An Exploratory Analysis of Temporal and Spatial Patterns of Autonomous Vehicle Collisions
Open accessAbstract
Recent advancements in autonomous vehicle (AV) technology have the potential to reduce road accidents caused by human error. However, to enhance their safety and performance, it is crucial to understand the patterns of AV collisions. This study examines AV collisions by analyzing their temporal and spatial patterns. Based on reports from the California DMV between 2014 and 2022, the analysis reveals that rear-end collisions are the most common type, while incidents involving pedestrians and overturned vehicles are rare. The majority of collisions involve mid-sized vehicles, and AVs are responsible for a minority of accidents. The study also identifies clusters of incidents in San Francisco, San Jose, Los Angeles, and San Diego, with San Francisco having largest concentration. Specific areas within San Francisco, like Mission District, Japantown, Union Square, and North Beach neighborhoods, show high incident rates. These findings highlight safety concerns, and aid in integration of AVs into transportation infrastructure.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Urban roads are more likely to have a combination of various ODDs that reduce the driving safety of AVs compared to roads such as freeways and expressways.
“The reason for this result is that compared to roads such as freeways and expressways, urban roads are more likely to have a combination of various ODDs that reduce the driving safety of AVs [15].”
From Evaluation of Autonomous Driving Safety by Operational Design Domains (ODD) in Mixed Traffic (2024) · cites this paper as [15]
Cites
A Systematic Review of Perception System and Simulators for Autonomous Vehicles Research
Rosique, F., Navarro, P. J., Fernández, C., & Padilla, A. (2019) · Sensors · doi:10.3390/s19030648 · Cited by 469 · see citing works
Machine learning, social learning and the governance of self-driving cars
Stilgoe, J. (2018) · Social Studies of Science · doi:10.1177/0306312717741687 · Cited by 375 · see citing works
Unintended effects of autonomous driving: a study on mobility preferences in the future
Pakusch, C., Stevens, G., Boden, A., & Bossauer, P. (2018) · Sustainability · doi:10.3390/su10072404 · Cited by 182 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Evaluation of Autonomous Driving Safety by Operational Design Domains (ODD) in Mixed Traffic
Kim, H., Ko, J., Oh, C., & Kim, S. (2024) · Sustainability · doi:10.3390/su16229672 · Cited by 18 · see citing works
“The reason for this result is that compared to roads such as freeways and expressways, urban roads are more likely to have a combination of various ODDs that reduce the driving safety of AVs [15].”
- Authors
- Patel, R. K., Channamallu, S. S., Khan, M. A., Kermanshachi, S., & Pamidimukkala, A.
- Affiliations
- The University of Texas at Arlington (US)
- Corresponding author
- Kermanshachi, Sharareh
- Venue
- Public Works Management & Policy
- Publisher
- SAGE Publications
- Published
- 2023-11-29
- Volume
- 29
- Issue
- 4
- Pages
- 588-611
- ISSN
- 1087-724X (ISSN-L)
- 1552-7549
- OpenAlex
- W4389125022
- Cited by
- 30
- References
- 3
- Citations by year
- 2026: 5 · 2025: 17 · 2024: 8
- FWCI
- 5.17
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Public Works Management & Policy (publishedVersion, cc-by)
- Topics
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Traffic and Road Safety
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Social Sciences › Psychology › Social Psychology › Human-Automation Interaction and Safety
- Keywords
- autonomous vehicles, vehicle collisions, temporal patterns, spatial patterns, rear-end collisions, pedestrian accidents, vehicle size, San Francisco, road safety
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
