Analysis of Contributing Factors in Crashes Involving Electric Vehicles and Vehicles with Automated Features

Harper, Corey; Hendrickson, Chris; Wang, Jiacheng · 2025 · ROSA P / Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

This study investigates the contributing factors and injury severity patterns in crashes involving vehicles equipped with Automated Driving Systems (ADS). Motivated by the high prevalence of human error in traffic fatalities and the increasing market penetration of automated and electric vehicles, the research aims to characterize crash distributions across variables such as weather, speed, and roadway type, and to estimate the relationship between these factors and crash severity. The analysis focuses specifically on ADS-equipped vehicles to assess their safety performance relative to other automated features. The researchers utilized summary incident report data from the National Highway Traffic Safety Administration (NHTSA) Standing General Order. After rigorous data cleaning to remove duplicates and retain only the latest report versions, the final dataset comprised 671 unique incidents involving ADS-equipped vehicles. The study employed descriptive statistics to analyze the distribution of crashes across various conditions and used multivariate logistic regression to model the influence of covariates on injury severity categories: no injuries, minor injuries, and moderate or more severe injuries. The findings reveal that the majority of ADS-related crashes occur at low speeds (0–10 MPH), in clear weather, on streets or at intersections, and during daylight hours. Crucially, the study found that ADS-equipped vehicles are disproportionately involved in incidents with no injuries (83% of no-injury cases) compared to more severe outcomes, with no fatalities reported. Logistic regression identified that higher injury severity is significantly associated with specific high-risk conditions: non-motorist actions by crash partners (e.g., pedestrians or cyclists), dark and unlighted conditions, and late-night occurrences. Conversely, low speeds, daylight, and parking lot locations were strongly correlated with no or minor injuries. While adverse weather was associated with no injuries, it did not show a statistically significant correlation with injury severity overall. The significance of this research lies in its demonstration that ADS technology may mitigate crash severity, as evidenced by the lower proportion of ADS vehicles in severe injury incidents compared to those with only Advanced Driver Assistance Systems (ADAS). The study highlights that visibility, time of day, and the presence of vulnerable road users are critical predictors of severe outcomes. However, the authors note limitations regarding the small sample size of severe crashes and the lack of comprehensive travel data, which prevents the calculation of crash rates per mile. Future work will expand the analysis to include electric vehicles to further contextualize safety trends in emerging vehicle technologies.

Key finding

Non-motorist crash partners, dark unlighted conditions, and late-night timing are the strongest predictors of moderate or more severe injuries in crashes involving ADS-equipped vehicles.

Methodology

dataset

Sample size: 671

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

StageOutcomeToolModelPromptAttemptsCompleted
discover success rosap 2 2026-05-23
archive success 1 2026-05-23
extract success cached 2 2026-06-10
clean success 1 2026-06-01
chunk success 1 2026-06-01
embed success 1 2026-06-02
enrich success 1 2026-05-23
promote success 1 2026-05-23
summarize success llm qwen3.6-27b-prismaquant summ-v5 3 2026-06-10
tag success vector_similarity 19 2026-06-11
verify partial 2 2026-06-10

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).