BusTr: Predicting Bus Travel Times from Real-Time Traffic

We present BusTr, a machine-learned model for translating road traffic forecasts into predictions of bus delays, used by Google Maps to serve the majority of the world's public transit systems where no official real-time bus tracking is provided. We demonstrate that our neural sequence model improves over DeepTTE, the state-of-the-art baseline, both in performance (-30% MAPE) and training stability. We also demonstrate significant generalization gains over simpler models, evaluated on longitudinal data to cope with a constantly evolving world.

[1]  Q. Shen,et al.  Examination of Traveler Responses to Real-Time Information about Bus Arrivals using Panel Data , 2008 .

[2]  Wasan Pattara-Atikom,et al.  Bus arrival time prediction at any distance of bus route using deep neural network model , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[3]  Yi-Hua Zhang,et al.  Improved iterative prediction for multiple stop arrival time using a support vector machine , 2012 .

[4]  Kari Watkins,et al.  An experiment evaluating the impacts of real-time transit information on bus riders in Tampa, Florida , 2014 .

[5]  Daniel Mendoza,et al.  Modeling net effects of transit operations on vehicle miles traveled, fuel consumption, carbon dioxide, and criteria air pollutant emissions in a mid-size US metro area: findings from Salt Lake City, UT , 2019, Environmental Research Communications.

[6]  Rahul Pathak,et al.  Public transit access and the changing spatial distribution of poverty , 2017 .

[7]  Raj Chetty,et al.  The Impacts of Neighborhoods on Intergenerational Mobility I: Childhood Exposure Effects , 2016 .

[8]  Jing Ying,et al.  Bus arrival time prediction with real-time and historic data , 2017, Cluster Computing.

[9]  Lelitha Vanajakshi,et al.  Bus travel time prediction: a log-normal auto-regressive (AR) modelling approach , 2019, Transportmetrica A: Transport Science.

[10]  Athanasios V. Vasilakos,et al.  Mobile Crowd Sensing for Traffic Prediction in Internet of Vehicles , 2016, Sensors.

[11]  Guiyuan Jiang,et al.  Bus Travel Speed Prediction using Attention Network of Heterogeneous Correlation Features , 2019, SDM.

[12]  D. Sculley,et al.  Google Vizier: A Service for Black-Box Optimization , 2017, KDD.

[13]  Anne Aguiléra,et al.  Passenger transport mode share in cities: exploration of actual and future trends with a worldwide survey , 2014 .

[14]  Giuseppe Salvo,et al.  Bus speed estimation by neural networks to improve the automatic fleet management , 2007 .

[15]  Majid Sarvi,et al.  Journal of Intelligent Transportation Systems: Technology, Planning, and Operations , 2011 .

[16]  Alan Borning,et al.  Where Is My Bus? Impact of mobile real-time information on the perceived and actual wait time of transit riders , 2011 .

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Ricardo Giesen,et al.  Real-time prediction of bus travel speeds using traffic shockwaves and machine learning algorithms , 2016 .

[19]  Salina Yoon.  Who's on Board? , 2006 .

[20]  C Terence,et al.  The Value of Time and Reliability: Measurement from a Value Pricing Experiment , 2003 .

[21]  Richard Barnes.  Optimal orientations of discrete global grids and the Poles of Inaccessibility , 2020, Int. J. Digit. Earth.

[22]  Alan Borning,et al.  OneBusAway: results from providing real-time arrival information for public transit , 2010, CHI.

[23]  Marcin Budka,et al.  Survey of ETA prediction methods in public transport networks , 2019, ArXiv.

[24]  William Vincent,et al.  The Potential for Bus Rapid Transit to Reduce Transportation-Related CO2 Emissions , 2006 .

[25]  Genevieve Giuliano,et al.  Does service reliability determine transit patronage? Insights from the Los Angeles Metro bus system , 2015 .

[26]  Permalink.  Title The Value of Time and Reliability : Measurement from a Value Pricing Experiment , 2004 .

[27]  Jules White,et al.  Real-Time and Predictive Analytics for Smart Public Transportation Decision Support System , 2016, 2016 IEEE International Conference on Smart Computing (SMARTCOMP).

[28]  O. Edenhofer,et al.  Climate change 2014 : mitigation of climate change , 2014 .

[29]  Xiaobo Liu,et al.  Using automatic passenger counter data in bus arrival time prediction , 2007 .

[30]  Michael L. Anderson.  Subways, Strikes, and Slowdowns: The Impacts of Public Transit on Traffic Congestion , 2013 .

[31]  Cristina Heghedus.  PhD Forum: Forecasting Public Transit Using Neural Network Models , 2017, 2017 IEEE International Conference on Smart Computing (SMARTCOMP).

[32]  Joseph Hyskell.  Who'S On Board? , 2010 .

[33]  Antorweep Chakravorty,et al.  Neural Network Frameworks. Comparison on Public Transportation Prediction , 2019, 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).

[34]  D. Sculley,et al.  Bayesian Optimization for a Better Dessert , 2017 .

[35]  M. Amaç Güvensan,et al.  A Novel Segment-Based Approach for Improving Classification Performance of Transport Mode Detection , 2017, Sensors.

[36]  Wei Cao,et al.  When Will You Arrive? Estimating Travel Time Based on Deep Neural Networks , 2018, AAAI.

[37]  K. Sahr,et al.  Geodesic Discrete Global Grid Systems , 2003 .

[38]  Steven Farber,et al.  Constructing a routable retrospective transit timetable from a real-time vehicle location feed and GTFS , 2017 .

[39]  Marco Gruteser,et al.  LiveTraVeL: Real-time matching of transit vehicle trajectories to transit routes at scale , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[40]  R. Jeong,et al.  Bus arrival time prediction using artificial neural network model , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[41]  Kaan Ozbay,et al.  Impact of Traffic Congestion on Bus Travel Time in Northern New Jersey , 2004 .