A car-following model considering asymmetric driving behavior based on long short-term memory neural networks

Abstract Asymmetric driving behavior is a critical characteristic of human driving behaviors and has a significant impact on traffic flow. In consideration of the asymmetric driving behavior, this paper proposes a long short-term memory (LSTM) neural networks (NN) based car-following (CF) model to capture realistic traffic flow characteristics by incorporating the driving memory. The NGSIM data are used to calibrate and validate the proposed CF model. Meanwhile, three characteristics closely related to the asymmetric driving behavior are investigated: hysteresis, discrete driving, and intensity difference. The simulation results show the good performance of the proposed CF model on reproducing realistic traffic flow features. Moreover, to further demonstrate the superiority of the proposed CF model, two other CF models including recurrent neural network based CF model and asymmetric full velocity difference model, are compared with LSTM-NN model. The results reveal that LSTM-NN model can capture the asymmetric driving behavior well and outperforms other models.

[1]  Bing-Hong Wang,et al.  An asymmetric full velocity difference car-following model , 2008 .

[2]  Martin Treiber,et al.  Calibrating Car-Following Models by Using Trajectory Data , 2008, 0803.4063.

[3]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[4]  Gentry Lee,et al.  A Generalization of Linear Car-Following Theory , 1966, Oper. Res..

[5]  Dirk Helbing,et al.  GENERALIZED FORCE MODEL OF TRAFFIC DYNAMICS , 1998 .

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

[7]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

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

[9]  Hao Xu,et al.  Modeling the asymmetry in traffic flow (b): Macroscopic approach , 2013 .

[10]  A. Nahvi,et al.  A new psychological methodology for modeling real-time car following maneuvers , 2015 .

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

[12]  Yunpeng Wang,et al.  Long short-term memory neural network for traffic speed prediction using remote microwave sensor data , 2015 .

[13]  J Treiterer,et al.  THE HYSTERESIS PHENOMENON IN TRAFFIC FLOW , 1974 .

[14]  Ludovic Leclercq,et al.  A mechanism to describe the formation and propagation of stop-and-go waves in congested freeway traffic , 2010, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

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

[16]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[17]  Liang Zheng,et al.  A simple nonparametric car-following model driven by field data , 2015 .

[18]  Soyoung Ahn,et al.  A method to account for non-steady state conditions in measuring traffic hysteresis , 2013 .

[19]  Nicholas G. Polson,et al.  Deep learning for short-term traffic flow prediction , 2016, 1604.04527.

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

[21]  Motohiro Fujita,et al.  Car-following behavior with instantaneous driver–vehicle reaction delay: A neural-network-based methodology , 2013 .

[22]  Martin Treiber,et al.  Microscopic Calibration and Validation of Car-Following Models – A Systematic Approach , 2013, 1403.4990.

[23]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[24]  P. G. Gipps,et al.  A behavioural car-following model for computer simulation , 1981 .

[25]  Christopher Monterola,et al.  Asymmetric optimal-velocity car-following model , 2015 .

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

[27]  Hwasoo Yeo,et al.  Asymmetric Microscopic Driving Behavior Theory , 2008 .

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

[29]  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.

[30]  P. Wagner,et al.  Metastable states in a microscopic model of traffic flow , 1997 .

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

[32]  S.J.L. Ossen,et al.  Longitudinal driving behavior: Theory and empirics , 2008 .

[33]  Robert Herman,et al.  Traffic Dynamics: Analysis of Stability in Car Following , 1959 .

[34]  Hongchao Liu,et al.  Analysis of asymmetric driving behavior using a self-learning approach , 2013 .

[35]  Vincenzo Punzo,et al.  On the assessment of vehicle trajectory data accuracy and application to the Next Generation SIMulation (NGSIM) program data , 2011 .

[36]  Samuele Salti,et al.  Vehicle classification from low-frequency GPS data with recurrent neural networks , 2018, Transportation Research Part C: Emerging Technologies.

[37]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[38]  W. V. Winsum.  THE HUMAN ELEMENT IN CAR FOLLOWING MODELS , 1999 .

[39]  Heng Tao Shen,et al.  Video Captioning by Adversarial LSTM , 2018, IEEE Transactions on Image Processing.

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

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

[42]  Linsen Chong,et al.  Simulation of Driver Behavior with Agent-Based Back-Propagation Neural Network , 2011 .

[43]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

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

[45]  Bin Ran,et al.  A hybrid deep learning based traffic flow prediction method and its understanding , 2018 .

[46]  H Ozaki,et al.  REACTION AND ANTICIPATION IN THE CAR-FOLLOWING BEHAVIOR. , 1993 .

[47]  R. Jiang,et al.  Full velocity difference model for a car-following theory. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[48]  E. Montroll,et al.  Traffic Dynamics: Studies in Car Following , 1958 .

[49]  Zhongke Shi,et al.  Enhanced stability of car-following model upon incorporation of short-term driving memory , 2017, Commun. Nonlinear Sci. Numer. Simul..

[50]  Li Li,et al.  Vehicle headway modeling and its inferences in macroscopic/microscopic traffic flow theory: A survey , 2017 .

[51]  Björn W. Schuller,et al.  Online Driver Distraction Detection Using Long Short-Term Memory , 2011, IEEE Transactions on Intelligent Transportation Systems.

[52]  Tomer Toledo,et al.  Driving Behaviour: Models and Challenges , 2007 .

[53]  Marcello Montanino,et al.  Making NGSIM Data Usable for Studies on Traffic Flow Theory , 2013 .

[54]  Hojjat Adeli,et al.  Neural Networks in Civil Engineering: 1989–2000 , 2001 .

[55]  Hussein Dia,et al.  Neural Agent Car-Following Models , 2007, IEEE Transactions on Intelligent Transportation Systems.

[56]  Ali Ghaffari,et al.  A Modified Car-Following Model Based on a Neural Network Model of the Human Driver Effects , 2012, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[57]  Martin Treiber,et al.  The Intelligent Driver Model with Stochasticity -New Insights Into Traffic Flow Oscillations , 2017 .

[58]  Wei-Zhen Lu,et al.  Nonlinear analysis of a new car-following model accounting for the optimal velocity changes with memory , 2016, Commun. Nonlinear Sci. Numer. Simul..