Advertisement

Tolerance Coefficient Based Improvement of Pedestrian Social Force Model

  • Ruiping Wang
  • Xiao SongEmail author
  • Junhua Zhou
  • Xu Li
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1094)

Abstract

In this paper, pedestrian evacuation is investigated by using an extended social force model that considers patience factor which can solve the situation pedestrian in the corner stay where they are until everyone is finished or there is an occasional gap. In the simulation of indoor evacuation, we add the endurance coefficient attribute to pedestrians. When pedestrians are blocked in a corner that is not conducive to passage, there will be temporary waiting. When more and more people behind them are found passing through the narrow gate, pedestrians generate greater “social forces” to enable them to pass through the narrow gate and avoid long waits. Besides, LSTM is used to learn scenario data by normalization of relative positions among pedestrians, transferring velocity vector to scalar and incorporating more path planning information, and thus to make it more adaptive to realistic scenarios. The results shows more realistic speed density curve and generates less trajectory fluctuations compared with social force model.

Keywords

Pedestrian behavior Long short term memory Social force 

References

  1. 1.
    Zhong, J., Luo, L., Cai, W., Lees, M.: EA-based evacuation planning using agent-based crowd simulation. In: Proceedings of the 2014Google Scholar
  2. 2.
    Song, X., Ma, L., Ma, Y., Yang, C., Ji, H.: Selfishness- and selflessness-based models of pedestrian room evacuation. Phys. A 447(6), 455–466 (2016)CrossRefGoogle Scholar
  3. 3.
    Shende, A., Singh, M.P., Kachroo, P.: Optimization-based feedback control for pedestrian evacuation from an exit corridor. IEEE Trans. Intell. Transp. Syst. 12(4), 1167–1176 (2011)CrossRefGoogle Scholar
  4. 4.
    Tsai, J., et al.: ESCAPES- evacuation simulation with children, authorities, parents, emotions, and social comparison. In: Tumer, K., Yolum, P., Sonenberg, L., Stone, P. (eds.) Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2011. Innovative Applications Track, Valencia (2011)Google Scholar
  5. 5.
    Takayama, Y., Miwa, H.: Quick evacuation method for evacuation navigation system in poor communication environment at the time of disaster. In: IEEE International Conference on Intelligent Networking and Collaborative Systems, pp. 415–421 (2014) Google Scholar
  6. 6.
    Hui, F., Pel, A.J., Hoogendoorn, S.P.: Optimization of evacuation traffic management with intersection control constraints. IEEE Trans. Intell. Transp. Syst. 16(1), 376–386 (2015)CrossRefGoogle Scholar
  7. 7.
    Fujihara, A., Miwa, H.: Necessary condition for self-organized follow-me evacuation guidance using opportunistic networking. In: IEEE International Conference on Intelligent Networking and Collaborative Systems, pp. 213–221 (2014)Google Scholar
  8. 8.
    Kinugasa, S., Izumi, T., Nakatani, Y.: Evaluation of a support system for large area tourist evacuation guidance: Kyoto simulation results. In: IEEE SCIS-ISIS 2012, Kobe, Japan, pp. 439–445 (2012)Google Scholar
  9. 9.
    Caggianese, G., Erra, U.: Parallel hierarchical A* for multi agent-based simulation on the GPU. In: an Mey, D., et al. (eds.) Euro-Par 2013. LNCS, vol. 8374, pp. 513–522. Springer, Heidelberg (2014).  https://doi.org/10.1007/978-3-642-54420-0_50CrossRefGoogle Scholar
  10. 10.
    Schadschneider, A., Klingsch, W., Klupfel, H., Kretz, T., et al.: Evacuation dynamics: empirical results, modeling and applications, pp. 517–551 (2008). https://arxiv.org/abs/08021620CrossRefGoogle Scholar
  11. 11.
    Langston, P.A., Masling, R., Asmar, B.N.: Crowd dynamics discrete element multi-circle model. Saf. Sci. 44, 395–417 (2006)CrossRefGoogle Scholar
  12. 12.
    Kang, J., Jeong, I.-J., Kwun, J.-B.: Optimal facility-final exit assignment algorithm for building complex evacuation. Comput. Ind. Eng. 85(4), 169–176 (2015)CrossRefGoogle Scholar
  13. 13.
    Song, X., Sun, J., Xie, H., et al.: Characteristic time based social force model improvement and exit assignment strategy for pedestrian evacuation. Phys. A Stat. Mech. Appl. 505(9), 530–548 (2018)CrossRefGoogle Scholar
  14. 14.
    Song, X., Han, D., Sun, J., Zhang, Z.: A data-driven neural network approach to simulate pedestrian movement. Phys. A Stat. Mech. Appl. 509(11), 827–844 (2018)CrossRefGoogle Scholar
  15. 15.
    Song, X., Xie, H., Sun, J., Han, D., Cui, Y., Chen, B.: Simulation of pedestrian rotation dynamics near crowded exits. IEEE Trans. Intell. Transp. Syst. (2018).  https://doi.org/10.1109/TITS.2018.2873118CrossRefGoogle Scholar
  16. 16.
    Liu, J., Song, X., Sun, J., Xie, Z.: Global A* for pedestrian room evacuation simulation. In: 2018 IEEE International Conference on Big Data and Smart Computing, vol. 1, Shanghai, China, pp. 573–577 (2008)Google Scholar
  17. 17.
    Luo, L., Zhou, S., et al.: Agent based human behavior modeling for crowd simulation. Comput. Animat. Virtual Worlds 19, 271–281 (2008)CrossRefGoogle Scholar
  18. 18.
    Bruneau, J., Pettré, J.: Energy-efficient mid-term strategies for collision avoidance in crowd simulation. In: ACM SCA (2015)Google Scholar
  19. 19.
    Luo, L., Chai, C., Ma, J., et al.: Proactive crowd: modelling proactive steering behaviours for agent-based crowd simulation. Comput. Graph. Forum 37(1), 375–388 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Automation Science and Electrical EngineeringBeihang UniversityBeijingChina
  2. 2.State Key Laboratory of Intelligent Manufacturing System TechnologyBeijing Institute of Electronic System EngineeringBeijingChina

Personalised recommendations