先前的研究提出了許多室內火災逃生方法來協助受困者逃生。貪婪的方法是尋找最近的出口並設法為受困者提供最短的疏散路徑。但是,這種方法太耗時而無法因應動態火勢蔓延。最佳化的方法使用隨機採樣演算法或萬有引力模型根據室內火災的特徵尋找逃生出口和路線。但是,這種方法有著運算量龐大的缺點。與以前的方法相比,本研究提供了一個結合輕量級的逃生出口決策公式與動態路徑規劃的逃生演算法。實驗結果表明,本論文提出的方法與 Force 和SCDER 方法相比,我們的方法將逃生路徑的計算時間加速了約 1.5 倍,並且我們的方法於實驗場景實現了高於 90%的受困者逃生率。

Numerous methods of indoor fire escape evacuation have been proposed to assist victims in escape. Greedy approaches focus on finding the closest exit and providing the victim with the shortest evacuation path. However, they are too time-consuming to respond to dynamic fire spread. Optimal approaches determine evacuation exits and routes based on the characteristics of indoor fires using probabilistic algorithms or gravitational models. However, their disadvantage is excessive amount of computation. In comparison to previous methods, this study provides a lightweight exit decision formulation paired with dynamic path planning. The experimental results indicate that our approach speedups the computation time around 1.5 times and achieves the victim survival rate higher than 90%.

[1] 中華民國內政部消防署，「109年全國火災統計分析」，2021。
[2] 高雄市鹽埕區城中城火災事件之行政調查報告，2021。
[3] 林金宏，「活著離開3」，雙葉書廊，台灣，2018。
[4] Structural Firefighting： Strategy and Tactics. 2. USA： NFPA, 2008.
[5] Kensek, Karen, “Building information modeling. Routledge,”, 2014.
[6] Volk, R., Stengel, J., & Schultmann, F. (2014). Building Information Modeling (BIM) for existing buildings—Literature review and future needs. Automation in construction, 38, 109-127.
[7] Song, Y., Niu, L., Liu, P., & Li, Y. (2022). Fire hazard assessment with indoor spaces for evacuation route selection in building fire scenarios. Indoor and Built Environment, 31(2), 452-465.
[8] Li, Z., Huang, H., Li, N., Zan, M. L. C., & Law, K. (2020). An agent-based simulator for indoor crowd evacuation considering fire impacts. Automation in Construction, 120, 103395.
[9] Liu, J., Rojas-Cessa, R., & Dong, Z. (2016, April). Sensing, calculating, and disseminating evacuating routes during an indoor fire using a sensor and diffusion network. In 2016 IEEE 13th International Conference on Networking, Sensing, and Control (ICNSC) (pp. 1-6). IEEE.
[10] K.T. Ye., P.H. Tsai. “Fire simulation of building fire protection system based on digital twin” (2020) 取自https：//hdl.handle.net/11296/8ujkjx
[11] H. Y. Chen and P. H. Tsai, " A Speedup Simulation-based Fire Prediction for Online Evacuation Planning," International Computer Symposium, ICS 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 73-78.
[12] Chai, Z., Yuan, C., Lin, Z., & Bai, Y. (2021). CMS-LSTM: context-embedding and multi-scale spatiotemporal-expression LSTM for video prediction. arXiv preprint arXiv:2102.03586.
[13] Shi, X., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., & Woo, W. C. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems, 28.
[14] Koenig, Sven, and Maxim Likhachev. "D^* lite." Aaai/iaai 15 (2002)： 476-483.
[15] 陳弘毅，「火災學」，鼎茂，台灣，2021
[16] 盧以霖，「以 FDS 模擬分析火災延燒」。國立交通大學機械工程系所，新竹市，2016。取自https：//hdl.handle.net/11296/94nu62
[17] 賴建豪，「以FDS模擬分析材料及熱釋放面積對延燒之影響」。國立交通大學機械工程系所，新竹市，2015。取自https：//hdl.handle.net/11296/7bx38s
[18] Thunderhead Engineering. (2017). PyroSim： A Model Construction Tool for Fire Dynamics Simulator. 於 PyroSim User Manual. Manhattan, USA： Thunderhead Eng.
[19] Forney, G. P. (2017). Smokeview (Version 5)-A Tool for Visualizing Fire Dynamics Simulation Data, Volume I: User's Guide..
[20] Liu, J., Rojas-Cessa, R., & Dong, Z. (2016, April). Sensing, calculating, and disseminating evacuating routes during an indoor fire using a sensor and diffusion network. In 2016 IEEE 13th International Conference on Networking, Sensing, and Control (ICNSC) (pp. 1-6). IEEE..
[21] 葉冠廷，「用於數位孿生建築消防系統之逃生演算法」。國立成功大學製造資訊與系統研究所碩士論文，台南市，2019。 取自https：//hdl.handle.net/11296/8ujkjx
[22] Zhang, C., Zhou, L., Li, Y., & Fan, Y. (2020). A dynamic path planning method for social robots in the home environment. Electronics, 9(7), 1173.
[23] Zhuang, H., Dong, K., Qi, Y., Wang, N., & Dong, L. (2021). Multi-destination path planning method research of mobile robots based on goal of passing through the fewest obstacles. Applied Sciences, 11(16), 7378.
[24] Yan, F. T., Hu, Y. H., Jia, J. Y., Guo, Q. H., Zhu, H. H., & Pan, Z. G. (2019). RFES: a real-time fire evacuation system for Mobile Web3D. Frontiers of Information Technology & Electronic Engineering, 20(8), 1061-1074.
[25] Jiang, H. (2019). Mobile fire evacuation system for large public buildings based on artificial intelligence and IoT. IEEE Access, 7, 64101-64109.
[26] Tao, Y., Gao, H., Ren, F., Chen, C., Wang, T., Xiong, H., & Jiang, S. (2021). A mobile service robot global path planning method based on ant colony optimization and fuzzy control. Applied Sciences, 11(8), 3605.
[27] Zeng, W., & Church, R. L. (2009). Finding shortest paths on real road networks: the case for A. International journal of geographical information science, 23(4), 531-543.
[28] Niewola, A., & Podsedkowski, L. (2018). L* algorithm—a linear computational complexity graph searching algorithm for path planning. Journal of Intelligent & Robotic Systems, 91(3), 425-444.
[29] Raheem, F. A., & Hameed, U. I. (2018). Path planning algorithm using D* heuristic method based on PSO in dynamic environment. American Academic Scientific Research Journal for Engineering, Technology, and Sciences, 49(1), 257-271..
[30] K. Sven, and M. Likhachev. (2022). D* lite. Aaai/iaai 15, 476-483
[31] Kensek, K. (2014). Building information modeling. Routledge.
[32] Hu, Y., Wang, X., & Wang, F. Y. (2018). A quantitative study of factors influence on evacuation in building fire emergencies. IEEE transactions on computational social systems, 5(2), 544-552.
[33] Li, Z., Huang, H., Li, N., Zan, M. L. C., & Law, K. (2020). An agent-based simulator for indoor crowd evacuation considering fire impacts. Automation in Construction, 120, 103395.