A Framework for Determining Collision Likelihood Using Continuous Friction Values in a Connected Vehicle Environment
Jurisdictions currently provide information on winter road conditions through qualitative descriptors like bare and fully snow-covered. Ideally, these descriptors are meant to warn drivers beforehand about hazardous roads. In practice, however, discerning between safe and unsafe roads is sometimes u...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/16/9/426 |
| _version_ | 1827727628035948544 |
|---|---|
| author | Qian Xie Tae J. Kwon |
| author_facet | Qian Xie Tae J. Kwon |
| author_sort | Qian Xie |
| collection | DOAJ |
| description | Jurisdictions currently provide information on winter road conditions through qualitative descriptors like bare and fully snow-covered. Ideally, these descriptors are meant to warn drivers beforehand about hazardous roads. In practice, however, discerning between safe and unsafe roads is sometimes unclear due to intermediate RSC classes covering too wide a range of conditions. This study aims at solving this safety ambiguity issue by proposing a framework for predicting collision likelihood within a road segment. The proposed framework converts road surface images into friction coefficients, which are then converted into continuous measurements through an interpolator. To find the best-performing interpolator, we evaluated geostatistical, machine learning, and hybrid interpolators. It was found that ordinary kriging had the lowest estimation error and was the least sensitive to changes in distance between measurements. After developing an interpolator, collision likelihood models were developed for segment lengths ranging from 0.5 km to 20 km. We chose the 6.5 km model based on its accuracy and intuitiveness. This model had 76.9% accuracy and included friction and AADT as predictors. It was also estimated that if the proposed framework were implemented in an environment with connected vehicles and intelligent transportation systems, it would offer significant safety improvements. |
| first_indexed | 2024-03-10T23:08:04Z |
| format | Article |
| id | doaj.art-f54d2a04866249238cf9d50a6724b2ff |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-10T23:08:04Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-f54d2a04866249238cf9d50a6724b2ff2023-11-19T09:12:58ZengMDPI AGAlgorithms1999-48932023-09-0116942610.3390/a16090426A Framework for Determining Collision Likelihood Using Continuous Friction Values in a Connected Vehicle EnvironmentQian Xie0Tae J. Kwon1Department of Civil and Environmental Engineering, University of Alberta, Edmonton, AB T6G 2W2, CanadaDepartment of Civil and Environmental Engineering, University of Alberta, Edmonton, AB T6G 2W2, CanadaJurisdictions currently provide information on winter road conditions through qualitative descriptors like bare and fully snow-covered. Ideally, these descriptors are meant to warn drivers beforehand about hazardous roads. In practice, however, discerning between safe and unsafe roads is sometimes unclear due to intermediate RSC classes covering too wide a range of conditions. This study aims at solving this safety ambiguity issue by proposing a framework for predicting collision likelihood within a road segment. The proposed framework converts road surface images into friction coefficients, which are then converted into continuous measurements through an interpolator. To find the best-performing interpolator, we evaluated geostatistical, machine learning, and hybrid interpolators. It was found that ordinary kriging had the lowest estimation error and was the least sensitive to changes in distance between measurements. After developing an interpolator, collision likelihood models were developed for segment lengths ranging from 0.5 km to 20 km. We chose the 6.5 km model based on its accuracy and intuitiveness. This model had 76.9% accuracy and included friction and AADT as predictors. It was also estimated that if the proposed framework were implemented in an environment with connected vehicles and intelligent transportation systems, it would offer significant safety improvements.https://www.mdpi.com/1999-4893/16/9/426road frictionroad weather interpolationfriction interpolationcollision modelingroad safetyconnected vehicle |
| spellingShingle | Qian Xie Tae J. Kwon A Framework for Determining Collision Likelihood Using Continuous Friction Values in a Connected Vehicle Environment Algorithms road friction road weather interpolation friction interpolation collision modeling road safety connected vehicle |
| title | A Framework for Determining Collision Likelihood Using Continuous Friction Values in a Connected Vehicle Environment |
| title_full | A Framework for Determining Collision Likelihood Using Continuous Friction Values in a Connected Vehicle Environment |
| title_fullStr | A Framework for Determining Collision Likelihood Using Continuous Friction Values in a Connected Vehicle Environment |
| title_full_unstemmed | A Framework for Determining Collision Likelihood Using Continuous Friction Values in a Connected Vehicle Environment |
| title_short | A Framework for Determining Collision Likelihood Using Continuous Friction Values in a Connected Vehicle Environment |
| title_sort | framework for determining collision likelihood using continuous friction values in a connected vehicle environment |
| topic | road friction road weather interpolation friction interpolation collision modeling road safety connected vehicle |
| url | https://www.mdpi.com/1999-4893/16/9/426 |
| work_keys_str_mv | AT qianxie aframeworkfordeterminingcollisionlikelihoodusingcontinuousfrictionvaluesinaconnectedvehicleenvironment AT taejkwon aframeworkfordeterminingcollisionlikelihoodusingcontinuousfrictionvaluesinaconnectedvehicleenvironment AT qianxie frameworkfordeterminingcollisionlikelihoodusingcontinuousfrictionvaluesinaconnectedvehicleenvironment AT taejkwon frameworkfordeterminingcollisionlikelihoodusingcontinuousfrictionvaluesinaconnectedvehicleenvironment |