AIU – Faculty of Informatics and Communications Engineering
Published June 4, 2026 | Version 1
Preprint Open

Robot-Assisted Emergency Evacuation of Crowds: A Comprehensive Survey of Modeling Approaches, Intelligent Guidance Systems, and Future Research Directions

Authors/Creators

  • 1. ROR icon Arab International University

Description

Emergency evacuation in crowded environments remains a major safety challenge due to complex crowd dynamics, congestion, and uncertainty during emergencies. Recent advances in autonomous robotic systems have introduced new opportunities for adaptive evacuation guidance and intelligent crowd management; however, research in this area remains fragmented across crowd modeling, robotics, human–robot interaction, and artificial intelligence. This paper presents a comprehensive survey of robot-assisted emergency evacuation systems, covering crowd behavior analysis, crowd modeling approaches, robotic guidance strategies, learning-based methods, simulation platforms, digital twins, and evaluation frameworks. A taxonomy of robot-assisted evacuation strategies is proposed, and the strengths, limitations, and applicability of existing approaches are critically analyzed. Furthermore, key research challenges and future directions are identified, including trust-aware guidance, safe reinforcement learning, scalable multi-robot coordination, simulation-to-reality transfer, and benchmark standardization. By providing a unified interdisciplinary perspective, this survey aims to serve as a reference framework for the development and evaluation of next-generation intelligent evacuation systems.

This work was conducted at Arab International University (AIU), Damascus, Syria.
Official website: https://www.aiu.edu.sy

Files

Crowds -researchsquare.pdf

Files (793.7 kB)

Name Size Download all
md5:276710385ddb98524ade854c1fc5002b
793.7 kB Preview Download

Additional details

References

  • [1] Y. Zhao, X. Liu, J. Wang, and S. J. Guy, "A survey on crowd simulation: Models, methods, and applications," Computer Animation and Virtual Worlds, vol. 30, no. 3–4, Art. no. e1881, 2019.
  • [2] N. Bellomo, B. Piccoli, and A. Tosin, "Modeling crowd dynamics from a complex systems perspective," Mathematical Models and Methods in Applied Sciences, vol. 28, no. 5, pp. 793–824, 2018.
  • [3] J. Shi, X. Ren, and G. Chen, "A review of pedestrian evacuation simulation models," Safety Science, vol. 118, pp. 1–14, 2019.
  • [4] X. Zheng, T. Zhong, and M. Liu, "A review of pedestrian evacuation modeling," Physica A: Statistical Mechanics and Its Applications, vol. 540, Art. no. 123012, 2020.
  • [5] J. E. Almeida, J. A. Silva, and A. L. Rocha, "Crowd simulation and modeling: A systematic literature review," ACM Computing Surveys, vol. 54, no. 4, Art. no. 86, 2021.
  • [6] S. J. Guy, J. van den Berg, W. Liu, R. Lau, M. Lin, and D. Manocha, "A statistical similarity measure for crowd simulation," ACM Transactions on Graphics (SIGGRAPH), vol. 38, no. 4, Art. no. 111, 2019.
  • [7] N. Pelechano, J. Allbeck, and N. Badler, Crowd Simulation, 2nd ed. San Rafael, CA, USA: Morgan & Claypool, 2018.
  • [8] A. Johansson, D. Helbing, and P. K. Shukla, "From crowd dynamics to crowd safety," Transportation Research Part C: Emerging Technologies, vol. 95, pp. 1–13, 2018.
  • [9] T. Kretz, A. Grünebohm, and M. Schreckenberg, "Benchmark data for pedestrian dynamics," Safety Science, vol. 132, Art. no. 104967, 2020.
  • [10] X. Liu, Y. Song, and Z. Chen, "Agent-based modeling of pedestrian evacuation under panic conditions," Simulation Modelling Practice and Theory, vol. 103, Art. no. 102104, 2020.
  • [11] B. Tang, C. Jiang, and Y. Guo, "Robot-assisted evacuation with human mobility modeling," IEEE Transactions on Human–Machine Systems, vol. 46, no. 5, pp. 694–707, 2016.
  • [12] E. Boukas, I. Kostavelis, and A. Gasteratos, "Robot-guided crowd evacuation," IEEE Transactions on Automation Science and Engineering, vol. 12, no. 2, pp. 739–751, 2015.
  • [13] I. Sakour and H. Hu, "Robot-assisted evacuation simulation," in Proc. 8th Computer Science and Electronic Engineering Conf. (CEEC), Colchester, U.K., 2016, pp. 1–6.
  • [14] S. Zhang and Y. Guo, "Distributed multi-robot evacuation incorporating human behavior," Asian Journal of Control, vol. 20, no. 1, pp. 34–44, 2018.
  • [15] Y. Cheng, H. Wang, and Z. Liu, "Multi-robot cooperation for emergency evacuation," Robotics and Autonomous Systems, vol. 112, pp. 1–14, 2019.
  • [16] P. Robinette, W. Li, R. Allen, A. Howard, and A. R. Wagner, "Overtrust of robots in emergency evacuation scenarios," in Proc. ACM/IEEE Int. Conf. Human–Robot Interaction (HRI), Vienna, Austria, 2017, pp. 101–108.
  • [17] A. R. Wagner, J. B. Scheutz, and P. A. Hancock, "Human–robot trust in emergency evacuation," IEEE Robotics & Automation Magazine, vol. 25, no. 1, pp. 38–47, 2018.
  • [18] C. S. Nam, M. A. Cummings, and J. J. Lee, "Trust in human–robot interaction: A review," Human Factors, vol. 62, no. 3, pp. 1–21, 2020.
  • [19] P. A. Hancock, D. R. Billings, and K. E. Schaefer, "A meta-analysis of trust in human–robot interaction," Human Factors, vol. 63, no. 3, pp. 1–27, 2021.
  • [20] S. Sebastian, A. R. Wagner, and H. Hu, "Compliance-aware robot guidance in evacuation," Robotics and Autonomous Systems, vol. 156, Art. no. 104193, 2022.
  • [21] J. Chen, M. Everett, and J. P. How, "Reinforcement learning for crowd-aware robot navigation," IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 1025–1032, 2019.
  • [22] M. Everett, Y. F. Chen, and J. P. How, "Motion planning among dynamic crowds using deep reinforcement learning," Science Robotics, vol. 6, no. 56, eaba4306, 2021.
  • [23] Y. Li, Z. Chen, and Y. Wang, "Multi-agent reinforcement learning for evacuation planning," IEEE Access, vol. 8, pp. 114–128, 2020.
  • [24] Z. Zhou, H. Wang, and Y. Guo, "Learning-based evacuation guidance using autonomous robots," Robotics and Autonomous Systems, vol. 146, Art. no. 103881, 2021.
  • [25] A. Rudenko, L. Palmieri, and K. O. Arras, "Human-aware robot navigation: A survey," International Journal of Robotics Research, vol. 39, no. 8, pp. 1–30, 2020.
  • [26] S. Ivaldi, V. Padois, and F. Nori, "Tools for dynamics simulation of robots: A survey," IEEE Robotics & Automation Magazine, vol. 21, no. 4, pp. 16–31, 2014.
  • [27] N. Koenig and A. Howard, "Design and use of the Gazebo simulator," in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS), Macau, China, 2019.
  • [28] O. Michel, "Webots: Professional mobile robot simulation," International Journal of Advanced Robotic Systems, vol. 15, no. 1, Art. no. 1729881418758390, 2018.
  • [29] Unity Technologies, Unity for Simulation and Robotics, White Paper, 2020.
  • [30] B. Kutscher, A. Johansson, and K. Still, "Digital twins for emergency evacuation," Safety Science, vol. 150, Art. no. 105689, 2022.
  • [31] D. Helbing, A. Johansson, and H. Z. Al-Abideen, "Self-organized pedestrian crowd dynamics," Transportation Science, vol. 52, no. 3, pp. 1–15, 2018.
  • [32] K. Still, G. G. Pereira, and J. Sime, "Crowd safety management revisited," Safety Science, vol. 114, pp. 1–12, 2019.
  • [33] J. D. Sime, "Human behavior in fire evacuation," Fire Safety Journal, vol. 120, Art. no. 103070, 2021.
  • [34] R. Lovreglio, E. Ronchi, and D. Nilsson, "Pedestrian decision-making during evacuation," Fire Technology, vol. 56, no. 3, pp. 1–27, 2020.
  • [35] D. Nilsson and A. Johansson, "Social influence in evacuation," Safety Science, vol. 132, Art. no. 104968, 2020.
  • [36] I. Karamouzas, N. Sohre, and R. Geraerts, "Predictive models of crowd behavior," ACM Transactions on Graphics, vol. 41, no. 4, Art. no. 96, 2022.
  • [37] R. Zhao, H. Wang, and Y. Guo, "AI-driven crowd evacuation systems," IEEE Access, vol. 10, pp. 1–15, 2022.
  • [38] H. Wang, Y. Cheng, and Z. Liu, "Autonomous robots for emergency response," Robotics, vol. 12, no. 3, Art. no. 78, 2023.
  • [39] J. Park, S. Kim, and K. Lee, "Human-centered robot evacuation guidance," IEEE Transactions on Robotics, vol. 39, no. 4, pp. 1–15, 2023.
  • [40] X. Liang, Y. Li, and Z. Zhou, "Trust-aware multi-robot evacuation systems," Robotics and Autonomous Systems, vol. 168, Art. no. 104496, 2024.
  • [41] J. D. Lee and K. A. See, "Trust in Automation: Designing for Appropriate Reliance," Human Factors, vol. 46, no. 1, pp. 50–80, 2004.
  • [42] A. Rudenko, L. Palmieri, M. Herman, K. O. Arras, and C. Amato, "Human Motion Trajectory Prediction: A Survey," International Journal of Robotics Research, vol. 39, no. 8, pp. 895–935, 2020.
  • [43] K. Zhang, Z. Yang, and T. Başar, "Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms," in Handbook of Reinforcement Learning and Control, Springer, 2021, pp. 321–384.
  • [44] J. García and F. Fernández, "A Comprehensive Survey on Safe Reinforcement Learning," Journal of Machine Learning Research, vol. 16, pp. 1437–1480, 2015.
  • [45] A. Fuller, Z. Fan, C. Day, and C. Barlow, "Digital Twin: Enabling Technologies, Challenges and Open Research," IEEE Access, vol. 8, pp. 108952–108971, 2020.
  • [46] F. Tao, H. Zhang, A. Liu, and A. Y. C. Nee, "Digital Twin in Industry: State-of-the-Art," IEEE Transactions on Industrial Informatics, vol. 15, no. 4, pp. 2405–2415, 2019.
  • [47] D. Pineau et al., "Improving Reproducibility in Machine Learning Research," Journal of Machine Learning Research, vol. 22, no. 164, pp. 1–20, 2021.
  • [48] B. A. Kitchenham and S. Charters, "Guidelines for Performing Systematic Literature Reviews in Software Engineering," EBSE Technical Report, Keele University and Durham University Joint Report, 2007.