Extreme value analysis for safety benefit estimation of adaptive cruise control (ACC)
As new automated features enter the automotive market, we need methods to assess their safety in a rapid, proactive, and iterative way. The traditional way of relying on crash statistics does not meet these needs. An alternative is to use extrapolation techniques designed to deal with rare events,...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Technology and Society, Faculty of Engineering, LTH, Lund University
2025-07-01
|
| Series: | Traffic Safety Research |
| Subjects: | |
| Online Access: | https://tsr.international/TSR/article/view/27511 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849729282305163264 |
|---|---|
| author | Alberto Morando |
| author_facet | Alberto Morando |
| author_sort | Alberto Morando |
| collection | DOAJ |
| description |
As new automated features enter the automotive market, we need methods to assess their safety in a rapid, proactive, and iterative way. The traditional way of relying on crash statistics does not meet these needs. An alternative is to use extrapolation techniques designed to deal with rare events, such as extreme value theory (EVT). In this paper, we applied EVT to estimate the risk of collision with and without adaptive cruise control (ACC) during steady-state car following. We defined a Bayesian regression model to estimate the parameters of the Weibull distribution for block maxima (BM) of the brake threat number (BTN). We used a small, open-access dataset collected during a platooning experiment on a test track, with and without ACC. We found that it is extremely unlikely that the use of ACC will result in a rear-end crash under normal car-following circumstances, a finding consistent with the general expectation that ACC is safer than manual driving. However, we found that the relative risk of ACC was actually higher than the human control baseline. The reason is that the baseline represents a cautious driving style which may not be typical of the driving style in real traffic. Nonetheless, EVT can measure the expected safety benefit of a vehicle system even without a large dataset. The BTN was an appropriate safety metric to compare automated and manual driving modes, as it accounts for specific brake behavior and performance.
|
| format | Article |
| id | doaj-art-ef8a0d3ac3d3463291cd430d601c5b78 |
| institution | DOAJ |
| issn | 2004-3082 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Technology and Society, Faculty of Engineering, LTH, Lund University |
| record_format | Article |
| series | Traffic Safety Research |
| spelling | doaj-art-ef8a0d3ac3d3463291cd430d601c5b782025-08-20T03:09:16ZengTechnology and Society, Faculty of Engineering, LTH, Lund UniversityTraffic Safety Research2004-30822025-07-01910.55329/byml9675Extreme value analysis for safety benefit estimation of adaptive cruise control (ACC)Alberto Morando0https://orcid.org/0000-0003-4937-6773Autoliv Development AB, Sweden As new automated features enter the automotive market, we need methods to assess their safety in a rapid, proactive, and iterative way. The traditional way of relying on crash statistics does not meet these needs. An alternative is to use extrapolation techniques designed to deal with rare events, such as extreme value theory (EVT). In this paper, we applied EVT to estimate the risk of collision with and without adaptive cruise control (ACC) during steady-state car following. We defined a Bayesian regression model to estimate the parameters of the Weibull distribution for block maxima (BM) of the brake threat number (BTN). We used a small, open-access dataset collected during a platooning experiment on a test track, with and without ACC. We found that it is extremely unlikely that the use of ACC will result in a rear-end crash under normal car-following circumstances, a finding consistent with the general expectation that ACC is safer than manual driving. However, we found that the relative risk of ACC was actually higher than the human control baseline. The reason is that the baseline represents a cautious driving style which may not be typical of the driving style in real traffic. Nonetheless, EVT can measure the expected safety benefit of a vehicle system even without a large dataset. The BTN was an appropriate safety metric to compare automated and manual driving modes, as it accounts for specific brake behavior and performance. https://tsr.international/TSR/article/view/27511automationcar-followingsafety benchmarksafety impact |
| spellingShingle | Alberto Morando Extreme value analysis for safety benefit estimation of adaptive cruise control (ACC) Traffic Safety Research automation car-following safety benchmark safety impact |
| title | Extreme value analysis for safety benefit estimation of adaptive cruise control (ACC) |
| title_full | Extreme value analysis for safety benefit estimation of adaptive cruise control (ACC) |
| title_fullStr | Extreme value analysis for safety benefit estimation of adaptive cruise control (ACC) |
| title_full_unstemmed | Extreme value analysis for safety benefit estimation of adaptive cruise control (ACC) |
| title_short | Extreme value analysis for safety benefit estimation of adaptive cruise control (ACC) |
| title_sort | extreme value analysis for safety benefit estimation of adaptive cruise control acc |
| topic | automation car-following safety benchmark safety impact |
| url | https://tsr.international/TSR/article/view/27511 |
| work_keys_str_mv | AT albertomorando extremevalueanalysisforsafetybenefitestimationofadaptivecruisecontrolacc |