Anterior|Siguiente

Digital twins of micro crowd： The concept， framwork， and methods

  • role： First author第一作者
  • Affiliation：

    National Engineering Research Center for Geomatics, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

  • Email：liwh@aircas.ac.cn
  • Introduction：李文航，研究方向为微观人群行为模拟。E-mail： liwh@aircas.ac.cn
LI Wenhang,  
  • Affiliation：

    National Engineering Research Center for Geomatics, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

GONG Jianhua,  
  • Affiliation：

    National Engineering Research Center for Geomatics, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

HUANG Lin,  
  • Affiliation：

    National Engineering Research Center for Geomatics, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

MA Haonan

resumen

raditional geography/GIS research on the spatiotemporal behavior of people focus on the meso and macro scale, while the research on the micro spatiotemporal behavior is relatively insufficient. To address this problem, first, a new concept of micro crowd digital twins is proposed. The idea is to map the real crowd and their behaviors into the virtual space, calculate and simulate the crowd behavior, mine the evolution mechanism, discover the operation rules, predict the trends, locate the abnormalities in advance, propose optimization strategies, and improve the efficiency and safety of real crowd and real society. The micro crowd digital twins can be divided into two stages, namely, special digital twins and general digital twins, according to whether they are synchronized in time between the real crowd and the virtual one.Then, the technical basis and research status of micro crowd digital twins are summarized from the aspects of crowd behavior experimental approaches, basic behavior/scenario behavior modeling, and typical applications. (1) According to the types of places and events, the crowd behavior experiment approaches can be divided into “real place-real event,” “real place-simulated event,” “simulated place-simulated event,” and “virtual place-virtual event.” (2) The status of crowd behavior modeling is summarized, which can be divided into basic micro crowd behavior models and scenario behavior models. The basic micro crowd behavior models are to model individual behaviors in a simple and abstracted space, with general interactions between individuals and obstacles. The scenario behavior models are to model crowd behaviors in complex and detailed space, with comprehensive interactions between crowds, environments, and geo-events. The advantages and disadvantages of typical basic micro crowd behavior models such as Social Force Model, Velocity Obstacle model (ORCA model), and Artificial Intelligence (AI) model are analyzed. (3) A typical case of micro crowd digital twins in a school evacuation is analyzed. The platform of digital twins of crowds is developed to simulate and examine the disordered behaviors and orderly behaviors, and the spatial layout of the school and the crowd evacuation strategies are optimized. In this manner, the special micro crowd digital twin is realized.Finally, the future research of crowd behavior experiments, crowd modeling, and theoretical system of micro human-land relationship are awaited from the perspective of geography. (1) New approaches such as credible micro crowd behavior experiment should be developed. In the crowd behavior experiments, the behavior errors caused by subjective and objective factors in crowd experiments need to be calibrated qualitatively and quantitatively, and the deviation correction algorithm should be developed to obtain reliable experimental results. (2) New micro crowd behavior modeling ideas should be proposed. Behavior models should focus on not only emergency disordered behaviors but also those orderly behaviors under the constraints of social rules and social orders in common daily conditions. The rules of individual “self-interest” used in traditional behavior modeling also need to be expanded, and the crowd interests should be introduced to build behavioral models considering “self-interest” and “altruism” rules. (3) The deterministic and stochastic characteristics of crowd behaviors should be considered. In view of the complementary characteristics of AI behavior models and traditional mathematical behavior models as well as the advantages of AI model in stochastic modeling, they can be combined to achieve this goal. (4) On the basis of the digital twinning of micro crowd, the innovative theoretical system of “micro human-land relationship” can be developed in the future, which will break through the traditional concept of “macro human-land relationship” modeling, and will make the theoretical system and modeling system of the study of human-land relationship in geography more complete. Then, the research of geography, geographic information system, and virtual geographic environments on modeling of micro crowd behaviors, micro spaces, and the applications can be promoted.

palabra clave

remote sensing;Digital twins of micro crowd;micro spatiotemporal crowd behavior;behavior modelling;VGE;geography

References

  1. 1.
    Arita C and Schadschneider A. 2011. Dynamical analysis of the exclusive queueing process. Physical Review E, 83(5): 051128
  2. 2.
    Cao S C, Song W G and Lv W. 2016. Modeling pedestrian evacuation with guiders based on a multi-grid model. Physics Letters A, 380(4): 540-547
  3. 3.
    Chen C K, Li J and Zhang D. 2012. Study on evacuation behaviors at a T-shaped intersection by a force-driving cellular automata model. Physica A: Statistical Mechanics and its Applications, 391(7): 2408-2420
  4. 4.
    Cisek M and Kapalka M. 2014. Evacuation route assessment model for optimization of evacuation in buildings with active dynamic signage system. Transportation Research Procedia, 2: 541-549
  5. 5.
    Ding N, Ma Y H, Dong D P and Wang Y D. 2021. Experiment and simulation study of emergency evacuation during violent attack in classrooms. Journal of Safety Science and Resilience, 2(4): 208-221
  6. 6.
    Gao J, Zhang J J, He J, Gong J H and Zhao J C. 2020. Experiment and simulation of pedestrian’s behaviors during evacuation in an office. Physica A: Statistical Mechanics and its Applications, 545: 123749
  7. 7.
    Gong G R, Du Y and Ouyang F. 2009. Method of achieving terrain verisimilitude in virtual geo-environment. Journal of Geomatics Science and Technology, 26(6): 458-461
  8. 8.
    Gong J H and Lin H. 2001. Virtual Geographic Environments-A Geographic Perspective on Online Virtual Reality. Beijing: Higher Education Press
  9. 9.
    Gong J H and Lin H. 2006. Exploring human-oriented GIS. Geomatics and Information Science of Wuhan University, 31(8): 704-708
  10. 10.
    Gong J H. 2008. Exploring human-oriented geovisualization. Journal of Remote Sensing (in Chinese), 12(5): 772-779
  11. 11.
    Goodchild M F. 2007. Citizens as voluntary sensors: spatial data infrastructure in the world of Web 2.0. International Journal of Spatial Data Infrastructures Research, 2: 24-32
  12. 12.
    Helbing D, Farkas I and Vicsek T. 2000. Simulating dynamical features of escape panic. Nature, 407(6803): 487-490
  13. 13.
    Haghani M, Ejtemai O, Sarvi M, Sobhani A, Burd M and Aghabayk K. 2014. Random utility models of pedestrian crowd exit selection based on SP-off-RP experiments. Transportation Research Procedia, 2: 524-532
  14. 14.
    Helbing D and Molnár P. 1995. Social force model for pedestrian dynamics. Physical Review E, 51(5): 4282-4286
  15. 15.
    Huang L, Gong J H and Li W H. 2021. A perception model for optimizing and evaluating evacuation guidance systems. ISPRS International Journal of Geo-Information, 10(2): 54
  16. 16.
    Hughes R L. 2002. A continuum theory for the flow of pedestrians. Transportation Research Part B: Methodological, 36(6): 507-535
  17. 17.
    Huo F Z, Li Y F, Li C and Ma Y P. 2022. An extended model describing pedestrian evacuation considering pedestrian crowding and stampede behavior. Physica A: Statistical Mechanics and its Applications, 604: 127907
  18. 18.
    Jiang B C, You X, Xia Q and Tian J P. 2013. Voxels and the Construction of a virtual geographic environment. Geomatics and Information Science of Wuhan University, 38(7): 875-878
  19. 19.
    Krasuski A and Krenski K. 2019. A-Evac: the evacuation simulator for stochastic environment. Fire Technology, 55(5): 1707-1732
  20. 20.
    Li M F, Zhao Y X, He L R, Chen W X and Xu X F. 2015a. The parameter calibration and optimization of social force model for the real-life 2013 Ya’an earthquake evacuation in China. Safety Science, 79: 243-253
  21. 21.
    Li W H, Gong J H, Yu P and Shen S. 2016a. Modeling, simulation and analysis of group trampling risks during escalator transfers. Physica A: Statistical Mechanics and its Applications, 444: 970-984
  22. 22.
    Li W H, Gong J H, Yu P, Shen S, Li R and Duan Q S. 2014. Simulation and analysis of individual trampling risk during escalator transfers. Physica A: Statistical Mechanics and its Applications, 408: 119-133
  23. 23.
    Li W H, Gong J H, Yu P, Shen S, Li R and Duan Q S. 2015b. Simulation and analysis of congestion risk during escalator transfers using a modified social force model. Physica A: Statistical Mechanics and its Applications, 420: 28-40
  24. 24.
    Li W H, Gong J H, Zhang L H and Zhou J P. 2007. Mobile oriented collaborative virtual geographic studio. Geomatics and Information Science of Wuhan University, 32(9): 817-820
  25. 25.
    Li W H, Li Y, Yu P, Gong J H, Fan H K, Zhang D, Huang L and Zhang G Y. 2022. Modeling orderly queuing behavior with bending effects. Physica A: Statistical Mechanics and its Applications, 601: 127608
  26. 26.
    Li W H, Li Y, Yu P, Gong J H and Shen S. 2016b. The Trace Model: a model for simulation of the tracing process during evacuations in complex route environments. Simulation Modelling Practice and Theory, 60: 108-121
  27. 27.
    Li W H, Li Y, Yu P, Gong J H, Shen S, Huang L and Liang J M. 2017. Modeling, simulation and analysis of the evacuation process on stairs in a multi-floor classroom building of a primary school. Physica A: Statistical Mechanics and its Applications, 469: 157-172
  28. 28.
    Liang J M, Gong J H and Li Y. 2015. Realistic rendering for physically based shallow water simulation in virtual geographic environments (VGEs). Annals of GIS, 21(4): 301-312
  29. 29.
    Liang M D, Xu J, Jia L M and Qin Y. 2020. An improved model of passenger merging in a Y-shaped passage. Physica A: Statistical Mechanics and its Applications, 540: 123233
  30. 30.
    Lin H and Gong J H. 2002. On virtual geographic environments. Acta Geodaetica et Cartographica Sinica, 31(1): 1-6
  31. 31.
    Lin H, Gong J H and Shi J J. 2003. From maps to GIS and VGE—A discussion on the evolution of the geographic language. Geography and Geo-Information Science, 19(4): 18-23
  32. 32.
    Lin H, Huang F R, Lu X J, Hu M Y, Xu B L and Wu L. 2010. Preliminary study on virtual geographic environment cognition and representation. Journal of Remote Sensing (in Chinese), 14(4): 822-838
  33. 33.
    Lin H, Zhang C X, Chen M and Zheng X Q. 2016. On virtual geographic environments for geographic knowledge representation and sharing. Journal of Remote Sensing (in Chinese), 20(5): 1290-1298
  34. 34.
    Lin H, Zhu Q and Chen M. 2018. The being and non-being generate each other, and the virtual and the real are mutually interactive—The progress of virtual geographic environments (VGE) studies in last 20 years. Acta Geodaetica et Cartographica Sinica, 47(8): 1027-1030
  35. 35.
    Liu Q. 2018. A social force model for the crowd evacuation in a terrorist attack. Physica A: Statistical Mechanics and its Applications, 502: 315-330
  36. 36.
    Liu X D, Song W G, Fu L B and Fang Z M. 2016. Experimental study of pedestrian inflow in a room with a separate entrance and exit. Physica A: Statistical Mechanics and its Applications, 442: 224-238
  37. 37.
    Liu Y. 2016. Revisiting several basic geographical concepts: a social sensing perspective. Acta Geographica Sinica, 71(4): 564-575
  38. 38.
    Liu Y X and Mao Z L. 2022. An experimental study on the critical state of herd behavior in decision-making of the crowd evacuation. Physica A: Statistical Mechanics and its Applications, 595: 127087
  39. 39.
    Lopez-Carmona M A and Garcia A P. 2022. Adaptive cell-based evacuation systems for leader-follower crowd evacuation. Transportation Research Part C: Emerging Technologies, 140: 103699
  40. 40.
    Lovreglio R, Dillies E, Kuligowski E, Rahouti A and Haghani M. 2022. Exit choice in built environment evacuation combining immersive virtual reality and discrete choice modelling. Automation in Construction, 141: 104452
  41. 41.
    Lü G N. 2011. Geographic analysis-oriented Virtual Geographic Environment: framework, structure and functions. Science China Earth Sciences, 54(5): 733-743
  42. 42.
    Ma P J, Jiang Y Q, Zhu J F and Chen B K. 2019. The effect of escape signs on the pedestrians evacuation. Physica A: Statistical Mechanics and its Applications, 534: 121133
  43. 43.
    Martinez-Gil F, Lozano M and Fernández F. 2014. MARL-Ped: a multi-agent reinforcement learning based framework to simulate pedestrian groups. Simulation Modelling Practice and Theory, 47: 259-275
  44. 44.
    Meng B, Huang S and Yin Q. 2019. Spatial and temporal distribution characteristics of residents' depart times elasticity in Beijing. Journal of Geo-information Science, 21(1): 107-117
  45. 45.
    Mnih V, Kavukcuoglu K, Silver D, Rusu A A, Veness J, Bellemare M G, Graves A, Riedmiller M, Fidjeland A K, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S and Hassabis D. 2015. Human-level control through deep reinforcement learning. Nature, 518(7540): 529-533
  46. 46.
    Pan B L, Wang J H, Ge Y and Ma M G. 2019. Spatial structure and population flow analysis in Chengdu-Chongqing urban agglomeration based on Weibo check-in big data. Journal of Geo-information Science, 21(1): 68-76
  47. 47.
    Pei T, Huang Q, Wang X, Chen X, Liu Y X, Song C, Chen J and Zhou C H. 2021. Big geodata aggregation: connotation, classification, and framework. National Remote Sensing Bulletin, 25(11): 2153-2162
  48. 48.
    Peng H, Du Y Y, Yi J W, Liu Z and Wang H M. 2019. Mining urban-rural spatial interaction pattern from mobile data of Beijing. Journal of Geo-Information Science, 21(1): 97-106
  49. 49.
    Poulos A, Tocornal F, De La Llera J C and Mitrani-Reiser J. 2018. Validation of an agent-based building evacuation model with a school drill. Transportation Research Part C: Emerging Technologies, 97: 82-95
  50. 50.
    Qu Y C, Xiao Y, Wu J J, Tang T and Gao Z Y. 2018. Modeling detour behavior of pedestrian dynamics under different conditions. Physica A: Statistical Mechanics and its Applications, 492: 1153-1167
  51. 51.
    Ran H C, Sun L H and Gao X Z. 2014. Influences of intelligent evacuation guidance system on crowd evacuation in building fire. Automation in Construction, 41: 78-82
  52. 52.
    Schulman J, Wolski F, Dhariwal P, Radford A and Klimov O. 2017. Proximal policy optimization algorithms. arXiv: 1707.06347
  53. 53.
    Silver D, Huang A, Maddison C J, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T and Hassabis D. 2016. Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587): 484-489
  54. 54.
    Snape J, Berg J V D, Guy S J and Manocha D. 2011. The hybrid reciprocal velocity obstacle. IEEE Transactions on Robotics, 27(4): 696-706
  55. 55.
    Sticco I M, Frank G A, Cerrotta S and Dorso C O. 2017. Room evacuation through two contiguous exits. Physica A: Statistical Mechanics and its Applications, 474: 172-185
  56. 56.
    Tang L Y, Chen C C and Lin D. 2010. HLA-based virtual forest environment construction. Geomatics and Information Science of Wuhan University, 35(3): 353-355
  57. 57.
    Tang L Y, Peng X M, Chen C C, Huang H Y and Lin D. 2019. Three-dimensional forest growth simulation in virtual geographic environments. Earth Science Informatics, 12(1): 31-41
  58. 58.
    Tang M, Jia H F, Ran B and Li J. 2016. Analysis of the pedestrian arching at bottleneck based on a bypassing behavior model. Physica A: Statistical Mechanics and its Applications, 453: 242-258
  59. 59.
    Torrey L. 2010. Crowd simulation via multi-agent reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 6(1): 89-94
  60. 60.
    Treuille A, Cooper S and Popović Z. 2006. Continuum crowds. ACM Transactions on Graphics, 25(3): 1160-1168
  61. 61.
    van den Berg J, Guy S J, Lin M and Manocha D. 2011. Reciprocal n-body collision avoidance//14th International Symposium of Robotic Research. Astoria Hotel: Springer: 3-19
  62. 62.
    Von Krüchten C and Schadschneider A. 2017. Empirical study on social groups in pedestrian evacuation dynamics. Physica A: Statistical Mechanics and its Applications, 475: 129-141
  63. 63.
    Wang L Y, Wu J S and Li W F. 2019. Usage patterns and driving mechanisms of public bicycle systems in small and medium-sized cities based on space-time data mining. Journal of Geo-information Science, 21(1): 25-35
  64. 64.
    Wang W L, Zhang J J, Li H C and Xie Q M. 2020. Experimental study on unidirectional pedestrian flows in a corridor with a fixed obstacle and a temporary obstacle. Physica A: Statistical Mechanics and its Applications, 560: 125188
  65. 65.
    Wang Z, Fang C and Wang Y. 2017. Design of aquatic ecological security evaluation system based on virtual geographic environment//Proceedings of the 2017 7th International Conference on Manufacturing Science and Engineering. Zhuhai: Atlantis Press: 51-54
  66. 66.
    Watkins C J C H and Dayan P. 1992. Q-learning. Machine Learning, 8: 279-292
  67. 67.
    Wu P H, Wang Y, Jiang J C, Wang J H and Zhou R. 2022. Evacuation optimization of a typical multi-exit subway station: overall partition and local railing. Simulation Modelling Practice and Theory, 115: 102425
  68. 68.
    Xu B L, Lin H, Zhu J and Deng L H. 2009. Construction of a virtual geographic environment for air pollution simulation in Pearl River Delta. Geomatics and Information Science of Wuhan University, 34(6): 636-640
  69. 69.
    Xu B L, Rao Y, Chen Y T, You L and Lin H. 2018. Role model-based geo-collaboration of virtual geographic environments. Geomatics and Information Science of Wuhan University, 43(10): 1580-1587
  70. 70.
    Yao Y S and Lu W. 2021. Children’s evacuation behavioural data of drills and simulation of the horizontal plane in kindergarten. Safety Science, 133: 105037
  71. 71.
    Yi J X, Pan S L and Chen Q. 2020. Simulation of pedestrian evacuation in stampedes based on a cellular automaton model. Simulation Modelling Practice and Theory, 104: 102147
  72. 72.
    Yu P. 2021. Modeling and simulation of cruise emergency evacuation process for layout optimization. China Safety Science Journal, 31(9): 142-149
  73. 73.
    Zhang Z P, Wan G and Liu J. 2015. Research of the space environment simulation technology. Engineering of Surveying and Mapping, 24(2): 15-18, 23
  74. 74.
    Zhao X F, Li Z B, Li P and Wen J L. 2009. Spatial cognition in virtual environment. Science of Surveying and Mapping, 34(S1): 35-37
  75. 75.
    Zhou J P, Gong J H, Chen Z and Du W. 2005. Study on collaborative virtual geographic environment system for multi-user interaction and communication. Geography and Geo-Information Science, 21(5): 33-37
  76. 76.
    Zhu J, Lin H, Lin W S and Xu B L. 2008. Study on virtual geographic environment for simulation of air pollution dispersion. Journal of System Simulation, 20(S1): 176-179, 186

Leer el texto completo

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website