AI-Assisted VR Simulation for Predicting and Minimizing Evacuation Congestion in School Shooting Emergencies

Authors

  • Eugene Samson Student Author

Keywords:

VR Evacuation Simulation, AI Congestion Prediction, Adaptive Pathfinding

Abstract

School emergencies involving violent attacks often lead to unpredictable evacuation behavior. Panic, congestion, and avoidance of the threat can direct students away from the nearest exits and create dangerous bottlenecks. Existing evacuation systems and building designs are typically evaluated using static routing methods that do not adapt to real-time crowd conditions. This limits their ability to prevent or reduce congestion during an active emergency. The study proposes the development of an AI-assisted, Unity-based virtual reality (VR) evacuation simulator that models student evacuation behavior during a simulated school-shooting emergency at the Systems Plus College Foundation (SPCF) campus. The system integrates a Gated Recurrent Unit (GRU) neural network to predict congestion in critical corridors and exits. It also utilizes the D* Lite adaptive pathfinding algorithm that reroutes evacuees away from forecasted bottlenecks in real time. The proposed GRU–D* Lite approach will be benchmarked against conventional A* routing across four performance measures: evacuation time, congestion level, route utilization, and evacuation success rate. The study will also test alternative building configurations, such as additional exits and external emergency stairs, to evaluate their effect on congestion. Following a Descriptive-Developmental research design implemented through the V-Model, the system is expected to demonstrate improved evacuation efficiency over static routing and provide the Physical Plant and Facilities Office (PPFO) with a safe, data-driven tool for evaluating evacuation plans and congestion-mitigation strategies. 

References

Associated Press. (2026, June 22). High school shooting in the Philippines kills 3, and police arrest 2 students. AP News. https://apnews.com/article/022bd9892d858b1bc5e9ed741e0d7222

Barbosa, P. C., Macatulad, E. G., & Ramos, R. V. (2024). ESCAPE: Evacuation simulation using cognitive agent-based modeling on possible earthquake in GAMA platform for the case of Kalayaan Residence Hall. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLVIII-4/W8-2023, 39–46. https://doi.org/10.5194/isprs-archives-XLVIII-4-W8-2023-39-2024

Caliwan, C. L. (2026, August 18). DILG orders probe into shooting incident in Ateneo Zamboanga. Philippine News Agency. https://www.pna.gov.ph/articles/1282143

Ding, N., Ma, Y., Dong, D., & Wang, Y. (2021). Experiment and simulation study of emergency evacuation during violent attack in classrooms. Journal of Safety Science and Resilience, 2(4), 208–221. https://doi.org/10.1016/j.jnlssr.2021.09.002

Duan, J., Liu, H., Fan, B., Li, X., & Li, W. (2026). Evacuation under terrorist attacks: A crowd congestion control method based on deep reinforcement learning. Reliability Engineering & System Safety, 267, 111951. https://doi.org/10.1016/j.ress.2025.111951

Guo, C., Huo, F., Deng, S., Huang, J., & Zhang, W. (2024). An evacuation model considering pedestrian group behavior under violent attacks. Physica A: Statistical Mechanics and Its Applications, 656, 130229. https://doi.org/10.1016/j.physa.2024.130229

Hassaan, Z. A., Yacoub, M. H., & Said, L. A. (2025). Gated recurrent unit accelerators for financial time series prediction on field-programmable gate array. Engineering Applications of Artificial Intelligence, 162, 112534. https://doi.org/10.1016/j.engappai.2025.112534

Huang, Y., Guo, Z., Chu, H., & Sengupta, R. (2023). Evacuation simulation implemented by ABM-BIM of Unity in students' dormitory based on delay time. ISPRS International Journal of Geo-Information, 12(4), 160. https://doi.org/10.3390/ijgi12040160

Jin, J., Zhang, Y., Zhou, Z., Jin, M., Yang, X., & Hu, F. (2023). Conflict-based search with D* Lite algorithm for robot path planning in unknown dynamic environments. Computers & Electrical Engineering, 105, 108473. https://doi.org/10.1016/j.compeleceng.2022.108473

Li, X., Lu, Y., Zhao, X., Deng, X., & Xie, Z. (2024). Path planning for intelligent vehicles based on improved D* Lite. The Journal of Supercomputing, 80(1), 1294–1330. https://doi.org/10.1007/s11227-023-05528-1

Lim, W. M. M., Canillas, A. B. F., Lee, M. S. G., & Galit, B. A. B. (2025). Development of an evacuation route planning simulation tool for Philippine Science High School–Main Campus using cellular automata crowd modeling. In Proceedings of the 43rd Samahang Pisika ng Pilipinas Physics Conference (SPP-2025-3C-03). https://proceedings.spp-online.org/article/view/SPP-2025-3C-03

Liu, R., Becerik-Gerber, B., & Lucas, G. M. (2023). Effectiveness of VR-based training on improving occupants' response and preparedness for active shooter incidents. Safety Science, 164, 106175. https://doi.org/10.1016/j.ssci.2023.106175

Liu, R., Wu, W., Becerik-Gerber, B., & Lucas, G. M. (2024). Enhancing building safety design for active shooter incidents: Exploration of building exit parameters using reinforcement learning-based simulations. In Proceedings of the 31st EG-ICE International Workshop on Intelligent Computing in Engineering (pp. 569–579). https://doi.org/10.35869/Proceedings_EGICE2024

Liu, X., Huang, J., Zhao, J., Ji, Y., Fan, X., & Du, T. (2024). Predicting temporal evacuation travel time in staircases between adjacent floors of super high-rise buildings by artificial neural networks. Journal of Building Engineering, 98, 111133. https://doi.org/10.1016/j.jobe.2024.111133

Lu, H., Li, J., Sun, S., Wang, J., Ye, R., Wu, J., & Wang, Y. (2024). Study on the propagation characteristics of shockwave in dense crowd in corner passage. International Journal of Disaster Risk Reduction, 113, 104826. https://doi.org/10.1016/j.ijdrr.2024.104826

McClurg, C. A., & Wagner, A. R. (2025). Using virtual reality to simulate and study the movements of school shooters. In Proceedings of the 2025 Annual Modeling and Simulation Conference (ANNSIM). Society for Modeling and Simulation International. https://pure.psu.edu/en/publications/using-virtual-reality-to-simulate-and-study-the-movements-of-scho-2

Merriam-Webster. (n.d.-a). Algorithm. In Merriam-Webster.com dictionary. Retrieved September 16, 2026, from https://www.merriam-webster.com/dictionary/algorithm

Merriam-Webster. (n.d.-b). Benchmark. In Merriam-Webster.com dictionary. Retrieved September 16, 2026, from https://www.merriam-webster.com/dictionary/benchmark

Merriam-Webster. (n.d.-c). Bottleneck. In Merriam-Webster.com dictionary. Retrieved September 16, 2026, from https://www.merriam-webster.com/dictionary/bottleneck

Merriam-Webster. (n.d.-d). Congested. In Merriam-Webster.com dictionary. Retrieved September 16, 2026, from https://www.merriam-webster.com/dictionary/congested

Merriam-Webster. (n.d.-e). Evacuation. In Merriam-Webster.com dictionary. Retrieved September 16, 2026, from https://www.merriam-webster.com/dictionary/evacuation

Merriam-Webster. (n.d.-f). Virtual reality. In Merriam-Webster.com dictionary. Retrieved September 16, 2026, from https://www.merriam-webster.com/dictionary/virtual%20reality

Panonce, C. N. (2024). The shadow of calamity: Experiences of STEM teachers in school serving as evacuation centers. Franciscan College of the Immaculate Conception Insights, 2(1), 92–125. https://doi.org/10.5281/zenodo.13316944

Philippine News Agency. (2023). [Article title and publication date unavailable]. https://www.pna.gov.ph/articles/1198177

Podoletz, L., McGill, M., McIlhatton, D., Marshall, J., Healy, N., & Tanczer, L. M. (2024). A critical review of virtual and extended reality immersive police training: Application areas, benefits & vulnerabilities. In Proceedings of the 30th ACM Symposium on Virtual Reality Software and Technology (Article 38). Association for Computing Machinery. https://doi.org/10.1145/3641825.3687707

Ren, Z., Rathinam, S., Likhachev, M., & Choset, H. (2022). Multi-objective path-based D* Lite. IEEE Robotics and Automation Letters, 7(2), 3318–3325. https://doi.org/10.1109/LRA.2022.3146918

Rico, E. R., Rabajante, J. F., Tubay, J. M., Lapitan, A. M., & Madrid, V. R. (2024). A multi-objective site selection model for evacuation centers in Taguig City, Philippines. Natural Hazards, 120(9), 8303–8321. https://doi.org/10.1007/s11069-024-06485-5

Shi, D., Li, J., Wang, Q., Chen, J., Lovreglio, R., Lo, J. T. Y., & Ma, J. (2025). Modeling and simulation of crowd dynamics at evacuation bottlenecks during flood disasters. Transportation Research Part E: Logistics and Transportation Review, 198, 104064. https://doi.org/10.1016/j.tre.2025.104064

Silinskaya, A. A., Bogomolov, A. S., & Kushnikov, V. A. (2025). Modeling evacuation from premises considering social groups and multiple exits. Mathematical Modeling and Computational Methods, 3(47), 85–102. https://doi.org/10.18698/2309-3684-2025-3-85102

Sun, L., Liu, H., Fan, B., Li, X., & Li, W. (2025). Multi-agent deep reinforcement learning-based path planning for crowd evacuation in buildings. Journal of Building Engineering, 111, 113345. https://doi.org/10.1016/j.jobe.2025.113345

Tao, B., & Kim, J.-H. (2024). Deep reinforcement learning-based local path planning in dynamic environments for mobile robot. Journal of King Saud University—Computer and Information Sciences, 36(10), 102254. https://doi.org/10.1016/j.jksuci.2024.102254

Venu, S., & Gurusamy, M. (2025). A comprehensive review of path planning algorithms for autonomous navigation. Results in Engineering, 28, 107750. https://doi.org/10.1016/j.rineng.2025.107750

Wächter, T., Rexilius, J., & König, M. (2022). Interactive evacuation in intelligent buildings assisted by mixed reality. Journal of Smart Cities and Society, 1(3), 179–194. https://doi.org/10.3233/SCS-220009

Wang, Y., Ding, N., Dong, D., & Zhu, Y. (2024). Simulation of crowd evacuation under attack considering emotion spreading. Chinese Physics B, 33(12), 128901. https://doi.org/10.1088/1674-1056/ad84c7

Wei, Y., Zhang, Y., Xu, Y., Wang, S., Liu, J., Jin, L., Ou, S., Pan, S., & Liu, Y. (2024). Impact of risk preferences on evacuee behavior and attention distribution in urban underground space evacuations. Physica A: Statistical Mechanics and Its Applications, 640, 129698. https://doi.org/10.1016/j.physa.2024.129698

Yang, L., & Ding, N. (2023). Evacuation behavior under violent attacks in classrooms based on experiments and interpretable machine learning method. Safety Science, 166, 106243. https://doi.org/10.1016/j.ssci.2023.106243

Yao, Z., Sun, J., Han, C., & Jin, L. (2025). A path-planning algorithm integrated improved A* and D* Lite with bat clustering. Journal of Computational Methods in Sciences and Engineering, 25(3), 2159–2184. https://doi.org/10.1177/14727978241310746

Ye, R., Li, J., Lu, H., Wang, J., Pan, Y., & Wang, Y. (2024). A study on the arch mechanism of pedestrian evacuation and congestion alleviation strategies at building exits. Journal of Building Engineering, 88, 109159. https://doi.org/10.1016/j.jobe.2024.109159

Zhang, Z., Ling, W., Yang, Z., Wei, X., & Wang, H. (2025). A congestion prediction model for optimizing emergency evacuation design of university libraries in China. Journal of Building Engineering, 99, 111537. https://doi.org/10.1016/j.jobe.2024.111537

Downloads

Published

2026-09-26

How to Cite

AI-Assisted VR Simulation for Predicting and Minimizing Evacuation Congestion in School Shooting Emergencies. (2026). International Journal of Research Proposals and Methodologies, 1(1). https://publish.acad-ira.top/index.php/IJRPM/article/view/31

Similar Articles

11-14 of 14

You may also start an advanced similarity search for this article.