JDF

Journal of Digital Frontier

Digital Intelligence Press

HK https://dipscie.com/index.php/JDF/index

3135-7695

149

Articles

<bold>Research on Simulation and Path Optimization of University Emergency Evacuation Based on Multi-Agent Reinforcement Learning</bold>

Yang

Linna

yangln@lzit.edu.cn

School of Economics and Management, Lanzhou Institute of Technology, Lanzhou, Gansu, China

30 10 2026

124 152

Received: 2782026

2026

Linna Yang (Author)

<a rel="license" href="https://creativecommons.org/licenses/by/4.0/"><img alt="Creative Commons License" src="//i.creativecommons.org/l/by/4.0/88x31.png" /></a><p>This work is licensed under a <a rel="license" href="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a>.</p>

Multi-agent reinforcement learning; Emergency evacuation; Bottleneck perception; State encoding; Reward decomposition

[1] Zhang, M., Li, Z., Si, H., Cheng, L., Zhou, X., & Wang, B. (2023). Urban travel time and residential location choice: The impacts of traffic congestion. Sustainable Cities and Society, 99, 104975. https://doi.org/10.1016/j.scs.2023.104975

[2] Fan, M., Hedayati Marzbali, M., Abdullah, A., & Maghsoodi Tilaki, M. J. (2024). Using a space syntax approach to enhance pedestrians’ accessibility and safety in the historic city of George Town, Penang. Urban Science, 8(1), 6. https://doi.org/10.3390/urbansci8010006

[3] Chen, L., Deng, P., Li, L., & Hu, X. (2025). Mixed motivation driven social multi-agent reinforcement learning for autonomous driving. IEEE/CAA Journal of Automatica Sinica, 12(6), 1272-1282. https://doi.org/10.1109/jas.2025.125201

[4] Lokam, A., & Dasari, K. (2026). A QMIX-driven routing protocol for dynamic Underwater Acoustic Sensor Networks. Scientific Reports. https://doi.org/10.1038/s41598-026-74771-2

[5] Guan, Y., Ren, Y., Sun, Q., Li, S. E., Ma, H., Duan, J., ... & Cheng, B. (2022). Integrated decision and control: Toward interpretable and computationally efficient driving intelligence. IEEE transactions on cybernetics, 53(2), 859-873. https://doi.org/10.1109/tcyb.2022.3163816

[6] Malathi, V., Sreedharan, P., PR, R., Anil Kumar, V., Sadasivan, A. L., Udupa, G., ... & Troppina, A. (2025). Decision-making for path planning of mobile robots under uncertainty: A review of belief-space planning simplifications. Robotics, 14(9), 127. https://doi.org/10.3390/robotics14090127

[7] Guo, Y., Mao, Z., Chen, X., Fan, X., Han, Y., Su, X., ... & Tian, H. (2026). Floor field cellular automata model of pedestrian crush and stampede behavior based on crowding force transmission mechanism. Physics Letters A, 131951. https://doi.org/10.1016/j.physleta.2026.131951

[8] Zambare, P., & Liu, Y. (2025). Modeling and simulation of pedestrian behavior in traffic environment: A systematic review of approaches and software. IEEE Access. https://doi.org/10.1109/access.2025.3602471

[9] Silva, E. C., Damazo, G. S., & Martins, L. G. (2025, February). Cellular Automata Applied to the Simulation of Pedestrian Evacuation with Surmountable Obstacles and Route Alternation Through an Impatience Mechanism. In International Conference on Agents and Artificial Intelligence (pp. 562-582). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-25032-2_27

[10] Imtiaz, T., Chai, L., Heal, K., Luo, X., Park, J., Dy, J., & Flynn, J. (2025, December). LVT: Large-Scale Scene Reconstruction via Local View Transformers. In Proceedings of the SIGGRAPH Asia 2025 Conference Papers (pp. 1-12). https://doi.org/10.1145/3757377.3763838

[11] Sun, T., Ji, J., Li, J., & Xv, Z. (2026). SpectVit: Spectral-spatial gating for efficient vision transformers. Pattern Recognition, 114749. https://doi.org/10.1016/j.patcog.2026.114749

[12] Ge, L., Wang, S., & Wang, G. (2024). Rapid vehicle trajectory prediction based on multi-attention mechanism for fusing multimodal information. Electronics, 13(23), 4806. https://doi.org/10.3390/electronics13234806

[13] Han, D., Ye, T., Han, Y., Xia, Z., Pan, S., Wan, P., ... & Huang, G. (2024, September). Agent attention: On the integration of softmax and linear attention. In European conference on computer vision (pp. 124-140). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72973-7_8

[14] Ye, K., Wu, Z., Wu, Y., Qian, H., Woo, S., Srigrarom, S., & Khoo, B. C. (2026). Topology-Safe Air-to-Air Interception via “Go”-Inspired Metrics and Multi-Agent Reinforcement Learning. Aerospace, 13(8), 680. https://doi.org/10.3390/aerospace13080680

[15] Terry, J. K., Black, B., Grammel, N., Jayakumar, M., Hari, A., Sullivan, R., ... & Ravi, P. (2021). Pettingzoo: Gym for multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 34, 15032-15043. https://doi.org/10.48550/arXiv.2009.14471

[16] Metelo, F., Soares, C., Racković, S., & Costa, P. Á. (2024, August). Peersimgym: An environment for solving the task offloading problem with reinforcement learning. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 38-54). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-70378-2_3

[17] Yang, H., Shi, J., Jiang, N., Yu, H., & Yang, L. (2026). Congestion-Mitigating Evacuation Path Planning in Subway Stations via Graph-Theoretic Deep Reinforcement Learning. Simulation Modelling Practice and Theory, 103315. https://doi.org/10.1016/j.simpat.2026.103315

[18] Moreno, J. V., Gonçalves, A. B., & Falcão, A. P. (2026). Bridging BIM and Path-Finding Algorithms: A Systematic Review and Analysis of Escape Route Generation. Sustainability, 18(20), 10490. https://doi.org/10.3390/su182010490

[19] Zhong, Z., & Ren, Z. (2026). Multi-agent Reinforcement Learning Optimization for Urban Earthquake Emergency Evacuation with GIS-based Real-time Decision Support. Journal of Earthquake and Tsunami, 2540002. https://doi.org/10.1142/s1793431125400020

[20] Low, D., & Zhou, Y. (2025). Cooperative multi-agent reinforcement learning for robotic systems: A review. Multiagent and Grid Systems, 21(2), 96-123. https://doi.org/10.1177/15741702251370050

[21] Zhang, J., & Wu, S. (2026). Master-Refined MAPPO for Long-Term Joint Resource Scheduling in NOMA-MEC Systems. Symmetry, 18(7), 1243. https://doi.org/10.3390/sym18071243

[22] Torres Rodríguez, I. J., Marsà Fargas, J., Candelo Zuluaga, C., Pérez Díaz, C. A., Martin Hernández, L. D., Sanz Merodio, D., ... & López Estévez, M. (2026, May). Toward Reproducible Actuator Characterization: A Comprehensive Framework for Robotics Applications. In Actuators (Vol. 15, No. 6, p. 301). MDPI. https://doi.org/10.3390/act15060301

[23] Kalkanlı, D., Kundak, S., Atun, F., & Van Westen, C. J. (2026). Human-Centric Digital Twins for Spatial Sustainability: A Procedural VR Framework for Calibrating Agent-Based Evacuation Models in Diverse Urban Morphologies. Sustainability, 18(3), 1482. https://doi.org/10.3390/su18031482