Modeling Real-Time Adaptive Pedestrian Behavior Based on Social Force Model

Jinsoo Kim; Changhoon Shin; Hoontae Park

doi:10.7470/jkst.2026.44.1.038

All Issue

2026 Vol.44, Issue 1 Preview Page Next Page

Article

Modeling Real-Time Adaptive Pedestrian Behavior Based on Social Force Model Social Force Model 기반 실시간 적응형 보행자 행태 모형 개발

28 February 2026. pp. 38-52

PDF XML

Abstract

This study proposes a real-time adaptive pedestrian behavior model that integrates a speed-based dynamic parameter adjustment algorithm with a visibility-based temporary path setting algorithm to overcome the limitations of the conventional social force model, which is widely used in pedestrian simulations. The traditional model, based on fixed parameters, lacks adaptability and fails to reproduce pedestrian behavior realistically in high-density or complex environments. The proposed model addresses these shortcomings by dynamically adjusting key parameters according to the ratio of a pedestrian's current speed to the desired speed and by correcting driving force through visibility-based temporary goal updating. To evaluate its performance, six scenarios―including low and high density, unidirectional and bidirectional flows, bottleneck sections, and complex paths―were designed to compare the proposed model with the conventional model. The results demonstrated that the proposed model outperforms the traditional model in terms of collision avoidance, maintenance of comfort levels, bottleneck passage, and navigation in complex routes. Furthermore, in the validation stage based on empirical comparison using the relationships among pedestrian occupancy space, walking speed, and pedestrian flow, the proposed model consistently produced lower errors than the conventional model, thereby verifying its precision and ability to generalize.

Keywords

parameter adjustment

pedestrian behavior model

pedestrian simulation

social force model

vision-based local pathfinding

본 연구는 보행 시뮬레이션의 대표 모형으로 활용되는 사회역학모형(Social Force Model)의 한계를 극복하기 위해 보행자 속도 기반 동적 파라미터 조정 알고리즘과 국지적 가시성 기반 임시 경로 설정 알고리즘을 통합한 실시간 적응형 보행자 행태 모형을 제안한다. 전통적인 사회역학모형은 고정된 파라미터 체계를 전제로 하여 다양한 보행 환경 변화에 대한 적응력이 제한적이며, 특히 고밀도 상황이나 복잡한 경로 조건에서 현실적인 보행 행태를 재현하지 못하는 한계를 지니고 있다. 반면 본 연구에서 제안하는 모형은 보행자의 현재 속도와 목표 속도의 비율에 따라 주요 파라미터를 실시간으로 조정하고, 가시성 영역을 기반으로 임시 목표 방향을 갱신하며 추진력을 보정함으로써 기존 모형의 한계를 보완한다. 본 연구에서는 저밀도/고밀도, 단방향/양방향, 병목 구간, 복잡 경로 등의 6개 시나리오를 설정해 제안 모형과 기존 모형의 성능을 비교 분석하였으며, 분석 결과 제안 모형이 보행자의 회피 기동, 쾌적 상태 확보, 병목 통과, 복잡 경로 진행 부문에서 월등한 성능을 보였다. 또한 보행점유공간, 보행속도, 보행교통류율의 관계식에 기반하여 실증 데이터를 통한 유효성 검증 단계에서도 제안 모형이 기존 모형과 비교하여 일관되게 낮은 오차를 보임으로써 모형의 정밀성 및 일반화 가능성을 입증하였다.

키워드

파라미터 조정

보행 행태 모형

보행 시뮬레이션

사회역학모형

가시성 기반 경로 탐색

References

Baglietto G., Parisi, D. R. (2011), Continuous-space Automaton Model for Pedestrian Dynamics, Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 83(5), 056-117.

10.1103/PhysRevE.83.056117

Benedikt M. L. (1979), To Take Hold of Space: Isovists and Isovist Fields, Environment and Planning B: Planning and Design, 6(1), 47-65.

10.1068/b060047

Caillou P., Gaudou B., Grignard A., Truong C. Q., Taillandier P. (2017), A Simple-to-use BDI Architecture for Agent-Based Modeling and Simulation, In Advances in Social Simulation 2015, Cham: Springer International Publishing, 15-28.

10.1007/978-3-319-47253-9_2

Chen H., Ding J., Li Y., Wang Y., Zhang X. (2024), Social Physics Informed Diffusion Model for Crowd Simulation, AAAI Conference on Artificial Intelligence, 38(1), 474-482.

10.1609/aaai.v38i1.27802

Chen X., Treiber M., Kanagaraj V., Li H. (2018), Social Force Models for Pedestrian Traffic-State of The Art, Transport Reviews, 38(5), 625-653.

10.1080/01441647.2017.1396265

Chiraibi M., Seyfried A., Schadschneider A. (2010), Generalized Centrifugal-Force Model for Pedestrian Dynamics, Physical Review E―Statistical, Nonlinear, and Soft Matter Physics, 82(4), 046-111.

10.1103/PhysRevE.82.046111

Farina F., Fontanelli D., Garulli A., Giannitrapani A., Prattichizzo D. (2017), Walking Ahead: The Headed Social Force Model, PloS One, 12(1), e0169734.

10.1371/journal.pone.016973428076435PMC5226724

Fruin J. J. (1971), Pedestrian Planning and Design.

Gracias J. S., Parnell G. S., Specking E., Pohl E. A., Buchanan R. (2023), Smart Cities—A Structured Literature Review, Smart Cities, 6(4), 1719-1743.

10.3390/smartcities6040080

Guo R., Tang T. (2012), A Simulation Model for Pedestrian Flow Through Walkways With Corners, Simulation Modelling Practice and Theory, 21(1), 103-113.

10.1016/j.simpat.2011.10.007

Han M. J., Jung D. J., Lee Y. I., Lee S. B. (2022) Modeling Pedestrian Movement Behavior Using Social Force Model and Fuzzy Inference, J. Korean Soc. Transp., 40(2), Korean Society of Transportation, 218-229.

10.7470/jkst.2022.40.2.218

Han S. J., Jang S. E., Jin J. W. (2019), Understanding of Pedestrian Traffic, Kinema-in Co. Ltd., Seoul, Korea. (보행교통의 이해)

Helbing D., Molnar P. (1995), Social Force Model for Pedestrian Dynamics, Physical Review E, 51(5), 4282-4286.

10.1103/PhysRevE.51.4282

Helbing D., Molnar P. (1998), Self-Organization Phenomea in Pedestrian Crowds, Self-Organization of Complex Structures: From Individual to Collective Dynamics, Gordon and Breach.

Hoogendoorn S. P. (2001), Microscopic Pedestrian Wayfinding and Dynamics Modeling, Pedestrian and Evacuation Dynamics, 123-154.

Johora F. T., Kraus P., Müller J. P. (2017), Dynamic Path Planning and Movement Control in Pedestrian Simulation, arXiv Preprint arXiv:1709.08235.

Kim D., Labate D., Mily K., Quaini A. (2024), Data Driven Learning to Enhance A Kinetic Model of Distressed Crowd Dynamics, arXiv Preprint arXiv:2411.12974.

10.1142/S021820252540007X

Kim J. Y., Yeo H. S. (2019), Pedestrian Simulation Model for Path Planning with Anticipation Behavior, J. Korean Soc. Transp., 37(5), Korean Society of Transportation, 410-421.

10.7470/jkst.2019.37.5.410

Kovacic M., Marvin S., While A. (2024), Regulating Sidewalk Delivery Robots as A Disruptive New Urban Technology, Urban Geography, 45(7), 1236-1255.

10.1080/02723638.2023.2275426

Lee J. H. (2008), Research Trends of Microscopic Pedestrian Simulation Model, Journal of Transport Technology and Policy, 5(4), 23-33.

Li J., Zhang H., Ni Z. (2020), Improved Social Force Model Based on Navigation Points for Crowd Emergent Evacuation, Journal of Information Processing Systems, 16(6).

10.3745/JIPS.04.0199

Müller-Eie D., Kosmidis I. (2023), Sustainable Mobility in Smart Cities: A Document Study of Mobility Initiatives of Mid-Sized Nordic Smart Cities, European Transport Research Review, 15(1), 36.

10.1186/s12544-023-00610-4

Patil S., Van Den Berg J., Curtis S., Lin M. C., Manocha D. (2010), Directing Crowd Simulations Using Navigation Fields, IEEE Transactions on Visualization and Computer Graphics, 17(2), 244-254.

10.1109/TVCG.2010.33

Peng J., Wei Z., Chen Y., Wang S., Li Y., Wang S. et al. (2025), Heterogeneous Pedestrian Simulation in Commercial Complexes: When Attractive Potential Meets Social Force, IEEE Transactions on Intelligent Transportation Systems.

10.1109/TITS.2025.3543613

Penn A., Turner A. (2002), Space Syntax Based Agent Simulation, Springer-Verlag.

Yan D., Ding G., Huang K., Bai C., He L., Zhang L. (2024), Enhanced Crowd Dynamics Simulation With Deep Learning and Improved Social Force Model, Electronics, 13(5), 934.

10.3390/electronics13050934

Zhang Y., Chai Z., Lykotrafitis G. (2021), Deep Reinforcement Learning With A Particle Dynamics Environment Applied to Emergency Evacuation of A Room With Obstacles, Physica A: Statistical Mechanics and its Applications, 571, 125845.

10.1016/j.physa.2021.125845

Information

Publisher :Korean Society of Transportation
Publisher(Ko) :대한교통학회
Journal Title :Journal of Korean Society of Transportation
Journal Title(Ko) :대한교통학회지
Volume : 44
No :1
Pages :38-52
Received Date : 2025-08-26
Revised Date : 2025-09-12
Accepted Date : 2025-10-13
DOI :https://doi.org/10.7470/jkst.2026.44.1.038

Journal of Korean Society of Transportation ISSN:1229-1366(Print) 2234-4217(Online) 대한교통학회지

All Issue