Abstract
Most existing crowd evacuation methods focus on internal factors and do not consider the influence of the external environment factors, producing unrealistic global behavior occurs when individuals are moving through the crowded space. As an essential part of a building, safety indication signs (SISs) are a form of environmental information and perceptual access that play an important role in promoting wayfinding by virtue of their guiding role in movement direction and route selection by providing guidance, warning and mandatory message to people. In this paper, we propose an innovative crowd simulation method guided by SISs with reinforcement learning strategy for use in emergencies. To illustratethe guiding function of the SISs, we establish a guidance field for each SIS and add the attractive force to the guidance field. Besides, we formulate the multi-agent (crowd) navigation problem as an action-selection problem and design a novel reinforcement learning strategy for driving individuals to accomplish collision-free movement more efficiently. Particularly, we define a state transition strategy between the SIS area and the non-SIS area to achieve continuity of guidance. We use extensive simulations to highlight the potential of our method in different scenarios and evaluate the results in terms of evacuation efficiency and the reasonableness of SIS placement. In practice, our system runs at interactive rates and can solve complex planning problems involving one or more groups.
Similar content being viewed by others
References
Sutton RS, Barto AG (2018) Reinforcement learning: An introduction. MIT press
Zhou M, Dong H, Ioannou PA, Zhao Y, Wang F-Y (2019) Guided crowd evacuation: approaches and challenges. IEEE/CAA J Autom Sinica 6(5):1081–1094
Liu J, Chen Y, Chen Y (2021) Emergency and disaster manage- ment-crowd evacuation research. J Ind Inf Integr 21:100191
Sharbini H, Sallehuddin R, Haron H (2021) Crowd evacuation simulation model with soft computing optimization techniques: a systematic literature review. J Manage Analy 8(3):443–485
Burstedde C, Klauck K, Schadschneider A, Zittartz J (2001) Simulation of pedestrian dynamics using a two-dimensional cellular automaton. Physica A 295(3-4):507–525
Li Y, Chen M, Dou Z, Zheng X, Cheng Y, Mebarki A (2019) A review of cellular automata models for crowd evacuation. Physica A 526:120752
Thalmann D, Musse SR (2012) Crowd simulation. Springer Science & Business Media
Pelechano N, Allbeck JM, Badler NI (2008) Virtual crowds: methods, simulation, and control. Synth Lect Comput Graph Animat 3(1):1–176
Henderson L (1971) The statistics of crowd fluids. Nature 229(5284):381–383
Henderson LF (1974) On the fluid mechanics of human crowd motion. Transp Res 8(6):509–515
Kerr W, Spears D (2005) Robotic simulation of gases for a surveillance task. In: 2005 IEEE/RSJ international conference on intelligent robots and systems. IEEE, pp 2905–2910
Reynolds CW (1987) Flocks, herds and schools: A distributed behavioral model. In: Proceedings of the 14th annual conference on Computer graphics and interactive techniques, pp 25–34
Reynolds CW et al (1999) Steering behaviors for autonomous characters. In: Game developers conference, vol 1999. Citeseer, pp 763–782
Kari J (2005) Theory of cellular automata: a survey. Theoretical Comput Sci 334(1-3):3–33
Padovani D, Neto JJ, Cereda PRM (2018) Modeling pedestrian dynamics with adaptive cellular automata. Procedia Comput Sci 130:1120–1127
Zhou X, Hu J, Ji X, Xiao X (2019) Cellular automaton simulation of pedestrian flow considering vision and multi-velocity. Physica A 514:982–992
Felcman J, Kubera P (2021) A cellular automaton model for a pedestrian flow problem. Math Model Nat Phenom 16:11
Van den Berg J, Lin M, Manocha D (2008) Reciprocal velocity obstacles for real-time multi-agent navigation. In: 2008 IEEE International Conference on Robotics and Automation. IEEE, pp 1928–1935
Muhammad F, Juniastuti S, Nugroho SMS, Hariadi M (2018) Crowds evacuation simulation on heterogeneous agent using agent-based reciprocal velocity obstacle. In: 2018 international seminar on intelligent technology and its applications (ISITIA). IEEE, pp 275–280
Douthwaite JA, Zhao S, Mihaylova LS (2019) Velocity obstacle approaches for multi-agent collision avoidance. Unmanned Syst 7(01):55–64
Li J, Zhang H (2021) Crowd evacuation simulation research based on improved reciprocal velocity obstacles (rvo) model with path planning and emotion contagion. Transportation Research Record, 03611981211056910
Helbing D, Molnar P (1995) Social force model for pedestrian dynamics. Phys Rev E 51 (5):4282
Liu B, Liu H, Zhang H, Qin X (2018) A social force evacuation model driven by video data. Simul Model Pract Theory 84:190–203
Li X, Liang Y, Zhao M, Wang C, Bai H, Jiang Y (2019) Simulation of evacuating crowd based on deep learning and social force model. IEEE Access 7:155361–155371
Li Q, Liu Y, Kang Z, Li K, Chen L (2020) Improved social force model considering conflict avoidance. Chaos: An Interdisciplinary Journal of Nonlinear Science 30(1):013129
Zhao Y, Liu H, Gao K (2021) An evacuation simulation method based on an improved artificial bee colony algorithm and a social force model. Appl Intell 51(1):100–123
Liu Y, Lyu L (2019) Diversified crowd evacuation method in large public places. IEEE Access 7:144874–144884
Nilsson D, Thompson P, McGrath D, Boyce K, Frantzich H (2020) Crowd safety: prototyping for the future: summary report showing how the science for “pedestrian flow” can keep up with demographic change
Mitchell TM, Mitchell TM (1997) Machine learning, vol 1. McGraw-hill New York
Adamatzky A (2018) Unconventional computing: A Volume in the Encyclopedia of Complexity and Systems Science. Springer
Longley P, Batty M (2003) Advanced spatial analysis: the CASA book of GIS, ESRI Inc.
Yao Z, Zhang G, Lu D, Liu H (2019) Data-driven crowd evacuation: a reinforcement learning method. Neurocomputing 366:314–327
Zhang Z, Lu D, Li J, Liu P, Zhang G (2021) Crowd evacuation simulation using hierarchical deep reinforcement learning. In: 2021 IEEE 24th international conference on computer supported cooperative work in design (CSCWD). IEEE, pp 563–568
Malebary SJ, Basori AH et al (2021) Reinforcement learning for pedestrian evacuation simulation and optimization during pandemic and panic situation. In: Journal of Physics: Conference Series, vol 1817. IOP Publishing, p 012008
Xue Y, Wu R, Liu J, Tang X (2021) Crowd evacuation guidance based on combined action reinforcement learning. Algorithms 14(1):26
Sutton RS (1988) Learning to predict by the methods of temporal differences. Mach Learn 3 (1):9–44
Audibert J-Y, Munos R, Szepesvári C (2009) Exploration–exploitation tradeoff using variance estimates in multi-armed bandits. Theor Comput Sci 410(19):1876–1902
Macready WG, Wolpert DH (1998) Bandit problems and the exploration/exploitation tradeoff. IEEE Trans Evol Comput 2(1):2–22
Koppell J (2011) International organization for standardization. Handb Transnatl Gov Inst Innov 41:289
Chen N, Zhao M, Gao K, Zhao J (2020) The physiological experimental study on the effect of different color of safety signs on a virtual subway fire escape—an exploratory case study of zijing mountain subway station. Int J Environ Res Public Health 17(16):5903
Zhu Y, Chen T, Ding N, Chraibi M, Fan W-C (2020) Follow the evacuation signs or surrounding people during building evacuation, an experimental study. Physica A 560:125156
Kavraki LE, Svestka P, Latombe J-C, Overmars MH (1996) Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Trans Robot Autom 12(4):566–580
LaValle SM et al (1998) Rapidly-exploring random trees: A new tool for path planning
Van Den Berg J, Guy SJ, Lin M, Manocha D (2011) Reciprocal n-body collision avoidance. In: Robotics research. Springer, pp 3–19
Lo S, Fang Z, Lin P, Zhi G (2004) An evacuation model: the sgem package. Fire Safety J 39(3):169–190
Wang Q, Liu H, Gao K, Zhang L (2019) Improved multi-agent reinforcement learning for path planning-based crowd simulation. IEEE Access 7:73841–73855
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant 61976127.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Pang, C., Lyu, L., Zhou, Q. et al. Environment-sensitive crowd behavior modeling method based on reinforcement learning. Appl Intell 53, 19356–19371 (2023). https://doi.org/10.1007/s10489-023-04509-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04509-4