在傳統製造業數位化轉型的浪潮中，產線中工業機械臂的佈局與運動規劃已成為制約生產週期的關鍵瓶頸。許多中小型製造公司長期面臨新產品產線開發週期長、成本高的行業困境，工程師需耗費數周甚至數月時間，反復調試機械臂的基座擺放位置與運動軌跡參數，而製造業的客制化生產需求高，需頻繁重新佈置產綫，並且，如西門子等工業軟體的高昂購置成本，讓中小型公司無法負擔，進一步加劇了智慧化轉型的難度。
本研究針對這一行業痛點，基於 Unity 平臺開發了一款人機協同式機械臂佈局優化決策系統，使用者可自由選擇路徑生成的評判標準（路徑最短模式或時間最優模式）。系統底層實作了嚴密的階層式物理約束過濾，能極速排除無效空間並生成無碰撞的平滑軌跡，同時，本系統將複雜的高維空間搜尋問題進行解耦，透過分數快取字典引擎與三態視覺化元件，為使用者提供直觀的視覺引導，進而實現即時且流暢的人機協同互動。本系統支持用戶實時調整基座位置並能即時獲取性能評分建議，以輔助使用者優化調整機械臂基座位置，最終實現產線設計效率與產品生產週期效率雙躍升的效果。

Amid the wave of digital transformation in traditional manufacturing, the layout and motion planning of industrial robotic arms in production lines have emerged as a critical bottleneck constraining production cycles. Many small and medium-sized enterprises (SMEs) have long been confronted with the industry dilemma of protracted development cycles and high costs for new product lines. Engineers often spend weeks or even months repeatedly fine-tuning the base placement and motion trajectory parameters of robotic arms. Furthermore, the high demand for customized manufacturing requires frequent reconfiguration of production lines. The prohibitive acquisition costs of commercial industrial software (e.g., Siemens) place a heavy financial burden on SMEs, further exacerbating the challenges of intelligent transformation.
To address these industry pain points, this research developed a human-machine collaborative decision support system for robotic arm layout optimization based on the Unity platform. Users can freely select the evaluation criteria for path generation (Shortest Path Mode or Time-Optimal Mode). The underlying architecture implements rigorous hierarchical physical constraint filtering, enabling the rapid elimination of invalid spatial configurations and the generation of collision-free, smooth trajectories. Simultaneously, the system decouples complex high-dimensional spatial search problems; through a score caching dictionary engine and tri-state visualization components, it provides users with intuitive visual guidance, thereby achieving real-time and fluent human-machine collaborative interaction. The system allows users to adjust the base position dynamically and instantly obtain performance scoring recommendations to assist in optimizing the base placement. Ultimately, this achieves a dual leap in both production line design efficiency and product production cycle efficiency.

[1] Dijkstra, Edsger W.. “A note on two problems in connexion with graphs.” Numerische Mathematik 1 (1959): 269-271.
[2] Hart, Peter E., Nils J. Nilsson, and Bertram Raphael. "A formal basis for the heuristic determination of minimum cost paths." IEEE transactions on Systems Science and Cybernetics 4.2 (1968): 100-107.
[3] LaValle, Steven M.. “Rapidly-exploring random trees : a new tool for path planning.” The annual research report (1998).
[4] Noreen, Iram, Amna Khan, and Zulfiqar Habib. "Optimal path planning using RRT* based approaches: a survey and future directions." International Journal of Advanced Computer Science and Applications 7.11 (2016): 97-107.
[5] Gottschalk, Stefan, Ming C. Lin, and Dinesh Manocha. "OBBTree: A hierarchical structure for rapid interference detection." Proceedings of the 23rd annual conference on Computer graphics and interactive techniques. 1996.
[6] Sandakalum, Thushara, and Marcelo H. Ang Jr. "Motion planning for mobile manipulators—a systematic review." Machines, 10.2 (2022): 97.
[7] Craig, John J. Introduction to robotics: mechanics and control, 3/E. Pearson Education India, 2009.
[8] LaValle, Steven M. Planning algorithms. Cambridge university press, 2006.
[9] Jiao, Jile, et al. "Bezier curve based path planning for a mobile manipulator in unknown environments." 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO). IEEE, 2013.
[10] Khatib, Oussama. "Real-time obstacle avoidance for manipulators and mobile robots." Proceedings. 1985 IEEE international conference on robotics and automation. Vol. 2. IEEE, 1985.
[11] Rimon, Elon. Exact robot navigation using artificial potential functions. Yale University, 1990.
[12] Spensieri, Domenico, et al. "Optimal robot placement for tasks execution." Procedia Cirp, 44 (2016): 395-400.
[13] Diankov, Rosen. Automated construction of robotic manipulation programs. Diss. Carnegie Mellon University, USA, 2010.
[14] N. Vahrenkamp, T. Asfour, and R. Dillmann, "Robot placement based on reachability inversion," Proceedings of 2013 IEEE International Conference on Robotics and Automation, 2013: IEEE, pp. 1970-1975.
[15] Paus, Fabian, et al. "A combined approach for robot placement and coverage path planning for mobile manipulation." Proceedings of 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, 2017.
[16] Yamaha Motor Co., Ltd., "水平多關節機器人高性價比機型 YK-XE,"[Online]. Available: https://global.yamaha-motor.com/business/robot_tw/ykx/yk-xe/.[Accessed: 05-Apr-2026].
[17] Sharma, Ajit, Philip Zanotti, and Laxmi P. Musunur. "Drive through robotics: Robotic automation for last mile distribution of food and essentials during pandemics." IEEE Access, 8 (2020): 127190-127219.
[18] XXX已失联, " V-rep學習筆記：機器人路徑規劃1,"Jan. 19, 2017. [Online]. Available: https://www.cnblogs.com/21207- iHome/p/6049259.html.[Accessed: 06-Apr-2026].
[19] 算法市集, " 碰撞檢測算法之包圍形法," May 3, 2022. [Online]. Available: https://zhuanlan.zhihu.com/p/508757803.[Accessed: 06-Apr-2026].
[20] -點燈-, " ROS：一種路徑優化方法-拉直法," Sep. 15, 2020. [Online]. Available: https://blog.csdn.net/qq_14977553/article/details/108600434. [Accessed: 06-Apr-2026].