A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement Reports
Autonomous vehicles (AVs) are being extensively tested on public roads in several states in the USA, such as California, Florida, Nevada, and Texas. AV utilization is expected to increase into the future, given rapid advancement and development in sensing and navigation technologies. This will event...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Sustainability |
Subjects: | |
Online Access: | https://www.mdpi.com/2071-1050/13/14/7938 |
id |
doaj-d1c018b5035640e590326a912544f852 |
---|---|
record_format |
Article |
spelling |
doaj-d1c018b5035640e590326a912544f8522021-07-23T14:08:15ZengMDPI AGSustainability2071-10502021-07-01137938793810.3390/su13147938A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement ReportsAmolika Sinha0Vincent Vu1Sai Chand2Kasun Wijayaratna3Vinayak Dixit4Research Centre for Integrated Transport Innovation (rCITI), School of Civil and Environmental Engineering, UNSW Sydney, Sydney, NSW 2052, AustraliaResearch Centre for Integrated Transport Innovation (rCITI), School of Civil and Environmental Engineering, UNSW Sydney, Sydney, NSW 2052, AustraliaResearch Centre for Integrated Transport Innovation (rCITI), School of Civil and Environmental Engineering, UNSW Sydney, Sydney, NSW 2052, AustraliaSchool of Civil and Environmental Engineering, University of Technology Sydney (UTS), Sydney, NSW 2007, AustraliaResearch Centre for Integrated Transport Innovation (rCITI), School of Civil and Environmental Engineering, UNSW Sydney, Sydney, NSW 2052, AustraliaAutonomous vehicles (AVs) are being extensively tested on public roads in several states in the USA, such as California, Florida, Nevada, and Texas. AV utilization is expected to increase into the future, given rapid advancement and development in sensing and navigation technologies. This will eventually lead to a decline in human driving. AVs are generally believed to mitigate crash frequency, although the repercussion of AVs on crash severity is ambiguous. For the data-driven and transparent deployment of AVs in California, the California Department of Motor Vehicles (CA DMV) commissioned AV manufacturers to draft and publish reports on disengagements and crashes. This study performed a comprehensive assessment of CA DMV data from 2014 to 2019 from a safety standpoint, and some trends were discerned. The results show that decrement in automated disengagements does not necessarily imply an improvement in AV technology. Contributing factors to the crash severity of an AV are not clearly defined. To further understand crash severity in AVs, the features and issues with data are identified and discussed using different machine learning techniques. The CA DMV accident report data were utilized to develop a variety of crash AV severity models focusing on the injury for all crash typologies. Performance metrics were discussed, and the bagging classifier model exhibited the best performance among different candidate models. Additionally, the study identified potential issues with the CA DMV data reporting protocol, which is imperative to share with the research community. Recommendations are provided to enhance the existing reports and append new domains.https://www.mdpi.com/2071-1050/13/14/7938autonomous vehiclescrash severitydisengagements |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Amolika Sinha Vincent Vu Sai Chand Kasun Wijayaratna Vinayak Dixit |
spellingShingle |
Amolika Sinha Vincent Vu Sai Chand Kasun Wijayaratna Vinayak Dixit A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement Reports Sustainability autonomous vehicles crash severity disengagements |
author_facet |
Amolika Sinha Vincent Vu Sai Chand Kasun Wijayaratna Vinayak Dixit |
author_sort |
Amolika Sinha |
title |
A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement Reports |
title_short |
A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement Reports |
title_full |
A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement Reports |
title_fullStr |
A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement Reports |
title_full_unstemmed |
A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement Reports |
title_sort |
crash injury model involving autonomous vehicle: investigating of crash and disengagement reports |
publisher |
MDPI AG |
series |
Sustainability |
issn |
2071-1050 |
publishDate |
2021-07-01 |
description |
Autonomous vehicles (AVs) are being extensively tested on public roads in several states in the USA, such as California, Florida, Nevada, and Texas. AV utilization is expected to increase into the future, given rapid advancement and development in sensing and navigation technologies. This will eventually lead to a decline in human driving. AVs are generally believed to mitigate crash frequency, although the repercussion of AVs on crash severity is ambiguous. For the data-driven and transparent deployment of AVs in California, the California Department of Motor Vehicles (CA DMV) commissioned AV manufacturers to draft and publish reports on disengagements and crashes. This study performed a comprehensive assessment of CA DMV data from 2014 to 2019 from a safety standpoint, and some trends were discerned. The results show that decrement in automated disengagements does not necessarily imply an improvement in AV technology. Contributing factors to the crash severity of an AV are not clearly defined. To further understand crash severity in AVs, the features and issues with data are identified and discussed using different machine learning techniques. The CA DMV accident report data were utilized to develop a variety of crash AV severity models focusing on the injury for all crash typologies. Performance metrics were discussed, and the bagging classifier model exhibited the best performance among different candidate models. Additionally, the study identified potential issues with the CA DMV data reporting protocol, which is imperative to share with the research community. Recommendations are provided to enhance the existing reports and append new domains. |
topic |
autonomous vehicles crash severity disengagements |
url |
https://www.mdpi.com/2071-1050/13/14/7938 |
work_keys_str_mv |
AT amolikasinha acrashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT vincentvu acrashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT saichand acrashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT kasunwijayaratna acrashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT vinayakdixit acrashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT amolikasinha crashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT vincentvu crashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT saichand crashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT kasunwijayaratna crashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports AT vinayakdixit crashinjurymodelinvolvingautonomousvehicleinvestigatingofcrashanddisengagementreports |
_version_ |
1721285796673093632 |