以及無特殊打光的情形下，精確抓取視覺系統視野內的工件。即使端接器逼近工件的過程中，工件在視野內稍微改變了位置和方位，最終仍然可以正確地抓取。

　A mobile manipulator mainly consists of a mobile base, a robot manipulator and a vision system. It is a flexible material transferring system, which is suitable for production lines with small sorts of products in large quantities. This flexible material transfer system can save human resources, and provide reliable and efficient transportation and handling.

　During pick-and-place operations between stations, a mobile manipulator is controlled to reach a station by guidance control system of the mobile base. Positioning errors of the mobile base and the non-horizontality of ground inevitably cause position and orientation errors of the mobile base relative to the station. Therefore, this study employs an uncalibrated eye-in-hand vision system to provide visual information for controlling the manipulator to pick up a workpiece located on the station. A vision-guided control strategy with a behavior-based look-and-move structure without any special lighting is proposed. Notably, the pose of the workpiece in relation to the end-effector of the manipulator is never numerically estimated. Also, the relationships between the deviations of the image features and the displacements of the end-effector are never determined. This strategy is based on six predefined image features. In the designed neural fuzzy controllers, each image feature is taken to generate intuitively
one DOF motion command relative to the camera coordinate frame using fuzzy rules, which define a specific visual behavior. These behaviors are then combined and executed in turns to perform grasping tasks.

　The end-effector of the manipulator is experimentally controlled to approach and grasp the workpiece in various locations on the station following the proposed control strategy. The experimental data indicate that the manipulator can grasp the workpiece in the field of view on non-planar ground without any special illumination. Even if the position and orientation of the workpiece are somewhat changed during the approach , the grasping can be completed without loss.

[1]. A. Anglani, F. Taurisano, R. De Giuseppe and C. Distante, “Learning to Grasp by using Visual Information,” Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and Automation, pp.7-14, Nov. 1999.
[2]. Z. Bien and J. Park, “Hybrid Fuzzy Self-Organizing Controller for Visual Tracking,” Fuzzy Logic: State of the Art, Kluwer Academic Publishes, 1993.
[3]. C. J. Chang, “Pose Control of Mobile Manipulators with an Uncalibrated Eye-in-Hand vision System,” M. S. Thesis, Department of Mechanical Engineering, National Cheng Kung University, R. O. C., 2003.
[4]. R. D. Giuseppe, F. Taurisano, C. Distante and A. Anglani, “Visual Servoing of a Robotic Manipulator Based on Fuzzy Logic Control,” Proceedings of the IEEE International Conference on Robotics and Automation, Vol. 2, pp.1487-1494, May 1999.
[5]. S. Hutchinson, G. D, Hager and P. I. Corke, “A Tutorial on Visual Servo Control,” IEEE Transaction on Robotics and Automation, Vol. 12, No. 5, pp.651-670, Oct. 1996.
[6]. S. H. Han, W. H. Seo, S. Y. Lee, S. H. Lee, H. W. Lee and H. Toshiro, “A Study on Real-Time Implementation of Visual Feedback Control for Robot Manipulator,” Proceedings of the IEEE International Conference on System Man and Cybernetics, Vol. 2, pp.824-829, Oct. 1999.
[7]. J. G. Kim, D. H. Cha, H. S. Cho and S. H. Kim, ”An Auto Tuning Fuzzy Rule-Based Visual Servoing Algorithm for a Slave Arm,” Proceedings of the IEEE International Symposium on Intelligent Control, pp.177-182, Aug. 1995.
[8]. R. Kelly, R. Carelli, O. Nasisi, B. Kuchen and F. Reyes, “Stable Visual Servoing of Camera-in-Hand Robotics Systems,” IEEE/ASME Transactions on Mechatronics, Vol. 5, No. 1, pp39-48, Mar. 2000.
[9]. C. S. Kim, W. H. Seo, S. H. Han and O. Khatib, “Fuzzy Logic Control of a Robot Manipulator Based on Visual Servoing,” Proceedings of the IEEE International Symposium on Industrial Electronics, Vol. 3, pp.1597-1602, June 2001.
[10]. C. T. Lin and G. Lee, Neural Fuzzy Systems: A Neural-Fuzzy Synergism to Intelligent Systems, Upper Saddle River, NJ: Prentice Hall PTR, 1996.
[11]. R. X. Lin, “Development of a Mobile Robot for Vision Guided Material Handling,” M. S. Thesis, Department of Mechanical Engineering, National Cheng Kung University, R. O. C., 2001.
[12]. H. Nomura, I. Hayashi and Noboru Wakami, “A Learning Method of Fuzzy Inference Rules by Descent Method,” Proceedings of the IEEE International Conference on Fuzzy Systems, pp.203-210, Mar. 1992.
[13]. A. C. Sanderson and L. E. Weiss, “Image-Based Visual Servo Control using Relational Graph Error Signals,” Proceedings of the IEEE International Conference on Cybernetics and Society, pp.1074-1077, 1980.
[14]. R. J. Schilling, “Fundamental of Robotics,” USA, Prentice Hall, 1990.
[15]. I. H. Suh, T. W. Kim, S. Heu and S. K. Oh, ”Visual Servoing by a Fuzzy Reasoning Method,” IEEE/RSJ International Workshop on Intelligent Robots and Systems, pp.111-116, Nov. 1991.
[16]. A. Schrott, “Feature-Based Camera-Guided Grasping by an Eye-in-Hand Robot,” Proceedings of the IEEE International Conference on Robotics and Automation, pp.1832-1837, May 1992.
[17]. I. H. Suh and T. W. Kim, “Fuzzy Membership Function Based Neural Networks with Applications to the Visual Servoing of robot Manipulators,” IEEE Transactions on Fuzzy Systems, Vol. 2, No. 3, pp.203-220, Aug. 1994.
[18]. I. H. Suh and T. W. Kim, “A Fuzzy-Neural-Network-Based Visual Feedback Learning Control for Robot Manipulators,” Proceedings of the IEEE International Conference on Computation Intelligence, Vol. 5, No. 27, pp.2781-2786, July 1994.
[19]. I. H. Suh and T. W. Kim, “A Visual Servoing Algorithm using Fuzzy Logics and Fuzzy-Neural Networks,” Proceedings of the IEEE International Conference on Robotics and Automation, pp.3605-3612, April 1996.
[20]. Z. Wasik and A. Saffiotti, “A Fuzzy Behavior-Based Control System for Manipulation,” Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.1596-1601, Oct. 2002.
[21]. Z. Wasik and A. Saffiotti, “A Hierarchical Behavior-Based Approach to Manipulation Tasks,” Proceedings of the IEEE International Conference on Robots and Automation, pp.2780-2785, Set. 2003.
[22]. Y. Ting, Y. H. Chen, M. Lin, S. C. Dai and Y. Kang, “A Study on the Inaccuracy of Vision Systems of Mobile Robots Causing the Failure of Pick-and-Place Tasks,” Proceedings of the Florida Conference on Recent Advances in Robotics, pp.43-46, Apr. 1997.