Comparison of Waymo Rider-Only Crash Rates by Crash Type to Human Benchmarks at 56.7 Million Miles
🤖 AI Summary
Prior evaluations of fully autonomous driving systems lacked statistically rigorous, collision-outcome–based safety assessments against human drivers. Method: This study conducts the first statistically significant, severity-based safety evaluation of a production-level driverless system—Waymo’s fully autonomous ride-hailing service (56.7 million operational miles)—against human drivers across 11 collision scenarios (e.g., vehicle-to-vehicle intersection crashes, pedestrian collisions). It employs NHTSA-mandated Safety Governance Office (SGO) crash reporting data, publicly disclosed vehicle miles traveled, and a rigorously matched human collision benchmark database—aligned by geography, road type, and vehicle class—for retrospective statistical analysis. Contribution/Results: The system demonstrates statistically significant safety improvements across multiple metrics: overall injury-involved crash rate is significantly lower than the human baseline; V2V intersection crash rate declines by 96% (95% CI: 87%–99%); airbag deployment rate drops by 91% (95% CI: 76%–98%); and five additional crash categories also show statistically significant reductions. No scenario exhibits degraded safety. This work establishes the first fine-grained, collision-type–specific safety evaluation framework for autonomous vehicles.
Application Category
📝 Abstract
SAE Level 4 Automated Driving Systems (ADSs) are deployed on public roads, including Waymo's Rider-Only (RO) ride-hailing service (without a driver behind the steering wheel). The objective of this study was to perform a retrospective safety assessment of Waymo's RO crash rate compared to human benchmarks, including disaggregated by crash type. Eleven crash type groups were identified from commonly relied upon crash typologies that are derived from human crash databases. Human benchmarks were aligned to the same vehicle types, road types, and locations as where the Waymo Driver operated. Waymo crashes were extracted from the NHTSA Standing General Order (SGO). RO mileage was provided by the company via a public website. Any-injury-reported, Airbag Deployment, and Suspected Serious Injury+ crash outcomes were examined because they represented previously established, safety-relevant benchmarks where statistical testing could be performed at the current mileage. Data was examined over 56.7 million RO miles through the end of January 2025, resulting in a statistically significant lower crashed vehicle rate for all crashes compared to the benchmarks in Any-Injury-Reported and Airbag Deployment, and Suspected Serious Injury+ crashes. Of the crash types, V2V Intersection crash events represented the largest total crash reduction, with a 96% reduction in Any-injury-reported (87%-99% CI) and a 91% reduction in Airbag Deployment (76%-98% CI) events. Cyclist, Motorcycle, Pedestrian, Secondary Crash, and Single Vehicle crashes were also statistically reduced for the Any-Injury-Reported outcome. There was no statistically significant disbenefit found in any of the 11 crash type groups. This study represents the first retrospective safety assessment of an RO ADS that made statistical conclusions about more serious crash outcomes and analyzed crash rates on a crash type basis.
Problem
Research questions and friction points this paper is trying to address.
Compare Waymo Rider-Only crash rates to human benchmarks
Assess safety by crash type across 56.7 million miles
Evaluate statistical significance of injury and airbag deployment outcomes
Innovation
Methods, ideas, or system contributions that make the work stand out.
SAE Level 4 ADS deployed without human drivers
Retrospective safety assessment using human benchmarks
Statistically significant crash rate reductions achieved
🔎 Similar Papers
No similar papers found.
