Learning the representation of surrogate safety measures to identify traffic conflict
Traffic conflict can be identified by the presence of evasive actions or the amount of temporal (spatial) proximity measures like time-to-collision (TTC). However, it is not enough to use only one kind of measures in some scenarios and it is hard to set a threshold for those measures. This paper proposed a method to identify traffic conflict by learning the representation of TTC and driver maneuver profiles with deep unsupervised learning and clustering the representations into traffic conflict and non-conflict clusters. The authors first trained a transformer encoder to encode sequences of surrogate safety measures into some latent space with unsupervised pre-training. Second, the authors identified informative clusters in the latent space by calculating the statistic summaries and visualizing trajectory pairs of each cluster. Some clusters are interpreted as traffic conflict clusters because they have small TTC, large deceleration rate and intertwining trajectories and they can be further interpreted as rear-end or angle conflicts. Moreover, the identified traffic conflicts contain critical conditions from the two vehicles in an interaction and one vehicle perceives them as abnormal and takes evasive action to avoid crashes.
- Record URL:
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/00014575
-
Supplemental Notes:
- © 2022 Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
-
Authors:
- Lu, Jiajian
- Grembek, Offer
- Hansen, Mark
- Publication Date: 2022-9
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: 106755
-
Serial:
- Accident Analysis & Prevention
- Volume: 174
- Issue Number: 0
- Publisher: Elsevier
- ISSN: 0001-4575
- Serial URL: http://www.sciencedirect.com/science/journal/00014575
Subject/Index Terms
- TRT Terms: Machine learning; Risk assessment; Safety analysis; Traffic conflicts; Vehicle trajectories
- Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;
Filing Info
- Accession Number: 01851585
- Record Type: Publication
- Files: TRIS
- Created Date: Jul 18 2022 9:28AM