Learning-based game theoretical framework for modeling pedestrian motion

Pedestrians are active agents that undergo a repeated decision-making process while walking. These anisotropic, interactive, and feedback-oriented agents observe their surroundings, anticipate the future state of the network, and decide on their next movements accordingly, while ensuring a collision-free path toward their destination. Aiming at capturing these behavioral characteristics of human agents while walking, the present study puts forward a learning-based game theoretical approach for modeling pedestrian motion in dynamic environments. The proposed game structure provides a technical foundation to analyze optimal decision-making by pedestrians where the outcome of the game for each player's choice depends primarily on the strategies played by other players. This, in turn, ensures the frequently observed collision avoidance behavior of pedestrians while walking. The influence of nearby pedestrians on one's decision-making process and the feedback-oriented behavior of human agents are also captured via incorporating a learning structure. Optimum moving strategies are selected based on Nash equilibria calculations, where everyone is playing optimally given what all other players are playing. The validation results using real-world trajectories of pedestrians provide evidence of the model's capability in describing pedestrian motion and walking behaviors at microscopic as well as macroscopic levels.

[1]  D. Helbing.  Traffic and related self-driven many-particle systems , 2000, cond-mat/0012229.

[2]  John Preston,et al.  Forecasting the effects of road user charge by stochastic agent-based modelling , 2008 .

[3]  Hani S. Mahmassani,et al.  A hybrid simulation-assignment modeling framework for crowd dynamics in large-scale pedestrian facilities , 2016 .

[4]  Xiaoning Zhang,et al.  Integrated daily commuting patterns and optimal road tolls and parking fees in a linear city , 2008 .

[5]  M. Burger,et al.  Mean field games with nonlinear mobilities in pedestrian dynamics , 2013, 1304.5201.

[6]  S Bouzat,et al.  Game theory in models of pedestrian room evacuation. , 2013, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  Serge P. Hoogendoorn,et al.  Pedestrian Flow Modeling by Adaptive Control , 2004 .

[8]  Michel Bierlaire,et al.  Discrete Choice Models for Pedestrian Walking Behavior , 2006 .

[9]  Luca Bruno,et al.  Non-local first-order modelling of crowd dynamics: A multidimensional framework with applications , 2010, 1003.3891.

[10]  Dirk Helbing,et al.  Simulating dynamical features of escape panic , 2000, Nature.

[11]  Meead Saberi,et al.  Exploring Areawide Dynamics of Pedestrian Crowds , 2014 .

[12]  Dirk Helbing,et al.  Self-Organizing Pedestrian Movement , 2001 .

[13]  Serge P. Hoogendoorn,et al.  State-of-the-art crowd motion simulation models , 2013 .

[14]  L. Shapley,et al.  Fictitious Play Property for Games with Identical Interests , 1996 .

[15]  Alexandra Kirsch,et al.  Strategies of locomotor collision avoidance. , 2013, Gait & posture.

[16]  Dirk Helbing.  A Fluid-Dynamic Model for the Movement of Pedestrians , 1992, Complex Syst..

[17]  Hairong Dong,et al.  Guided crowd dynamics via modified social force model , 2014 .

[18]  Christian Dogbé,et al.  Modeling crowd dynamics by the mean-field limit approach , 2010, Math. Comput. Model..

[19]  J. Pettré,et al.  Minimal predicted distance: a common metric for collision avoidance during pairwise interactions between walkers. , 2012, Gait & posture.

[20]  Armin Seyfried,et al.  Collecting pedestrian trajectories , 2013, Neurocomputing.

[21]  Andreas Schadschneider,et al.  Friction effects and clogging in a cellular automaton model for pedestrian dynamics. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  T. Nagatani,et al.  Jamming transition in pedestrian counter flow , 1999 .

[23]  José Holguín-Veras,et al.  Optimal tolls for multi-class traffic: Analytical formulations and policy implications , 2009 .

[24]  Marie-Therese Wolfram,et al.  On a mean field game approach modeling congestion and aversion in pedestrian crowds , 2011 .

[25]  Julien Pettré,et al.  Collision avoidance between two walkers: role-dependent strategies. , 2013, Gait & posture.

[26]  Chelsea C. White,et al.  The dynamic shortest path problem with anticipation , 2007, Eur. J. Oper. Res..

[27]  Michael G.H. Bell,et al.  A game theory approach to measuring the performance reliability of transport networks , 2000 .

[28]  Bernhard Friedrich,et al.  A multi-layer social force approach to model interactions in shared spaces using collision prediction , 2017 .

[29]  Armin Seyfried,et al.  Collective phenomena in crowds—Where pedestrian dynamics need social psychology , 2017, PloS one.

[30]  L. F. Henderson.  On the fluid mechanics of human crowd motion , 1974 .

[31]  A. Borzì,et al.  Pedestrian motion modelled by Fokker–Planck Nash games , 2017, Royal Society Open Science.

[32]  Hani S. Mahmassani,et al.  Modeling Lane-Changing Behavior in a Connected Environment: A Game Theory Approach , 2015 .

[33]  Michel Bierlaire,et al.  Specification, estimation and validation of a pedestrian walking behaviour model , 2007 .

[34]  Mao-Bin Hu,et al.  Pedestrian flow dynamics in a lattice gas model coupled with an evolutionary game. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[35]  N. Bellomo,et al.  ON THE MODELLING CROWD DYNAMICS FROM SCALING TO HYPERBOLIC MACROSCOPIC MODELS , 2008 .

[36]  Michael G.H. Bell.  Games, Heuristics, and Risk Averseness in Vehicle Routing Problems , 2004 .

[37]  P. Lions,et al.  Jeux à champ moyen. I – Le cas stationnaire , 2006 .

[38]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[39]  Serge P. Hoogendoorn,et al.  Simulation of pedestrian flows by optimal control and differential games , 2003 .

[40]  Victor J. Blue,et al.  Cellular automata microsimulation for modeling bi-directional pedestrian walkways , 2001 .

[41]  Martin Buss,et al.  Understanding Human Avoidance Behavior: Interaction-Aware Decision Making Based on Game Theory , 2016, Int. J. Soc. Robotics.