Short-Term Prediction of Operational and Safety Impacts of Lane Changes in Oscillations with Empirical Vehicle Trajectories
Lane changes made during the oscillations of the traffic flow may largely affect the traffic operation and the safety on freeways. Predicting these impacts, can help to develop optimal lane change strategies for autonomous vehicles. The study aims at proposing a machine learning method for short-term prediction of the lane change impacts (LCI). The empirical lane-changing trajectory database was obtained from the Next Generation Simulation (NGSIM) method. A support vector regression (SVR) model was trained in this study to predict the LCI on the flow changes and crash risks using microscopic traffic variables such as speed, gap and acceleration on both original lanes and target lanes. Sensitivity analyses were conducted in the SVR to quantify the contributions of correlative lane changing factors. The results showed that the trained SVR model achieved an accuracy of 95.34% in predicting the flow change and 72.81% for the risk of crashes. Lower speed and acceleration of the lane changer caused larger decrease in the traffic flow. The gaps and speed differences between individual vehicles had positive effects on safety performance. Finally, the authors also compared the LCIs for motorcycles, automobiles and trucks as well as the LCIs for both lane-changing directions (from left to right and from right to left).
-
Supplemental Notes:
- This paper was sponsored by TRB committee ABJ70 Standing Committee on Artificial Intelligence and Advanced Computing Applications.
-
Corporate Authors:
Transportation Research Board
, -
Authors:
- Li, Meng
- Li, Zhibin
- Pu, Ziyuan
- Liu, Tong
- Liu, Pan
-
Conference:
- Transportation Research Board 98th Annual Meeting
- Location: Washington DC, United States
- Date: 2019-1-13 to 2019-1-17
- Date: 2019
Language
- English
Media Info
- Media Type: Digital/other
- Features: Figures; References; Tables;
- Pagination: 9p
Subject/Index Terms
- TRT Terms: Autonomous vehicles; Highway operations; Lane changing; Mathematical prediction; Vehicle trajectories
- Uncontrolled Terms: Support vector regression
- Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;
Filing Info
- Accession Number: 01697459
- Record Type: Publication
- Report/Paper Numbers: 19-04005
- Files: TRIS, TRB, ATRI
- Created Date: Mar 1 2019 3:50PM