Towards data-driven car-following models

Abstract Car following models have been studied with many diverse approaches for decades. Nowadays, technological advances have significantly improved our traffic data collection capabilities. Conventional car following models rely on mathematical formulas and are derived from traffic flow theory; a property that often makes them more restrictive. On the other hand, data-driven approaches are more flexible and allow the incorporation of additional information to the model; however, they may not provide as much insight into traffic flow theory as the traditional models. In this research, an innovative methodological framework based on a data-driven approach is proposed for the estimation of car-following models, suitable for incorporation into microscopic traffic simulation models. An existing technique, i.e. locally weighted regression (loess), is defined through an optimization problem and is employed in a novel way. The proposed methodology is demonstrated using data collected from a sequence of instrumented vehicles in Naples, Italy. Gipps’ model, one of the most extensively used car-following models, is calibrated against the same data and used as a reference benchmark. Optimization issues are raised in both cases. The obtained results suggest that data-driven car-following models could be a promising research direction.

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

[2]  Mike McDonald,et al.  Car-following: a historical review , 1999 .

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

[4]  Haneen Farah,et al.  Latent class model for car following behavior , 2012 .

[5]  Roberta Di Pace,et al.  Development and testing of a fully Adaptive Cruise Control system , 2013 .

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

[7]  Haris N. Koutsopoulos,et al.  A Synthesis of emerging data collection technologies and their impact on traffic management applications , 2011 .

[8]  H. Greenberg An Analysis of Traffic Flow , 1959 .

[9]  R. E. Wilson,et al.  An analysis of Gipps's car-following model of highway traffic , 2001 .

[10]  Ronghui Liu Traffic Simulation with DRACULA , 2010 .

[11]  Nitin H. Vaidya,et al.  A vehicle-to-vehicle communication protocol for cooperative collision warning , 2004, The First Annual International Conference on Mobile and Ubiquitous Systems: Networking and Services, 2004. MOBIQUITOUS 2004..

[12]  Eleni I. Vlahogianni,et al.  Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach , 2005 .

[13]  H T Fritzsche,et al.  A MODEL FOR TRAFFIC SIMULATION , 1994 .

[14]  Haris N. Koutsopoulos,et al.  Dynamic data-driven local traffic state estimation and prediction , 2013 .

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

[16]  Mike McDonald,et al.  Determinants of following headway in congested traffic , 2009 .

[17]  Vassilis Gikas,et al.  Towards distribution-based calibration for traffic simulation , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[18]  Partha Chakroborty,et al.  Evaluation of the General Motors based car-following models and a proposed fuzzy inference model , 1999 .

[19]  R. Sollacher,et al.  Multi-anticipative car-following model , 1999 .

[20]  Axel Klar,et al.  Derivation of Continuum Traffic Flow Models from Microscopic Follow-the-Leader Models , 2002, SIAM J. Appl. Math..

[21]  K. Ahmed Modeling drivers' acceleration and lane changing behavior , 1999 .

[22]  Lei Yu,et al.  AN EVALUATION OF TRAFFIC SIMULATION MODELS FOR SUPPORTING ITS DEVELOPMENT , 2000 .

[23]  P Hidas A car-following model for urban traffic simulation , 1998 .

[24]  Ronald R. Mourant,et al.  Toward More Realistic Driving Behavior Models for Autonomous Vehicles in Driving Simulators , 2003 .

[25]  Rahim F Benekohal,et al.  Comparison of Car-Following Models for Simulation , 1999 .

[26]  Marjan Bilban,et al.  Age affects drivers' response times. , 2009, Collegium antropologicum.

[27]  J. W. C. van Lint,et al.  Online Learning Solutions for Freeway Travel Time Prediction , 2008, IEEE Transactions on Intelligent Transportation Systems.

[28]  W. Cleveland,et al.  Regression by local fitting: Methods, properties, and computational algorithms , 1988 .

[29]  David Shinar,et al.  Minimum and Comfortable Driving Headways: Reality versus Perception , 2001, Hum. Factors.

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

[31]  R. E. Wilson,et al.  Bifurcations and multiple traffic jams in a car-following model with reaction-time delay , 2005 .

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

[33]  Fei-Yue Wang,et al.  Data-Driven Intelligent Transportation Systems: A Survey , 2011, IEEE Transactions on Intelligent Transportation Systems.

[34]  Mark W. Watson Introduction to econometrics. , 1968 .

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

[36]  Alejandra Medina Flintsch,et al.  A rule-based neural network approach to model driver naturalistic behavior in traffic , 2013 .

[37]  Punzo Vincenzo,et al.  May we trust results of car-following models calibration based on trajectory data? , 2012 .

[38]  L. A. Pipes An Operational Analysis of Traffic Dynamics , 1953 .

[39]  W. Cleveland Robust Locally Weighted Regression and Smoothing Scatterplots , 1979 .

[40]  Vincenzo Punzo,et al.  Human-Like Adaptive Cruise Control Systems through a Learning Machine Approach , 2009 .

[41]  Gaetano Fusco,et al.  Artificial Neural Network Models for Car Following: Experimental Analysis and Calibration Issues , 2014, J. Intell. Transp. Syst..

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

[43]  Heikki Summala,et al.  Brake reaction times and driver behavior analysis , 2000 .

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

[45]  Gunnar Flötteröd,et al.  Stability Analysis of a Multi Phase Car-Following Model , 2013 .

[46]  Haris N. Koutsopoulos,et al.  Estimation of Traffic Dynamics Models with Machine-Learning Methods , 2006 .

[47]  E. Huang,et al.  Real-time multi-sensor multi-source network data fusion using dynamic traffic assignment models , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[48]  E. Kometani,et al.  On the stability of traffic flow , 1958 .

[49]  Stephen Dunne,et al.  Regime-Based Short-Term Multivariate Traffic Condition Forecasting Algorithm , 2012 .

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

[51]  Hesham Rakha,et al.  Procedure for Calibrating Gipps Car-Following Model , 2009 .

[52]  Bart De Schutter,et al.  Models for traffic control , 2002 .

[53]  Ziyou Gao,et al.  A new car-following model: full velocity and acceleration difference model , 2005 .

[54]  Dirk Helbing,et al.  Delays, inaccuracies and anticipation in microscopic traffic models , 2006 .

[55]  Ioanna Spyropoulou,et al.  SIMULATION USING GIPPS' CAR-FOLLOWING MODEL—AN IN-DEPTH ANALYSIS , 2007 .

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

[57]  Hariharan Subramanian,et al.  Estimation of car-following models , 1996 .

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

[59]  G R Preziotti,et al.  ALERT ALGORITHM DEVELOPMENT PROGRAM: NHTSA REAR-END COLLISION ALERT ALGORITHM , 2002 .

[60]  Gordon F. Newell,et al.  A simplified car-following theory: a lower order model , 2002 .

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

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

[63]  Wilhelm Leutzbach,et al.  Introduction to the Theory of Traffic Flow , 1987 .

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

[65]  L Yu,et al.  AN EVALUATION OF TRAFFIC SIMULATION MODELS FOR SUPPORTING INTELLIGENT TRANSPORTATION SYSTEMS (ITS) DEVELOPMENT , 2000 .

[66]  Shiro Sawada GENERALIZED OPTIMAL VELOCITY MODEL FOR TRAFFIC FLOW , 2001, nlin/0105054.

[67]  Mike McDonald,et al.  Driver behaviour and traffic modelling. Are we looking at the right issues? , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[68]  T. Nakatsuji,et al.  MICROSCOPIC TRAFFIC DATA WITH REAL-TIME KINEMATIC GLOBAL POSITIONING SYSTEM , 2005 .

[69]  Harilaos N. Koutsopoulos,et al.  A microscopic traffic simulator for evaluation of dynamic traffic management systems , 1996 .

[70]  Andreas Tapani,et al.  Comparison of car-following models , 2004 .

[71]  D. Rubinfeld,et al.  Econometric models and economic forecasts , 2002 .

[72]  Marc Green,et al.  "How Long Does It Take to Stop?" Methodological Analysis of Driver Perception-Brake Times , 2000 .

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

[74]  J. Barceló Fundamentals of traffic simulation , 2010 .

[75]  Kay Fitzpatrick,et al.  Driver Perception–Brake Response in Stopping Sight Distance Situations , 1998 .

[76]  Jordi Casas,et al.  Dynamic Network Simulation with AIMSUN , 2005 .

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

[78]  Eleni I. Vlahogianni,et al.  Statistical methods versus neural networks in transportation research: Differences, similarities and some insights , 2011 .

[79]  Mohammed Elhenawy,et al.  Dynamic travel time prediction using data clustering and genetic programming , 2014 .

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

[81]  H. J. Van Zuylen,et al.  Accurate freeway travel time prediction with state-space neural networks under missing data , 2005 .

[82]  Vincenzo Punzo,et al.  Part 1: Traffic Flow Theory and Car Following: Nonstationary Kalman Filter for Estimation of Accurate and Consistent Car-Following Data , 2005 .

[83]  Eleni I. Vlahogianni,et al.  Temporal Evolution of Short‐Term Urban Traffic Flow: A Nonlinear Dynamics Approach , 2008, Comput. Aided Civ. Infrastructure Eng..

[84]  Partha Chakroborty,et al.  CAR-FOLLOWING MODEL BASED ON FUZZY INFERENCE SYSTEM , 1992 .

[85]  Tsuna Sasaki,et al.  ON THE STABIliTY OF TRAFFIC FLOW (REPORT-I) , 1958 .

[86]  Louis A. Pipes,et al.  Car following models and the fundamental diagram of road traffic , 1967 .

[87]  Hani S. Mahmassani,et al.  Driver Car-Following Behavior: From Discrete Event Process to Continuous Set of Episodes , 2008 .

[88]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[89]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[90]  G. Johansson,et al.  Drivers' Brake Reaction Times , 1971, Human factors.