在現代工業4.0的背景下，智慧自動化生產已成為提升生產效率和降低成本的關鍵。自主移動機器人(AMR, Autonomous Mobile Robot)在自動化物料搬運中扮演著重要角色，特別是在勞動力短缺和成本壓力增大的情況下，AMR的靈活性可以顯著提高物料運輸效率。然而，如何在多任務負荷下同時管理 AMR的派工與充電管理機制，以確保高效的生產運作，成為一項挑戰。
本研究運用FlexSim系統模擬軟體，結合基因演算法(GA, Genetic Algorithm)，建立一套決策模型來優化AMR派工法則並於既定門檻式充電管理機制下評估系統績效。模型根據 AMR的電量狀況、任務位置距離及閒置時間，計算加權綜合評分以選擇最適合的車輛執行任務，同時在電量不足時優先進行充電，以避免任務中斷。本研究透過基因演算法調整評分權重參數，可找出在不同環境條件下的最佳組合，使模型具備適應能力。
實驗結果表明，本研究所建立的最佳化模型能有效減少AMR的充電等待時間，進而縮短任務總完工時間，達到最佳的產能配置。在多個模擬場景下，該模型顯示出其在不同環境中調整AMR派工的能力，為智慧工廠的運作提供了實用的解決方案。

Driven by the development of Industry 4.0, intelligent manufacturing has become essential for improving production efficiency and reducing operational costs. Autonomous Mobile Robots (AMRs) play an important role in automated material handling systems, especially under conditions of labor shortages and rising cost pressures. However, managing AMR dispatching and charging management simultaneously under multiple task loads remains a significant challenge for maintaining overall productivity.
To address this issue, this study emphasizes the joint consideration of task assignment and energy availability, since battery-related decisions can directly influence congestion and system stability. It further evaluates the proposed approach under different workload and fleet-size conditions to support practical deployment decisions.
This study integrates the FlexSim system simulation software with a Genetic Algorithm (GA) to develop an optimization model for AMR dispatching rules and charging management. The model calculates a weighted composite score based on factors such as AMR battery level, task distance, and idle time to determine the most suitable robot for each task, while prioritizing charging when the battery level is insufficient. The GA is applied to optimize the weighting parameters and identify the best combinations under various operating conditions, thereby enhancing the model’s adaptability to dynamic production environments.
Experimental results show that the proposed model effectively improves AMR operational efficiency, reduces charging waiting time, and achieves better production capacity allocation. These findings demonstrate that the model provides a practical and adaptive solution for AMR scheduling and energy management in smart factory operations.

許雅婷。（2020）。AGV最佳車數研究—以IC封裝廠為例（碩士論文）。國立清華大學，全球營運管理碩士雙聯學位學程。
林政宏。（2022）。應用系統模擬於工廠AGV需求分析以線纜工廠為例（碩士論文）。國立中原大學，工業與系統工程學系。
黃政傑。（2021）。利用模擬最佳化演算法求解有限成本及空間限制下機台選擇及緩衝區配置問題（碩士論文）。國立清華大學，工業工程與工業管理學系。
楊廣宜。（2002）。以基因演算法結合離散事件模擬求解最佳CONWIP生產架構（碩士論文）。國立成功大學，製造工程研究所。
吳昇峰。（2019）。結合ARENA軟體與資料包絡分析法評估生產流程中AGV數量（碩士論文）。國立高雄科技大學，工業工程與管理系。
Chen, J. C., Chen, T.-L., & Teng, Y.-C. (2021). Meta-model based simulation optimization for automated guided vehicle system under different charging mechanisms. Simulation Modelling Practice and Theory, 106, 102208.
Deb, K. (2001). Multi-objective optimization using evolutionary algorithms. Wiley.
Egbelu, P. J., & Tanchoco, J. M. A. (1984). Characterization of automatic guided vehicle dispatching rules. International Journal of Production Research, 22(3), 359–374.
Eiben, A. E., & Smith, J. E. (2003). Introduction to evolutionary computing. Springer.
Ghosh, J. B. (2016). Simulation-based optimization of material handling systems in manufacturing and distribution. Simulation Modelling Practice and Theory, 60, 66–76.
Kabir, Q. S., & Suzuki, Y. (2018). Increasing manufacturing flexibility through battery management of automated guided vehicles. Computers & Industrial Engineering, 117, 225–236.
Li, J., Cheng, W., Lai, K. K., & Ram, B. (2022). Multi-AGV flexible manufacturing cell scheduling considering charging. Mathematics, 10(19), 3417.
Li, X., Wang, L., & Zhu, X. (2021). Simulation and optimization of automated warehouse based on FlexSim. In S. Liu, G. Bohács, X. Shi, X. Shang, & A. Huang (Eds.), LISS 2020 (pp. 245–261). Springer.
Lo Iudice, F., Olm, J. M., & Suárez, R. (2024). Optimal recharge sequencing in multi-AGV systems: A mixed ILP approach. Computers & Industrial Engineering, 196, 110510.
Schmidt, J., Meyer-Barlag, C., Eisel, M., Kolbe, L. M., & Appelrath, H.-J. (2015). Using battery-electric AGVs in container terminals: Assessing the potential and optimizing the economic viability. Research in Transportation Business & Management, 17, 99–111.
Singh, N., Akcay, A., Dang, V., Martagan, T., & Adan, I. (2024). Dispatching AGVs with battery constraints using deep reinforcement learning. Computers & Industrial Engineering, 187, 109678.
Umar, U. A., Ariffin, M. K. A., Ismail, N., & Tang, S. H. (2015). Hybrid multiobjective genetic algorithms for integrated dynamic scheduling and routing of jobs and automated-guided vehicle (AGV) in flexible manufacturing systems (FMS) environment. The International Journal of Advanced Manufacturing Technology, 81, 2123–2141.
Zhong, M., Yang, Y., Dessouky, Y., & Postolache, O. (2020). Multi-AGV scheduling for conflict-free path planning in automated container terminals. Computers & Industrial Engineering, 142, 106371.