Sage Journals: Discover world-class research

Abstract

This paper quantifies the safety benefits of a proposed near real-time traffic control system for highway–rail grade crossing (HRGC) utilizing emerging safety technologies in connected and autonomous vehicles (CAV). The connected-vehicle technologies that have applications at a railroad crossing include vehicle-based technologies (railroad crossing violation warning, automated or semi-automated braking system, drowsiness/distracted driver alert) and technologies that require cooperation from the railroad industry (advanced warnings to trains about an occupied crossing). This paper provides a methodology to quantify the reduction in crashes as safety technologies become prevalent. It first identifies crash characteristics that enable the classification of crashes as preventable crashes or not. This classification is used to train machine learning models to estimate the likelihood of a potential crash being preventable. The machine learning model is used along with the zero inflated negative binomial with empirical Bayes system (ZINEBS) model to estimate the expected accident count at a crossing when a percentage of vehicles in the traffic stream is CAV. This paper presents case studies for three crossings to show the reduction in crashes with the increase in the percentage of connected vehicles in the traffic stream. It also presents the general trend in the reduction expected by analyzing 50 crossings of each warning device type.

Keywords

data and data science data analytics machine learning (artificial intelligence)supervised learning analysis modeling multivariate safety rail highway/rail grade crossings prediction warning

Get full access to this article

View all access options for this article.

References

Operation Lifesaver. Collisions Casualties by Year. Operation Lifesaver, 2021. https://oli.org/track-statistics/collisions-casualties-year.

Safety. Rail Safety Week2020. https://iseptaphilly.com/blog/railsafetyweek2020. Accessed April 14, 2021.

Federal Railroad Administration. Highway-Rail Crossing & Trespassing Fact Sheet. FRA, 2016. https://railroads.dot.gov/sites/fra.dot.gov/files/docs/newsroom/186/rrx-fact-sheet-final12716.pdf.

Mok

S. C.

Savage

Why Has Safety Improved at Rail-Highway Grade Crossings?

Risk Analysis, Vol. 25, No. 4, 2005, pp. 867–881.

FRA. Federal Railroad Administration Office of Safety Analysis. Federal Railroad Administration, 2016. https://safetydata.fra.dot.gov/OfficeofSafety/publicsite/downloads/downloads.aspx.

Hellman

Lopez-Bernal

Highway-Rail Intersection Crash Taxonomy for Connected Vehicle Safety Research. United States Federal Railroad Administration, Office of Research and Development, Washington, D.C., May, 2015.

Najm

W. G.

Koopmann

Smith

J. D.

Brewer

Frequency of Target Crashes for IntelliDrive Safety Systems. National Highway Traffic Safety Administration, October, 2010. https://trid.trb.org/view/1085215.

National Highway Traffic Safety Administration. Federal Motor Vehicle Safety Standards. V2V Communications, 2017, pp. 3854–4019. https://www.govinfo.gov/content/pkg/FR-2017-01-12/pdf/2016-31059.pdf.

NHTSA Benefits Working Group. Preliminary Assessment of Crash Avoidance Systems Benefits. Paragraph. NHTSA, Washington, D.C., October, 1996.

10.

Najm

W. G.

Sen

Smith

J. D.

Campbell

B. N.

Analysis of Light Vehicle Crashes and Pre-Crash Scenarios Based on the 2000 General Estimates System. National Academies of Sciences, Engineering, and Medicine, Washington, DC, 2003, p. 80.

11.

Najm

W. G.

Smith

J. D.

Yanagisawa

Pre-Crash Scenario Typology for Crash Avoidance Research. Security. United States National Highway Traffic Safety Administration, Washington, D.C., April, 2007, p. 128.

12.

Najm

W. G.

Ranganathan

Srinivasan

Smith

J. D.

Toma

Swanson

Burgett

Description of Light-Vehicle Pre-Crash Scenarios for Safety Applications Based on Vehicle-to-Vehicle Communications. United States National Highway Traffic Safety Administration, Washington, D.C., May, 2013.

13.

Farmer

C. M.

Crash Avoidance Potential of Five Vehicle Technologies. Insurance Institute for Highway Safety, 2008. http://iihs.org/research/topics/pdf/r1107.pdf.

14.

Page

Cuny

Is ESP Effective on French Roads?

Accident Analysis & Prevention, Vol. 38, No. 2, 2006, pp. 357–364. http://www.sciencedirect.com/science/article/pii/S0001457505001788.

15.

Lie

Tingvall

Krafft

Kullgren

The Effectiveness of Electronic Stability Control (ESC) in Reducing Real Life Crashes and Injuries. Traffic Injury Prevention, Vol. 7, No. 1, 2006, pp. 38–43. https://www.tandfonline.com/doi/full/10.1080/15389580500346838.

16.

COWI. Cost-Benefit Assessment and Prioritisation of Vehicle Safety Technologies. Final Report. European Commission, 2006, p. 161.

17.

Bueno

Fabrigoule

Fort

Effectiveness of Forward Collision Warning Systems: A Contribution from the Cognitive Analysis Combining Behavioral and Electrophysiological Measurements. IET Digital Library, 2014.

18.

Anderson

R. W. G.

Hutchinson

T. P.

Linke

Ponte

Analysis of Crash Data to Estimate the Benefits of Emerging Vehicle Technology. Centre for Automotive Safety Research, The University of Adelaide, April, 2011, p. 85. http://casr.adelaide.edu.au/publications/researchreports.

19.

Carroll

Passera

Tingos

Vehicle Proximity Alert System for Highway-Railroad Grade Crossings-Prototype Research. United States Federal Railroad Administration, Washington, DC, 2001, p. 129.

20.

URS Corporation, and TranSmart Technologies Inc. Low-Cost Highway-Rail Intersection Active Warning System Field Operational Test. Evaluation Report. Minnesota Department of Transportation, St. Paul, December, 2005, p. 72.

21.

Aycin

Benekohal

Performance Evaluation of the Pilot Study of Advisory On-Board Vehicle Warning Systems at Railroad Grade Crossings. The Illinois Department of Transportation, 2002, p. 117. https://www.ideals.illinois.edu/handle/2142/46343.

22.

SRF Consulting Group, and Minnesota Department of Transportation. In-Vehicle Signing for School Buses at Railroad-Highway Grade Crossings. Evaluation Report. Minnesota Department of Transportation, St. Paul, August, 1998.

23.

Landry

Jeon

Lautala

Nelson

Getting Active with Passive Crossings: Investigating the Use of In-Vehicle Auditory Alerts for Highway-Rail Grade Crossings. Proc., ASME/IEEE Joint Rail Conference, Vol. 49675, Columbia, SC, American Society of Mechanical Engineers, New York, 2016, p. V001T06A019.

24.

Transit Cooperative Research Program. Second Train Coming Warning Sign Demonstration Projects. No. 51. Federal Transit Administration, Washington, DC, 2002.

25.

Neumeister

Zink

Sanchez-Badillo

Prototype Rail Crossing Violation Warning Application. Project Report. Volpe National Transportation Systems Center, Cambridge, MA, 2017. https://rosap.ntl.bts.gov/view/dot/34852.

26.

Reilly

D. L.

A Neural Network Video Sensor Application for Rail Crossing Safety. Public Works. Transportation Research Board, Washington, DC, 2001.

27.

Sheikh

Y. A.

Zhai

Shafique

Shah

M. A.

Visual Monitoring of Railroad Grade Crossing. In Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense III ( Carapezza

E. M.

, ed.), Vol. 5403, International Society for Optics and Photonics, Bellingham, 2004, pp. 654–660.

28.

Xue

Cheng

Wang

Gao

Visual Monitoring-Based Railway Grade Crossing Surveillance System. Proc., 1st International Congress on Image Signal Process CISP, Sanya, China, 2008, pp. 427–431.

29.

Silar

Dobrovolny

Objects Detection and Tracking on the Level Crossing. In Computational Collective Intelligence ( Nguyen

N. T.

Pimenidis

Khan

Trawiński

, eds.), Springer, Cham, 2015, pp. 245–255. http://link.springer.com/10.1007/978-3-319-98446-9.

30.

Grade-Crossing Safety. IEEE Vehicular Technology Magazine, Vol. 5, No. 3, 2010, pp. 75–81.

31.

Federal Railroad Administration, and Federal Transit Administration. Fiscal Year 2017 Positive Train Control Grant Program Project Selections. Federal Register, Vol. 82, No. 216, 2017, pp. 58–60. https://www.govinfo.gov/content/pkg/FR-2017-11-09/pdf/2017-24364.pdf.

32.

U.S. Department of Transportation. Federal Funding Support for Positive Train Control Implementation. Office of Inspector General, Washington, DC, 2018.

33.

Iteris.com. Railroad Crossing Violation Warning. CVRIA, 2016. https://local.iteris.com/cvria/html/applications/app53.html.

34.

Plapper

Zink

Neumeister

Vehicle-to-Infrastructure Rail Crossing Violation Warning Concept of Operations Phase I. United States Department of Transportation, Intelligent Transportation Systems Joint Program Office, Washington, DC, 2016.

35.

Neumeister

Campbell

Sharkey

Utterback

Prototype Rail Crossing Violation Warning (RCVW)—Advancing the Use of Connected Vehicle Technologies to Prevent Crashes at Rail Grade Crossings by Warning Vehicle Drivers of Predicted Violations, Vol. 110. United States Federal Highway Administration, Washington, DC, 2017. http://indexsmart.mirasmart.com/AREMA_CP_2019/PDFFiles/66Neumeisteretal.pdf .

36.

Wang

Zhang

Qiu

T. Z.

Active Warning System for Highway-Rail Grade Crossings Using Connected Vehicle Technologies. Journal of Advanced Transportation, Vol. 2019, 2019. https://doi.org/10.1155/2019/3219387.

37.

FHWA. Chapter 3. Treatment Selection Guidance. In Highway-Rail Crossing Handbook, 3rd ed. Federal Highway Administration, Washington, DC, 2019. https://safety.fhwa.dot.gov/hsip/xings/com_roaduser/fhwasa18040/chp2e.cfm#:~:text=The distance from the advance,advance of the nearest rail.

38.

NHTSA. Automatic Emergency Braking. National Highway Traffic Safety Administration, Washington, DChttps://www.safercar.gov/Vehicle+Shoppers/Safety+Technology/aeb-1/.

39.

Kozai

Takahashi

Kida

Hiromitsu

Kitaura

Sawada

Acervo

Ichim

Development of Automatic Braking System to Help Reduce Rear Impacts. SAE Technical Paper 2017-01-1408. Society of Automotive Engineers, Detroit, 2017. https://saemobilus.sae.org/content/2017-01-1408/.

40.

Sahayadhas

Sundaraj

Murugappan

Detecting Driver Drowsiness Based on Sensors: A Review. Sensors (Switzerland), Vol. 12, No. 12, 2012, pp. 16937–16953.

41.

Rau

P. S.

Drowsy Driver Detection and Warning System for Commercial Vehicle Drivers: Field Operational Test Design, Data Analyses, and Progress. National Highway Traffic Safety Administration, Washington, DC, 2005, pp. 1–17. https://www-esv.nhtsa.dot.gov/Proceedings/19/05-0192-W.pdf.

42.

Schwarz

Brown

Lee

Gaspar

Kang

The Detection of Visual Distraction Using Vehicle and Driver-Based Sensor. SAE Technical Paper 2016-01-0114. Society of Automotive Engineers, Detroit, 2016. https://www.sae.org/publications/technical-papers/content/2016-01-0114/.

43.

Mathew

Benekohal

R. F.

Highway-Rail Grade Crossings Accident Prediction Using Zero Inflated Negative Binomial and Empirical Bayes Method. Journal of Safety Research, Vol. 79, 2021, pp. 211–236. https://doi.org/10.1016/j.jsr.2021.09.003.

44.

Mathew

Benekohal

R. F.

Medina

J. C.

Accident Prediction Models Using Macro and Micro Scale Analysis: Dynamic Tree and Zero Inflated Negative Binomial Models with Empirical Bayes Accident History Adjustment. 2019. https://conservancy.umn.edu/bitstream/handle/11299/201747/CTS%2019-02.pdf?sequence=1.

45.

Mathew

Benekohal

R. F.

A New Accident Prediction Model for Highway-Rail Grade Crossings Using the USDOT Formula Variables. Journal of Traffic and Transportation Engineering, Vol. 8, No. 1, 2020, pp. 1–13.

46.

Wager

Hastie

Efron

Confidence Intervals for Random Forests: The Jackknife and the Infinitesimal Jackknife. The Journal of Machine Learning Research, Vol. 15, 2014, pp. 1625–1651.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.02 MB

Quantifying the Extent to Which Connected and Autonomous Vehicles Reduce Accidents at Railroad Grade Crossings: A Machine Learning Approach

Abstract

Keywords

Get full access to this article

References

Supplementary Material