隨著工業 4.0 與智慧製造的快速發展，越來越多機械手臂被導入生產線，進行重複性高且具精度要求之操作任務，以提升生產效率。有鑑於此，本論文提出一套整合運動規劃與力量控制之架構，可應用於機械手臂執行塗膠、焊接等任務中。本論文首先透過視覺方法擷取目標圖像之輪廓，做為運動軌跡輸入。接著，本論文提出改良式弧長動態運動原語(MAL-DMP)，除了具備軌跡模仿功能外，還透過對動態運動原語(DMP)進行弧長參數化，將運動速度從系統中分離，使得運動規劃更具彈性與直觀性，能根據需求靈活調整。在力量控制方面，提出改良之模糊適應性導納控制，透過模糊邏輯根據外力誤差及其變化率動態調整參數，不僅改善力量暫態響應並降低力量追蹤誤差，也展現良好之環境變化適應能力。進一步，本論文將該控制器與MAL-DMP整合，提出兩種力量控制架構，包含串接導納控制與使用耦合項之方式，以實現具順應性之軌跡調整。最後，透過本論文所設計的模擬與實驗，實驗結果顯示本論文所提出之方法在運動規劃與力量控制表現上皆具有效性與可行性。

With the rapid advancement of Industry 4.0 and smart manufacturing, an increasing number of robot manipulators have been introduced into production lines to perform highly repetitive and precision-demanding tasks, thereby enhancing productivity and manufacturing efficiency. In light of such demands, this thesis proposes an integrated framework combining motion planning and force control, aimed at robot manipulators applications such as glue dispensing and welding. The proposed system first employs a computer vision method to extract the contour of the target object from images, which serves as the input trajectory. Subsequently, a Modified Arc-Length Dynamic Movement Primitive (MAL-DMP) is proposed. In addition to trajectory imitation, MAL-DMP introduces arc-length parameterization to the original Dynamic Movement Primitives (DMP), enabling the decoupling of motion speed from the trajectory generation process. This enhances the flexibility and intuitiveness of motion planning, allowing dynamic adjustment according to task requirements. For force control, this thesis presents an improved fuzzy adaptive admittance control method. By using fuzzy logic to dynamically adjust controller parameters based on force error and its rate of change, the proposed method improves transient response, reduces force tracking error, and demonstrates strong adaptability to environmental variations. Moreover, the fuzzy admittance controller is integrated with the MAL-DMP framework, and two force control frameworks are proposed—one using a cascaded architecture where MAL-DMP generates the trajectory followed by admittance control, and another using coupling terms—both aiming to achieve compliant trajectory adaptation. Finally, through simulation and real-world experiments, the results confirm the effectiveness and feasibility of the proposed methods in both motion planning and force control.

[1] 2024/2025產業技術白皮書，經濟部技術處，2024。
[2] S. Schaal, P. Mohajerian, and A. Ijspeert, “Dynamics systems vs. optimal control — a unifying view,” Progress in Brain Research, pp. 425–445, Jan. 2007.
[3] A. J. Ijspeert, J. Nakanishi, H. Hoffmann, P. Pastor, and S. Schaal, “Dynamical Movement Primitives: learning attractor models for motor behaviors,” Neural Computation, vol. 25, no. 2, pp. 328–373, Nov. 2012.
[4] M. Saveriano, F. J. Abu-Dakka, A. Kramberger, and L. Peternel, “Dynamic movement primitives in robotics: A tutorial survey,” The International Journal of Robotics Research, vol. 42, no. 13, pp. 1133–1184, Sep. 2023.
[5] F. Stulp, E. A. Theodorou, and S. Schaal, “Reinforcement learning with sequences of motion primitives for robust manipulation,” IEEE Transactions on Robotics, vol. 28, no. 6, pp. 1360–1370, Sep. 2012.
[6] F. J. Abu-Dakka, B. Nemec, J. A. Jørgensen, T. R. Savarimuthu, N. Krüger, and A. Ude, “Adaptation of manipulation skills in physical contact with the environment to reference force profiles,” Autonomous Robots, vol. 39, no. 2, pp. 199–217, May 2015.
[7] O. Spector and M. Zacksenhouse, “Learning Contact-Rich assembly Skills using residual admittance policy,” in Proceedings of 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6023–6030, Sep. 2021.
[8] Y. Yuan, Z. Li, T. Zhao, and D. Gan, “DMP-Based Motion generation for a walking exoskeleton robot using reinforcement learning,” IEEE Transactions on Industrial Electronics, vol. 67, no. 5, pp. 3830–3839, May 2019.
[9] M. Ginesi, N. Sansonetto, and P. Fiorini, “Overcoming some drawbacks of Dynamic Movement Primitives,” Robotics and Autonomous Systems, vol. 144, p. 103844, Jul. 2021.
[10] N. R. Wang, Y. Wu, N. W. L. Chan, and N. K. P. Tee, “Dynamic Movement Primitives Plus: For enhanced reproduction quality and efficient trajectory modification using truncated kernels and Local Biases,” in Proceedings of 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3765–3771, Oct. 2016.
[11] A. Dahlin and Y. Karayiannidis, “Adaptive trajectory generation under velocity constraints using dynamical movement primitives,” IEEE Control Systems Letters, vol. 4, no. 2, pp. 438–443, Oct. 2019.
[12] A. Dahlin and Y. Karayiannidis, “Temporal coupling of dynamical movement primitives for constrained velocities and accelerations,” IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 2233–2239, Feb. 2021.
[13] C.-C. Huang and M.-Y. Cheng, “Contour error reduction of DMPs with time-dilation-based time scale adjustment,” in System Innovation for an Artificial Intelligence Era, CRC Press, 2024, pp. 103–107.
[14] B. Nemec, A. Gams, and A. Ude, “Velocity adaptation for self-improvement of skills learned from user demonstrations,” in Proceedings of 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids), vol. 165, pp. 423–428, Oct. 2013.
[15] A. Ude, R. Vuga, B. Nemec, and J. Morimoto, “Trajectory representation by nonlinear scaling of dynamic movement primitives,” in Proceedings of 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4728–4735, Oct. 2016.
[16] T. Gašpar, B. Nemec, J. Morimoto, and A. Ude, “Skill learning and action recognition by arc-length dynamic movement primitives,” Robotics and Autonomous Systems, vol. 100, pp. 225–235, Dec. 2017.
[17] S. Jung, T. C. Hsia, and R. G. Bonitz, “Force tracking impedance control of robot manipulators under unknown environment,” IEEE Transactions on Control Systems Technology, vol. 12, no. 3, pp. 474–483, May 2004.
[18] 王俊翔，工業用機械手臂之混合順應控制研究，碩士論文，國立成功大學，電機工程學系，2020。
[19] H. Cao, X. Chen, Y. He, and X. Zhao, “Dynamic Adaptive hybrid impedance control for dynamic contact force tracking in uncertain environments,” IEEE Access, vol. 7, pp. 83162–83174, Jan. 2019.
[20] J. Duan, Y. Gan, M. Chen, and X. Dai, “Adaptive variable impedance control for dynamic contact force tracking in uncertain environment,” Robotics and Autonomous Systems, vol. 102, pp. 54–65, Feb. 2018.
[21] Z. Li, H. Huang, X. Song, W. Xu, and B. Li, “A fuzzy adaptive admittance controller for force tracking in an uncertain contact environment,” IET Control Theory and Applications, vol. 15, no. 17, pp. 2158–2170, Aug. 2021.
[22] G. Peng, C. L. P. Chen, and C. Yang, “Neural networks Enhanced optimal admittance control of Robot–Environment interaction using reinforcement learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 9, pp. 4551–4561, Mar. 2021.
[23] Y. Li, L. Zheng, Y. Wang, E. Dong, and S. Zhang, “Impedance learning-based adaptive force tracking for robot on unknown terrains,” IEEE Transactions on Robotics, pp. 1–17, Jan. 2025.
[24] D.-H. Zhai, Z. Xia, H. Wu, and Y. Xia, “A motion planning method for robots based on DMPs and modified Obstacle-Avoiding algorithm,” IEEE Transactions on Automation Science and Engineering, vol. 20, no. 4, pp. 2678–2688, Aug. 2022.
[25] 洪瑋伶，基於動態運動原語之機械手臂軌跡命令修正研究，碩士論文，國立成功大學，電機工程學系，2023。
[26] 黃嘉浚，基於控制障礙函數之線上動態運動原語避障軌跡修正研究，碩士論文，國立成功大學，電機工程學系，2024。
[27] A. Gams, B. Nemec, A. J. Ijspeert, and A. Ude, “Coupling movement primitives: interaction with the environment and bimanual tasks,” IEEE Transactions on Robotics, vol. 30, no. 4, pp. 816–830, Feb. 2014.
[28] A. Kramberger, E. Shahriari, A. Gams, B. Nemec, A. Ude, and S. Haddadin, “Passivity Based Iterative Learning of Admittance-Coupled Dynamic Movement Primitives for Interaction with Changing Environments,” in Proceedings of 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6023–6028, Oct. 2018.
[29] L. Han, P. Kang, Y. Chen, W. Xu, and B. Li, “Trajectory Optimization and Force Control with Modified Dynamic Movement Primitives under Curved Surface Constraints,” in Proceedings of 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1065–1070, Dec. 2019.
[30] L. Han, H. Yuan, W. Xu, and Y. Huang, “Modified Dynamic Movement primitives: robot trajectory planning and force control under curved surface constraints,” IEEE Transactions on Cybernetics, vol. 53, no. 7, pp. 4245–4258, Mar. 2022.
[31] R. Keating and N. J. Cowan, “UR5 Inverse Kinematics,” unpublished, Johns Hopkins University, 2016. https://tianyusong.com/wpcontent/uploads/2017/12/ur5_inverse_kinematics.pdf.
[32] K. S. Arun, T. S. Huang, and S. D. Blostein, “Least-Squares fitting of two 3-D point sets,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-9, no. 5, pp. 698–700, Sep. 1987.
[33] N. Ravi et al., “SAM 2: Segment anything in images and videos,” 2024, arXiv:2408.00714.