Prediction of Pedestrian Speed with Artificial Neural Networks

Pedestrian behaviours tend to depend on the type of facility. Therefore accurate predictions of pedestrians movements in complex geometries (including corridor, bottleneck or intersection) are difficult to achieve for classical models with few parameters. Artificial neural networks have multiple parameters and are able to identify various types of patterns. They could be a suitable alternative for forecasts. We aim in this paper to present first steps testing this approach. We compare estimations of pedestrian speed with a classical model and a neural network for combinations of corridor and bottleneck experiments. The results show that the neural network is able to differentiate the two geometries and to improve the estimation of pedestrian speeds when the geometries are mixed.

[1]  Matjaz Perc,et al.  Modeling the Seasonal Adaptation of Circadian Clocks by Changes in the Network Structure of the Suprachiasmatic Nucleus , 2012, PLoS Comput. Biol..

[2]  Silvio Savarese,et al.  Social LSTM: Human Trajectory Prediction in Crowded Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Mohcine Chraibi,et al.  Generalized centrifugal-force model for pedestrian dynamics. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[4]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[5]  E. Ziegel,et al.  Bootstrapping: A Nonparametric Approach to Statistical Inference , 1993 .

[6]  Hubert Klüpfel,et al.  Evacuation Dynamics: Empirical Results, Modeling and Applications , 2009, Encyclopedia of Complexity and Systems Science.

[7]  Mohcine Chraibi,et al.  Jamming transitions in force-based models for pedestrian dynamics. , 2015, Physical review. E, Statistical, nonlinear, and soft matter physics.

[8]  Wei Lv,et al.  A Two-Dimensional Optimal Velocity Model for Unidirectional Pedestrian Flow Based on Pedestrian's Visual Hindrance Field , 2013, IEEE Transactions on Intelligent Transportation Systems.

[9]  Winnie Daamen,et al.  Modelling passenger flows in public transport facilities , 2004 .

[10]  Akihiro Nakayama,et al.  Instability of pedestrian flow and phase structure in a two-dimensional optimal velocity model. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  Jitendra Malik,et al.  Recurrent Network Models for Human Dynamics , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[12]  Martin Treiber,et al.  Traffic Flow Dynamics , 2013 .

[13]  Hai-Jun Huang,et al.  A microscopic pedestrian-simulation model and its application to intersecting flows , 2010 .

[14]  Nasser Sadati,et al.  Solving robot motion planning problem using Hopfield neural network in a fuzzified environment , 2002, 2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291).

[15]  Bernhard Steffen,et al.  New Insights into Pedestrian Flow Through Bottlenecks , 2009, Transp. Sci..

[16]  Manoranjan Parida,et al.  Analysis of interrelationship between pedestrian flow parameters using artificial neural network , 2015 .

[17]  Eric Krotkov,et al.  How DARPA structures its robotics programs to improve locomotion and navigation , 2007, CACM.

[18]  Nakayama,et al.  Dynamical model of traffic congestion and numerical simulation. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[19]  Yi Ma,et al.  An Artificial Intelligence-Based Approach for Simulating Pedestrian Movement , 2016, IEEE Transactions on Intelligent Transportation Systems.

[20]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[21]  Daniel R. Parisi,et al.  Influence of bottleneck lengths and position on simulated pedestrian egress , 2017 .

[22]  Lubos Buzna,et al.  Self-Organized Pedestrian Crowd Dynamics: Experiments, Simulations, and Design Solutions , 2005, Transp. Sci..

[23]  Cécile Appert-Rolland,et al.  Traffic Instabilities in Self-Organized Pedestrian Crowds , 2012, PLoS Comput. Biol..

[24]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[25]  A. Seyfried,et al.  The fundamental diagram of pedestrian movement revisited , 2005, physics/0506170.

[26]  Jun Zhang,et al.  Experimental studies of pedestrian flows under different boundary conditions , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[27]  Stefan Fritsch,et al.  neuralnet: Training of Neural Networks , 2010, R J..

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