Removing alcohol-impaired drivers lowers the average urban fatal crash involvement rate by 23%, from 1.42 to 1.10 per 100 million miles, according to new peer-reviewed research from Waymo. The first study, accepted for publication in the Journal of Safety Research, estimates sober driving baselines across the 50 most populous U.S. urban areas. Waymo says even fully sober drivers face fatal crash risk at night that is 3.1 to 3.9 times higher than during the day.
Highlights
- 23% lower urban fatal crash involvement rate when alcohol-involved drivers are removed (1.42 to 1.10 per 100 million miles)
- 31% reduction in Houston versus 13% in Minneapolis, showing wide geographic variation
- 3.1 to 3.9 times higher nighttime fatal crash risk for sober drivers than daytime risk
- 8.2% of 37,654 fatal cases in 2023 FARS data involved human behavior factors alone
How Did Waymo Build a Sober Driver Baseline?
National traffic databases do not track vehicle miles traveled (VMT) by a driver’s blood alcohol concentration (BAC). To fill that gap, Waymo researchers built an exposure reconstruction model that cross-references toxicology data from the Fatality Analysis Reporting System (FARS) with real-world telematics.
The model estimates miles driven by sober (zero BAC) and impaired drivers in each of the 50 urban areas. Waymo used those estimates to set city-level unimpaired driving baselines. The work builds on the company’s earlier research on crash risk by time and location. Waymo says the zero-BAC cohort lets it evaluate autonomous vehicle safety against a higher bar: a non-impaired human driver.
According to the company’s estimates, more than 2% of nighttime drivers in some areas, or 1 in 50, are over the legal blood alcohol limit.
Alcohol’s Impact Varies by City
The effect of removing impaired drivers differs sharply by geography:
- Urban average: 23% reduction in fatal crash involvement
- Houston: 31% reduction
- Minneapolis: 13% reduction
Waymo says the spread shows why local human benchmarks are more useful than national averages for evaluating road safety.
“Waymo’s work here can fill a major gap in road safety research. Finding a way to granularly track where and when alcohol-impaired driving happens gives the safety community a much clearer picture of where the real risks lie on our roads. This underscores why cutting-edge autonomous technology can be a vital tool — alongside anti-drunk driving technology built into all human-driven vehicles — to protect lives where human limits meet the road,” said Stacey D. Stewart, CEO of Mothers Against Drunk Driving (MADD).
Why Is Nighttime Driving Riskier for Sober Drivers?
The study tested whether elevated nighttime crash rates come only from impaired driving. It found they do not: fatal crash risk for 100% sober drivers remains 3.1 to 3.9 times higher at night than during the day.
Waymo attributes part of that gap to sober drivers reacting to impaired ones. It also points to other known nighttime hazards:
- Reduced visibility and inadequate lighting
- Driver fatigue
- Road layouts that encourage speeding
- Unpredictable road users
Compounding Risks in Fatal Crashes
A second study, published by the International Research Council on the Biomechanics of Injury (IRCOBI), analyzed 37,654 fatal cases from the 2023 FARS database. It used the U.S. Department of Transportation’s Safe System Approach, which relies on four layers of protection: Safer People, Safer Vehicles, Safer Speeds and Safer Roads.
The findings:
- More than 77% of fatal cases involved at least one of impairment, speeding, or seat belt/helmet nonuse or misuse.
- 9.2% involved all three.
- 8.2% involved human behavior factors alone.
According to Waymo, most fatal crashes combine factors, such as an unlit road, a large vehicle size mismatch and unexpectedly high speeds.
What the Benchmark Means for AV Evaluation
Waymo says it continues to benchmark its performance against real-world human driving under actual road conditions. The sober baseline adds a second lens: comparison against an optimized human standard.
The company says the Waymo Driver is designed around Safe System elements, including constant 360-degree vigilance, adherence to posted speed limits, defensive driving, and zero impairment or distraction. Waymo’s analysis estimates autonomous systems could address up to 83% of the system failures that contribute to passenger-vehicle-involved fatal crashes in the U.S.
“To truly understand road safety—and to properly evaluate the impact of autonomous vehicles—we must recognize that traffic fatalities are a complex, systemic issue. Fatal crashes typically result from compounding factors—like low visibility, high speeds, and poor road design—that even sober drivers cannot always overcome. The Waymo Driver is built to solve for both sides of that equation, eliminating the impairment factors entirely while simultaneously accounting for environmental vulnerabilities and addressing systemic hazards that contribute to traffic fatalities,” said Mauricio Pena, Chief Safety Officer at Waymo.
