An Artificial Neural Network Framework for Pedestrian Walking Behavior Modeling and Simulation

Peter Kielar; André Borrmann

doi:10.17815/CD.2020.62

Authors

Peter Kielar Chair of Computational Modeling and Simulation, Technische Universität München, Munich, Germany
André Borrmann Chair of Computational Modeling and Simulation, Technische Universität München, Munich, Germany

DOI:

https://doi.org/10.17815/CD.2020.62

Keywords:

pedestrian Simulation, framework, artificial neutral network, walking behavior

Abstract

Movement behavior models of pedestrian agents form the basis of computational crowd simulations. In contemporary research, a large number of models exist. However, there is still no walking behavior model that can address the various influence factors of movement behavior holistically. Thus, we endorse the use of artificial neural networks to develop walking behavior models because machine learning methods can integrate behavioral factors efficiently, automatically, and data-driven. In this paper, we support this approach by providing a framework that describes how to include artificial neural networks into a pedestrian research context. The framework comprises 5 phases: data, replay, training, simulation, and validation. Furthermore, we describe and discuss a prototype of the framework.

References

S. P. Hoogendoorn, and P. H. L. Bovy, „Pedestrian route-choice and activity scheduling theory and models”, Transportation Research Part B: Methodological, vol. 38, no. 2, pp. 169-190, 2004.

M. Bierlaire, and T. Robin, „Pedestrians Choices” in Pedestrian Behavior: Models, Data Collection and Applications, H. Timmermans, Ed. Emerald Group Publishing, 2009, pp. 1-26.

P. M. Kielar, „Kognitive Modellierung und computergestützte Simulation der räumlich-sequenziellen Zielauswahl von Fußgängern“, Ph.D. Dissertation, Technische Universität München, 2017.

P. M. Kielar and A. Borrmann, „Spice: A Cognitive Agent Framework for Computational Crowd Simulations in Complex Environments“, Autonomous Agents and Multi-Agent Systems, DOI: 10.1007/s10458-018-9383-2, 2018.

D. Helbing, L. Buzna, A. Johansson, and T. Werner, „Self-organized pedestrian crowd dynamics: Experiments, simulations, and design solutions“, Transportation Science, vol. 39, no. 1, pp. 1-24, 2005.

A. Portz, and A. Seyfried, „Analyzing Stop-and-Go Waves by Experiment and Modeling“, in International Conference on Pedestrian and Evacuation Dynamics, 2010, pp. 577-586.

D. Helbing, and P. Molnár. „Social force model for pedestrian dynamics“, Physical Review E, vol. 51, no. 5, pp. 4282-4286, 1995.

M. Moussaıïd, D. Helbing, and G. Theraulaz, „How simple rules determine pedestrian behavior and crowd disasters“, Proceedings of the National Academy of Sciences, vol. 108, no. 17, pp. 6884-6888, 2011.

J. Pettré, D. Wolinski, and A.-H. Olivier, „Velocity-Based Models for Crowd Simulation“, in International Conference on Pedestrian and Evacuation Dynamics, 2014, pp. 1065-1078.

V. J. Blue., and J. L. Adler, „Cellular automata microsimulation for modeling bi-directional pedestrian walkways“, Transportation Research Part B: Methodological, vol. 35, no. 3, pp. 293-312, 2001.

Y. Ma, E. W. M. Lee, and R. K. K. Yuen, „An Artificial Intelligence-Based Approach for Simulating Pedestrian Movement”, IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 11, pp. 3159-3170, 2016.

P. Shao, „A more realistic simulation of pedestrian based on cellular automata,” in IEEE International Workshop on Open-source Software for Scientific Computation, 2009, pp. 24-2.

C. Keip and K. Ries, „Dokumentation von Versuchen zur Personenstromdynamik“, Technical Report, Project Hermes, 2009.

P. M. Kielar, D. H. Biedermann, and A. Borrmann, „MomenTUMv2: a modular, extensible, and generic agent-based pedestrian behavior simulation framework“, Technical Report, Technische Unversität München, 2016.

M. Abadi et al., „TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems“, Whitepaper, https://www.tensorflow.org/, 2015.

W. Shao and D. Terzopoulos. „Autonomous pedestrians“, Graphical Models, vol. 69, no. 5-6, pp. 246-274, 2007.

S. Schwarzkopf, et al., „What Lab Eye Tracking Tells us about Wayfinding: A Comparison of Stationary and Mobile Eye Tracking in a Large Building Scenario“, in International Workshop Eye Tracking for Spatial Research in conjunction with COSIT, pp. 31-36, 2013

P. M. Kielar, D. H. Biedermann, A. Kneidl, and A. Borrmann, „A Unified Pedestrian Routing Model for Graph-Based Navigation Built on Cognitive Principles“, Transportmetrica A: Transport Science, vol. 14, no. 5, pp. 406-432, 2017.

P. M. Kielar and A. Borrmann, „Coupling Spatial Task Solving Models to Simulate Complex Pedestrian Behavior Patterns“, in International Conference on Pedestrian and Evacuation Dynamics, 2016, pp. 229-235.

A. L. Maas, A. Y. Hannun, and Y. Ng. Andrew, “Rectifier nonlinearities improve neural network acoustic models”, in Proc. ICML, vol. 30, no. 1, pp. 3-11, 2013

C. M. Bishop, Machine learning and pattern recognition, Springer, 2006.

M. A. Nielson, ANNs and Deep Learning, Determination Press, 2015.

M. D. Zeiler, „ADADELTA: An Adaptive Learning Rate Method”, arXiv:1212.5701, 2012.

S. Holl, „Methoden für die Bemessung der Leistungsfähigkeit multidirektional genutzter Fußverkehrsanlagen“, Ph.D. dissertation, Bergische Universität Wuppertal, 2016

H. He and E. A. Garcia, “Learning from imbalanced data”, IEEE Transactions on knowledge and data engineering, vol. 21, no. 9, pp. 1263-1284, 2009