隨著自動化技術日益成熟，使用機械手臂作為生產製造工具已是大勢所趨。然而機械手臂在執行任務時，難免會出現不可預期的障礙物，必須規劃適當的避障路徑。本論文針對此一問題，發展一結合 S-curve 與人工勢場法之機械手臂避障路徑規劃方法。首先利用 S-curve 產生一條由起始點至目標點的命令路徑，若所產生的命令路徑十分接近障礙物，則使用人工勢場法來作靜態障礙物的避障。然而使用傳統人工勢場法在障礙物離目標點很近的情境下，可能導致機械手臂在目標點附近來回移動而無法抵達目標點。為避免上述情況，本論文使用兩種方法：第一種方法是在斥力位能中增添與目標點距離項之改良式卡式空間人工勢場法，第二種方法為在軌跡規劃過程中不需計算逆向運動學之關節空間人工勢場法。本論文以KUKA youBot 為實驗平台，驗證所提方法之可行性。實驗結果顯示，不論是使用 S-curve 結合改良式卡式空間人工勢場法或是使用 S-curve 結合關節空間人工勢場法，機械手臂均可成功避障，順利到達目標點。

As the automation technologies gradually maturing, it becomes a trend to use robot manipulators as production/manufacturing tools. However, when a robot manipulator executes tasks, obstacles may appear accidently. Proper trajectory planning must be performed to avoid collision with the obstacle. To cope with the aforementioned problem, this paper develops an obstacle avoidance approach for robot manipulators based on S-curve and artificial potential field. In particular, the S-curve method is used to generate a command path from the initial point to the target point. If the generated command trajectory is close to the obstacles, then the artificial potential field method is employed to perform static object collision avoidance. However, for the scenario that the obstacles are close to the target point, conventional artificial potential field methods may result in a problem that the robot manipulator may wander around the target point. To prevent from the aforementioned situation, this thesis uses two approaches: the first one is the modified cartesian space artificial potential field method, in which the repulsive force field is added a term related to the distance between the target point and the obstacles; the second one is the joint space artificial potential field method, in which the calculation of inverse kinematics is not essential during the trajectory planning process. A KUKA youBot is used as the experimental platform to verify the effectiveness of the proposed approach. Experimental results indicate that, either using the S-curve combined with the modified cartesian space artificial potential field method or using the S-curve combined with the joint space artificial potential field method, the robot manipulator can avoid obstacles and successfully reach the target point.

[1]STARSHIP, “Starship Launches in Finland – Partners First with Leading Retail Operator HOK-Elanto Group,” 2022. [Online]. Available: https://www.starship.xyz/press_releases/starship-launches-robot-grocery-delivery-services-in-finland-partners-first-with-a-leading-retail-operator-hok-elanto-group/
[2]Brain Navi, “Our robots,” 2022. [Online]. Available: https://brainnavi.com/
[3]A. Shahzad, X. Gao, A. Yasin, K. Javed and S. M. Anwar, “A Vision-Based Path Planning and Object Tracking Framework for 6-DOF Robotic Manipulator,” IEEE Access, vol. 8, pp. 203158-203167, 2020.
[4]M. Wermelinger, R. Johns, F. Gramazio, M. Kohler and M. Hutter, “Grasping and Object Reorientation for Autonomous Construction of Stone Structures,” IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5105-5112, July. 2021.
[5]O. Khatib, “Real-time Obstacle Avoidance for Manipulators and Mobile Robots,” in Proc. IEEE International Conference on Robotics and Automation, St. Louis, MO, USA , 25-28 May 1985, pp. 500-505.
[6]X. Wang, J. Wang, P. Cao and Y. Yang, “Research on Obstacle Avoidance Strategy and Method of UR Manipulator,” in Proc. 2021 International Conference on Communications, Information System and Computer Engineering (CISCE), Beijing, China, 14-16 May 2021, pp. 204-208.
[7]N. Baba and N. Kubota, “Collision Avoidance Planning of a Robot Manipulator by Using Genetic Algorithm. A Consideration for the Problem in Which Moving Obstacles and/or Several Robots Are Included in the Workspace,” in Proc. 1st IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence, Orlando, FL, USA , 27-29 June, 1994, vol.2, pp. 714-719.
[8]L.P. Xi, Z.L. Chen and S.J. Sun, “Obstacle Avoiding Research on the Manipulator Based on Genetic Algorithm,” in Proc. 2011 1st International Conference on Instrumentation, Measurement, Computer, Communication and Control, Beijing, China, 21-23 October, 2011, pp. 865-867.
[9]B. Sangiovanni, G.P. Incremona, M. Piastra and A. Ferrara, “Self-Configuring Robot Path Planning With Obstacle Avoidance via Deep Reinforcement Learning,” IEEE Control Systems Letters, vol. 5, no. 2, pp. 397-402, April 2021.
[10]S. Du, W. Shang, S. Cong, C. Zhang and K. Liu, “Moving Obstacle Avoidance of a 5-DOF Robot Manipulator by Using Repulsive Vector,” in Proc. 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), Macau, Macao, 05-08 December 2017, pp. 688-693.
[11]N. Wan, D. Xu and H. Ye, “Improved Cubic B-spline Curve Method for Path Optimization of Manipulator Obstacle Avoidance,” in Proc. 2018 Chinese Automation Congress (CAC), Xi'an, China, 30 November-02 December 2018, pp. 1471-1476.
[12] S. Sabarigirish and S.J. Mija, “Obstacle Avoiding Trajectory Planning for 5 Degree of Freedom Robot,” in Proc. 2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), Delhi, India, 04-06 July 2016, pp. 1-5.
[13]W.R. Wang, M.C. Zhu, X.M. Wang, S.A. He, J.P. He, Z.B. Xu, “An Improved Artificial Potential Field Method of Trajectory Planning and Obstacle Avoidance for Redundant Manipulators,” International Journal of Advanced Robotic Systems, vol. 15, no. 5, September 2018.
[14] H. An, J. Hu and P. Lou, “Obstacle Avoidance Path Planning Based on Improved APF and RRT,” in Proc. 2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), Changsha, China , 26-28 March 2021, pp. 1028-1032.
[15]M.H.R. Seyyed, K.S. Arun, J. Wang and X. Liu, “Obstacle Avoidance of Mobile Robots Using Modified Artificial Potential Field Algorithm,” EURASIP Journal on Wireless Communications and Networking, vol. 2019, March 2019.
[16]youBot store GmbH, “Main Page,” 2015. [Online]. Available: http://www.youbot-store.com/wiki/index.php/Main_Page.
[17]ROS, “Documentation – ROS Wiki,” 2011. [Online]. Available: http://wiki.ros.org/
[18]巴布羅，應用於多面物體自動夾取之基於 Kinect 即時三維點雲處理研究，碩士論文，國立成功大學，電機工程學系，台灣，2016。
[19]林彥如，基於演化式演算法與非對稱S-curve之工業用機械手臂運動規劃研究，碩士論文，國立成功大學，電機工程學系，台灣，2021。
[20]S. Sharma, G.K. Kraetzschmar, C. Scheurer and R. Bischoff, "Unified Closed Form Inverse Kinematics for the KUKA youBot," in Proc. ROBOTIK 2012, 7th German Conference on Robotics, Munich, Germany, 21-22 May 2012, pp. 1-6.
[21]黃俊龍，在輪廓誤差與物理限制下之一種基於演化式計算之機械手臂運動規劃研究，碩士論文，國立成功大學，電機工程學系，台灣，2020。
[22] N. Zhang, Y. Zhang, C. Ma and B. Wang, “Path Planning of six-DOF Serial Robots Based on Improved Artificial Potential Field Method,” in Proc. 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), Macau, Macao, 05-08 Dec. 2017, pp. 617-621.
[23]Lingzhu Xiang, “OpenKinect/libfreenect2,” 2020. [Online]. Available: https://github.com/OpenKinect/libfreenect2
[24]Arghya Chatterjee, “Microsoft-Kinect-v2-SDK-Installation-ROS-Wrapper-and-Rtabmap-on-Ubuntu-18.04,” 2022. [Online]. Available: https://github.com/ArghyaChatterjee/SDK-Installation-ROS-Wrapper-for-Kinect-v2-on-Ubuntu-18.04
[25]penny4860, “Retinanet-digit-detector,” 2019. [Online]. Available: https://github.com/penny4860/retinanet-digit-detector
[26]陳亞伶，基於電腦視覺與深度增強式學習之工業用機械手臂物件取放任務研究，碩士論文，國立成功大學，電機工程學系，台灣，2021。
[27]ROS, “Distribution – ROS Wiki,” 2021. [Online]. Available: http://wiki.ros.org/Distributions
[28]D. Shen, W. Niu, J. Liu, H. Li, C. Tan, Y. Xue, Y. Sun, “Obstacle Avoidance Path Planning for Double Manipulators Based on Improved Artificial Potential Field Method,” in Proc. ICITEE-2019: 2nd International Conference on Information Technologies and Electrical Engineering, Zhuzhou Hunan China, 06-07 December 2019, No. 50, pp. 1-5.
[29] J. Zhao, Q. Zhao, J. Wang, X. Zhang and Y. Wang, "Path Planning and Evaluation for Obstacle Avoidance of Manipulator Based on Improved Artificial Potential Field and Danger Field," in Proc. 2021 33rd Chinese Control and Decision Conference (CCDC), 22-24 May 2021, pp. 3018-3025