Autors: Budakova, D. V., Vasilev, V. E., Dakovski L.
Title: Modeling Virtual Agent Behavior Using an Adaptive Multi-Plan Evacuation Strategy
Keywords:

Abstract: This paper models the behavior of a virtual agent that uses an adaptive multi-plan evacuation strategy. A utility-based learning agent is used as a leader to guide people to the exit via the safest possible route. The effectiveness of using multiple plans to optimize evacuation routes is investigated. The agent has neural networks to embed the plans and quickly and efficiently find the most appropriate action plan according to the fire's location and characteristics and available equipment. In this way, an application of neural networks in agent decision-making support problem is presented. Modification of reinforcement learning, the Q-learning algorithm that uses multiple plans is provided as an efficient approach to deal with non-stationary environments by allowing agents to dynamically adapt their decision-making processes, learn various strategies, and make more informed policy choices based on the specific characteristics of the surrounding environment. For the experiment, a model of a real existing electrical substation was implemented.

References

  1. D. V. Budakova, V. E. Vasilev, L. G. Dakovski, “A reinforcement learning algorithm for the optimal evacuation route finding from an electrical substation,” in AIP conference proceeding, Volume 3078, Issue 1, TechSys-2023, (AIP Conference, Plovdiv, Bulgaria, 2024), pp. 040005-1 - 040005-6. https://doi.org/10.1063/5.0209018.
  2. M. López-Carmona, A. Paricio, “CellEVAC: An adaptive guidance system for crowd evacuation through behavioral optimization.”, Safety Science-2021, (arXiv:2007.05963, 2021) 139. 105215. 10.1016/j.ssci.2021.105215., (2021).
  3. M. Manley, Y. S. Kim, K. Christensen, A. Chen, "Airport Emergency Evacuation Planning: An Agent-Based Simulation Study of Dirty Bomb Scenarios," in IEEE Transactions on Systems, Man, and Cybernetics: Systems, (IEEE, Oct. 2016), vol. 46, no. 10, pp. 1390-1403, doi: 10.1109/TSMC.2015.2497213.
  4. J., Tsai, E. Bowring, S. Marsella, M. Tambe, “Empirical Evaluation of Computational Emotional Contagion Models,” in Intelligent Virtual Agents IVA-2011. (Springer, Lecture Notes in Computer Science, Berlin, Heidelberg,) vol 6895. https://doi.org/10.1007/978-3-642-23974-8_42.
  5. H. Jeremy, “Modern Airports Offer No Easy Way Out for Panicking Crowds Simulations have highlighted the flaws of modern airport layouts when it comes to enabling emergency evacuations,” IEEE Spectrum-2016, https://spectrum.ieee.org/modern-airports-have-no-easy-exit-for-panicking-crowds.
  6. “Improving the evacuation of high-risk buildings with adaptive exit guidance WorkSafe, Adaptive evacuation white paper,” EATON, Powering Business Worldwide, (Effective December 2017).
  7. J. Lin, L. Cao, N. Li, “How the completeness of spatial knowledge influences the evacuation behavior of passengers in metro stations: A VR-based experimental study,” Automation in Construction-2020, Volume 113, 103136, ISSN 0926-5805, https://doi.org/10.1016/j.autcon.2020.103136.(https://www.sciencedirect.com/science/article/pii/S0926580519312452).
  8. Y. Mao, X. Wang, Q. Bai, Wu He, G. Pan, “Simulated interventions based on virtual reality to improve emergency evacuation under different spatial perception models,” International Journal of Industrial Ergonomics - 2024, Volume 99, 103545, ISSN 0169-8141, https://doi.org/10.1016/j.ergon.2024.103545.(https://www.sciencedirect.com/science/article/pii/S0169814124000015).
  9. R.A. Epstein, E. Z. Patai, J. B. Julian, H.J. Spiers, “The cognitive map in humans: spatial navigation and beyond.” Nat Neurosci - 2017, Oct 26;20(11):1504-1513. doi: 10.1038/nn.4656. PMID: 29073650; PMCID: PMC6028313.
  10. L. J. McCunn, R. Gifford, “Place imageability, sense of place, and spatial navigation: A community investigation,” Cities-2021, Volume 115, 103245, ISSN 0264-2751, https://doi.org/10.1016/j.cities.2021.103245.(https://www.sciencedirect.com/science/article/pii/S02642751210 01451).
  11. Y. Zhang, Q. Guo, and P. Kordjamshidi., “Towards Navigation by Reasoning over Spatial Configurations.” In Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics-2021, (online. Association for Computational Linguistics, 2021), pages 42-52.
  12. J. Zhang, X. Xia, R. Liu, N. Li, “Enhancing human indoor cognitive map development and wayfinding performance with immersive augmented reality-based navigation systems,” Advanced Engineering Informatics-2021, Volume 50, 101432, ISSN 1474-0346, https://doi.org/10.1016/j.aei.2021.101432.(https://www.sciencedirect.com/science/article/pii/S1474034621001841).
  13. K. McGrattan, R. McDermott, C. Weinschenk and G. Forney, “Fire Dynamics Simulator Users Guide”,, National Institute of Standards and Technology-2013, Sixth Edition, Special Publication 2013, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.sp.1019 (AccessedMay, 2023).
  14. National Institute of Standards and Technology U.S. Department of Commerce, “The Fire Research Division, Fire Dynamics Simulator (FDS)” [online] https://www.nist.gov/el/fire-research-division-73300 (Accessed May 2023).
  15. S. Subramanian and M. Crowley, “Using Spatial Reinforcement Learning to Build Forest Wildfire Dynamics Models From Satellite Images”, Frontiers in ICT. 5. 6. 10.3389/FICT.2018.00006, (2018).
  16. J. Lin et al., “How the completeness of spatial knowledge influences the evacuation behavior of passengers in metro stations: a VR-based experimental study” Autom. ConStruct. (2020).
  17. J. Lin et al., “Do people follow the crowd in building emergency evacuation? A cross-cultural immersive virtual reality-based study,” Adv. Eng. Inf. (2020).
  18. Y. Feng et al., “Hoogendoorn, Wayfinding behavior in a multi-level building: a comparative study of HMD VR and Desktop VR,” Adv. Eng. Inf. (2022).
  19. D. Shin, “Empathy and embodied experience in a virtual environment: to what extent can virtual reality stimulate empathy and embodied experience?” Comput. Hum. Behav. (2018).
  20. C. Becker-Asano et al., “Outline of an empirical study on the effects of emotions on strategic behavior in virtual emergencies,” Int. Conf. Affective Computing & Intelligent Interaction, (2011).
  21. L. Castelli et al. “Spatial navigation in large-scale virtual environments: gender differences in survey tasks”, Comput. Hum. Behav. (2008).
  22. Electric Substation (Power Grid) | Unity Packages, https://assetstore.unity.com/packages/3d/props/industrial/electric-substation-power-grid-133434
  23. H. H. Zhuo, X. Chen, & R. Pan, “On the Roles of LLMs in Planning: Embedding LLMs into Planning Graphs.”, ArXiv-2024, abs/2403.00783.
  24. H. Zhang, Q. Zhao, Z. Cheng, L. Liu, Y. Su, "Dynamic Path Optimization with Real-Time Information for Emergency Evacuation", Mathematical Problems in Engineering-2021, vol. 2021, Article ID 3017607, 9 pages, https://doi.org/10.1155/2021/3017607. (2021).
  25. Y. Lin and Y. Jeon, “Random Forests and Adaptive Nearest Neighbors.” Journal of the American Statistical Association-2006, 101(474), 578-590. https://doi.org/10.1198/016214505000001230, (2006).
  26. H. Temesgen, M. J. Ver Hoef, “Evaluation of the spatial linear model, random forest and gradient nearest-neighbor methods for imputing potential productivity and biomass of the Pacific Northwest forests,” Forestry: An International Journal of Forest Research, Volume 88, Issue 1, January 2015, Pages 131-142, https://doi.org/10.1093/forestry/cpu036.
  27. L. Xiaoyan, L. Xuedong, W. Xia, W. Rong, S. Lingli, X. Wentao, “Deep reinforcement learning for optimal rescue path planning in uncertain and complex urban pluvial flood scenarios,” Applied Soft Computing, Volume 144, 2023, 110543, ISSN 1568-4946, https://doi.org/10.1016/j.asoc.2023.110543.(https://www.sciencedirect.com/science/article/pii/S1568494623005616).
  28. F. Meneguzzi, L, De Silva, “Planning in BDI agents: a survey of the integration of planning algorithms and agent reasoning”, The Knowledge Engineering Review-2015, Vol 30, Issue 1, DOI: https://doi.org/10.1017/S0269888913000337, 2015, pp. 1 - 44, Cambridge University Press. (2015).
  29. L. Silva, F. Meneguzzsi, B. Logan, “BDI agent architectures: A survey”, 29 International Joint Conference on Artificial Intelligence (IJCAI-20) Survey Track, 2021, Article N:684, pp. 4914-4921.
  30. D. Budakova, V. Petrova-Dimitrova, V. Vasilev, and L. Dakovski, “Modelling of More Realistic Intelligent Virtual Agent in Virtual and Mixed Reality”, 10-th International Scientific Conference TechSys’21, (AIP Conference Proceedings 2449(1):040011, Plovdiv, Bulgaria, 2022) https://doi.org/10.1063/5.0090660.

Issue

AIP Conference Proceedings, vol. 3274, 2025, Albania, https://doi.org/10.1063/5.0259700

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus