Long memory is important: A test study on deep-learning based car-following model

Abstract Whether long memory effect plays an important role in car-following models remains unsolved. In this paper, we study the possible relationship between long memory effect and hysteresis phenomena observed in practice. Especially, we have compared the performance of different deep learning based car-following models that take various time-scale historical information as inputs. Test show that hysteresis phenomena can be correctly simulated only by car-following models with long memory. So, we argue that car-following models should embed long memory effect appropriately.

[1]  Xiqun Chen,et al.  Phase Diagram Analysis Based on a Temporal-Spatial Queueing Model , 2012, IEEE Transactions on Intelligent Transportation Systems.

[2]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[3]  L. C. Edie.  Car-Following and Steady-State Theory for Noncongested Traffic , 1961 .

[4]  Haixin Wang,et al.  Empirical evidence and stability analysis of the linear car-following model with gamma-distributed memory effect , 2016 .

[5]  Bing-Hong Wang,et al.  Abnormal hysteresis effect and phase transitions in a velocity-difference dependent randomization CA model , 2007 .

[6]  Benjamin Coifman,et al.  A critical evaluation of the Next Generation Simulation (NGSIM) vehicle trajectory dataset , 2017 .

[7]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[8]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[9]  Dirk Helbing,et al.  Adaptive cruise control design for active congestion avoidance , 2008 .

[10]  Mao-Bin Hu,et al.  Understanding the structure of hyper-congested traffic from empirical and experimental evidences , 2015 .

[11]  X. Chen,et al.  A global optimization algorithm for trajectory data based car-following model calibration , 2016 .

[12]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[13]  Nagatani.  Bunching of cars in asymmetric exclusion models for freeway traffic. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[14]  Dirk Helbing,et al.  Memory effects in microscopic traffic models and wide scattering in flow-density data. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[15]  Monica Menendez,et al.  Use of Microsimulation for Examination of Macroscopic Fundamental Diagram Hysteresis Patterns for Hierarchical Urban Street Networks , 2015 .

[16]  Vincenzo Punzo,et al.  Steady-State Solutions and Multiclass Calibration of Gipps Microscopic Traffic Flow Model , 2007 .

[17]  Dirk Helbing,et al.  Three-phase traffic theory and two-phase models with a fundamental diagram in the light of empirical stylized facts , 2010, 1004.5545.

[18]  Masao Kuwahara,et al.  Microsimulation of Freeway Ramp Merging Processes Under Congested Traffic Conditions , 2007, IEEE Transactions on Intelligent Transportation Systems.

[19]  Marcello Montanino,et al.  Thirty Years of Gipps’ Car-Following Model , 2012 .

[20]  Dirk Helbing,et al.  Enhanced intelligent driver model to access the impact of driving strategies on traffic capacity , 2009, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[21]  C. Daganzo,et al.  Possible explanations of phase transitions in highway traffic , 1999 .

[22]  Zonglian He,et al.  A figure-eight hysteresis pattern in macroscopic fundamental diagrams and its microscopic causes , 2015 .

[23]  L. C. Davis,et al.  Modifications of the optimal velocity traffic model to include delay due to driver reaction time , 2003 .

[24]  D. Gazis,et al.  Nonlinear Follow-the-Leader Models of Traffic Flow , 1961 .

[25]  A. Skabardonis,et al.  Understanding stop-and-go traffic in view of asymmetric traffic theory , 2009 .

[26]  Serge P. Hoogendoorn,et al.  A Microscopic Investigation Into the Capacity Drop: Impacts of Longitudinal Behavior on the Queue Discharge Rate , 2017, Transp. Sci..

[27]  Silviu-Iulian Niculescu,et al.  Stability of car following with human memory effects and automatic headway compensation , 2010, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[28]  Martin A. Tanner,et al.  From EM to Data Augmentation: The Emergence of MCMC Bayesian Computation in the 1980s , 2010, 1104.2210.

[29]  T. Nagatani.  Stabilization and enhancement of traffic flow by the next-nearest-neighbor interaction. , 1999, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[30]  G. F. Newell.  THEORIES OF INSTABILITY IN DENSE HIGHWAY TRAFFIC , 1962 .

[31]  Antoine Tordeux,et al.  Adaptive Time Gap Car-Following Model , 2010 .

[32]  D. Helbing,et al.  Theoretical vs. empirical classification and prediction of congested traffic states , 2009, 0903.0929.

[33]  Xiaobo Qu,et al.  A recurrent neural network based microscopic car following model to predict traffic oscillation , 2017 .

[34]  Boris S. Kerner,et al.  Criterion for traffic phases in single vehicle data and empirical test of a microscopic three-phase traffic theory , 2006 .

[35]  Fei-Yue Wang,et al.  Capturing Car-Following Behaviors by Deep Learning , 2018, IEEE Transactions on Intelligent Transportation Systems.

[36]  K. Hasebe,et al.  Analysis of optimal velocity model with explicit delay , 1998, patt-sol/9805002.

[37]  R. E. Wilson,et al.  Global bifurcation investigation of an optimal velocity traffic model with driver reaction time. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[38]  Jorge A. Laval.  Hysteresis in traffic flow revisited: An improved measurement method , 2011 .

[39]  R. B. Potts,et al.  Car-Following Theory of Steady-State Traffic Flow , 1959 .

[40]  Helbing,et al.  Congested traffic states in empirical observations and microscopic simulations , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[41]  F. Atay.  Distributed delays facilitate amplitude death of coupled oscillators. , 2003, Physical review letters.

[42]  H. M. Zhang.  A mathematical theory of traffic hysteresis , 1999 .

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

[44]  Michael J. Cassidy,et al.  Driver memory: Motorist selection and retention of individualized headways in highway traffic , 1998 .

[45]  H. M. Zhang,et al.  A Car-Following Theory for Multiphase Vehicular Traffic Flow , 2003 .

[46]  Lu Lu,et al.  A Comparison of Phase Transitions Produced by PARAMICS, TransModeler, and VISSIM , 2010, IEEE Intelligent Transportation Systems Magazine.

[47]  Hai-Jun Huang,et al.  A CELLULAR AUTOMATA MODEL OF TRAFFIC FLOW WITH CONSIDERATION OF THE INERTIAL DRIVING BEHAVIOR , 2010 .

[48]  Dirk Helbing,et al.  Empirical Features of Congested Traffic States and Their Implications for Traffic Modeling , 2007, Transp. Sci..

[49]  Boris S. Kerner,et al.  Cellular automata approach to three-phase traffic theory , 2002, cond-mat/0206370.

[50]  G. F. Newell.  Nonlinear Effects in the Dynamics of Car Following , 1961 .