TRB Pubsindex
Text Size:
x

« Prev Next »

Return to Results | New Search

Bookmark and Share

Title:

Vehicle Collision Risk Prediction at Intersections based on Comparison of Minimal Distance between Vehicles and Dynamic Thresholds

Accession Number:

01625576

Record Type:

Component

Abstract:

Accurate collision risk prediction algorithms are of essential importance for providing prompt and reliable warning messages to drivers. This study introduces a novel approach for collision avoidance applications in driving scenarios when the subject vehicle is approaching an intersection. The algorithm involves the use of an index called “Minimal Future Distance (MFD)”, which is defined to be a future distance between the subject vehicle and the primary other vehicle, and a two-level dynamic threshold for preforming the collision prediction task. Real-time vehicle motion information and surrounding road geometry, which are based on a combination of data from Global Positioning System (GPS), Inertial Navigation System (INS) and a digital map, are utilized to forecast future distances between any two vehicles (FDs) within an upcoming time horizon, and the MFD is subsequently identified from these FDs. The dynamic thresholds are a function of vehicle current speed and compared with MFD to determine the risks of potential collisions. Such calculations are repeatedly performed at a frequency based on the data update frequency. The combined use of vehicle real-time state and road geometry in the algorithm significantly increased the prediction accuracy. Furthermore, the use of dynamic thresholds ensured the promptness and robustness of the collision warning system. Simulation results show that false positive rate and false negative rate of severe collisions can be robustly eliminated and those of marginal collisions can be kept low at 2.2% and 4.5% respectively.

Supplemental Notes:

This paper was sponsored by TRB committee AND20 Standing Committee on User Information Systems.

Monograph Accession #:

01618707

Report/Paper Numbers:

17-02683

Language:

English

Corporate Authors:

Transportation Research Board

500 Fifth Street, NW
Washington, DC 20001 United States

Authors:

Wang, Pin
Chan, Ching-Yao

Pagination:

16p

Publication Date:

2017

Conference:

Transportation Research Board 96th Annual Meeting

Location: Washington DC, United States
Date: 2017-1-8 to 2017-1-12
Sponsors: Transportation Research Board

Media Type:

Digital/other

Features:

Figures; References (15) ; Tables

Subject Areas:

Highways; Safety and Human Factors

Source Data:

Transportation Research Board Annual Meeting 2017 Paper #17-02683

Files:

TRIS, TRB, ATRI

Created Date:

Dec 8 2016 11:01AM