Iterative Bayesian Estimation of Travel Times on Urban Arterials: Fusing Loop Detector and Probe Vehicle Data

On urban arterials, travel time estimation is challenging especially from various data sources. Typically, fusing loop detector data and probe vehicle data to estimate travel time is a troublesome issue while considering the data issue of uncertain, imprecise and even conflicting. In this paper, we propose an improved data fusing methodology for link travel time estimation. Link travel times are simultaneously pre-estimated using loop detector data and probe vehicle data, based on which Bayesian fusion is then applied to fuse the estimated travel times. Next, Iterative Bayesian estimation is proposed to improve Bayesian fusion by incorporating two strategies: 1) substitution strategy which replaces the lower accurate travel time estimation from one sensor with the current fused travel time; and 2) specially-designed conditions for convergence which restrict the estimated travel time in a reasonable range. The estimation results show that, the proposed method outperforms probe vehicle data based method, loop detector based method and single Bayesian fusion, and the mean absolute percentage error is reduced to 4.8%. Additionally, iterative Bayesian estimation performs better for lighter traffic flows when the variability of travel time is practically higher than other periods.

[1]  Toshiyuki Yamamoto,et al.  Feasibility of Using Taxi Dispatch System as Probes for Collecting Traffic Information , 2009, J. Intell. Transp. Syst..

[2]  Liping Fu,et al.  Assessing Expected Accuracy of Probe Vehicle Travel Time Reports , 1999 .

[3]  Isha Dhiman,et al.  Phase diagram of a continuum traffic flow model with a static bottleneck , 2015 .

[4]  Chuan Ding,et al.  Impacts of SOC on car-following behavior and travel time in the heterogeneous traffic system , 2016 .

[5]  Keechoo Choi,et al.  A Data Fusion Algorithm for Estimating Link Travel Time , 2002, J. Intell. Transp. Syst..

[6]  Martin L. Hazelton.  Estimating Vehicle Speed from Traffic Count and Occupancy Data , 2004 .

[7]  Kai Liu,et al.  COST-EFFECTIVENESS IN PROBE VEHICLE SYSTEMS , 2007 .

[8]  Simon Maskell,et al.  A Bayesian approach to fusing uncertain, imprecise and conflicting information , 2008, Inf. Fusion.

[9]  Tomio Miwa,et al.  Route Identification and Travel Time Prediction Using Probe-Car Data , 2004 .

[10]  Simon Cohen,et al.  Travel Time Estimation Between Loop Detectors and Fcd: A Compatibility Study on the Lille Network, France☆ , 2015 .

[11]  Fangfang Zheng,et al.  Uncertainty and Predictability of Urban Link Travel Time , 2010 .

[12]  S Lim,et al.  Data fusion algorithm improves travel time predictions , 2011 .

[13]  Kai Liu,et al.  Research on Installation Site of Loop Detectors for Link Travel Time Estimation , 2014 .

[14]  Baibing Li.  Recursive estimation of average vehicle time headway using single inductive loop detector data , 2012 .

[15]  John Rice,et al.  Accurate estimation of travel times from single-loop detectors 1 1 Funding for this research was pro , 1998 .

[16]  Henry Leung,et al.  Data fusion in intelligent transportation systems: Progress and challenges - A survey , 2011, Inf. Fusion.

[17]  El Faouzi Nour-Eddin.  Bayesian and Evidential Approaches for Traffic Data Fusion: Methodological Issues and Case Study , 2006 .

[18]  Tomio Miwa,et al.  Modeling Distribution of Travel Time in Signalized Road Section Using Truncated Distribution , 2014 .

[19]  Takayuki Morikawa,et al.  Use of Probe Vehicle Data to Determine Joint Probability Distributions of Vehicle Location and Speed on an Arterial Road , 2014 .

[20]  Fangfang Zheng,et al.  Urban link travel time estimation based on sparse probe vehicle data , 2013 .

[21]  Alexander Mendiburu,et al.  A Review of Travel Time Estimation and Forecasting for Advanced Traveler Information Systems , 2012 .

[22]  Takashi Nagatani,et al.  Driving behavior and control in traffic system with two kinds of signals , 2014 .

[23]  Didier Colle,et al.  Real-time traffic monitoring by fusing floating car data with stationary detector data , 2015, 2015 International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS).

[24]  Hai-Jun Huang,et al.  A Multilane Traffic Flow Model Accounting for Lane Width, Lane-Changing and the Number of Lanes , 2014 .

[25]  黒田 孝次,et al.  Highway Capacity Manual改訂の動向--テイラ-教授の講演より , 1984 .

[26]  J. V. van Lint,et al.  Improving a Travel-Time Estimation Algorithm by Using Dual Loop Detectors , 2003 .

[27]  Liping Fu,et al.  Decomposing Travel Times Measured by Probe-based Traffic Monitoring Systems to Individual Road Segments , 2008 .

[28]  Masao Kuwahara,et al.  Implementing kinematic wave theory to reconstruct vehicle trajectories from fixed and probe sensor data , 2011 .

[29]  Liping Fu,et al.  Reducing bias in probe-based arterial link travel time estimates , 2002 .

[30]  Rua Luís,et al.  Journal of Intelligent Transportation Systems: Technology, Planning, and Operations , 2013 .

[31]  Ashish Bhaskar,et al.  Fusing Loop Detector and Probe Vehicle Data to Estimate Travel Time Statistics on Signalized Urban Networks , 2011, Comput. Aided Civ. Infrastructure Eng..

[32]  Benjamin Coifman,et al.  Estimating travel times and vehicle trajectories on freeways using dual loop detectors , 2002 .

[33]  Haris N. Koutsopoulos,et al.  Travel time estimation for urban road networks using low frequency probe vehicle data , 2013, Transportation Research Part B: Methodological.

[34]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .