Amid significant advances in automated vehicle safety, Waymo’s driverless taxi service shows that the reduction in crashes has dropped dramatically compared to human drivers, with the results of crashes being particularly impressive at Road intersections.
A peer review study published on Traffic Injury Prevention examines 56.7 million miles of Waymo’s rider (RO) services – vehicles running without a human and discovers safety improvements in multiple crash types.
The most compelling result comes from the crossroads collapse, with 96% fewer reported incidents compared to human benchmarks. Intersection collision is one of the most dangerous and common crash scenarios on American roads.
“The V2V intersection crash event represents the largest reduction in total crash, with a 96% reduction in any injury report (87%-99% confidence interval) and a 91% reduction in airbag deployment (76%-98% confidence interval),” the researchers reported. ”
The study, led by Waymo’s Kristofer Kusano and colleagues, is the first comprehensive assessment of automated ride service services that draw statistical conclusions on severe crash results and analyze performance through specific crash types.
In addition to the intersection, Waymo vehicles also showed significant safety improvements in crashes involving cyclists (82%), motorcycle riders (82%), pedestrians (92%), bicycle events (93%) and side impact collisions (74%).
The researchers took careful steps to ensure fair comparisons were made, adjusting factors such as vehicle type, road type, and specific locations where Waymo operates. Their analysis focused on three levels of collapse severity: any report of injury, airbag deployment, and suspected serious injury or death.
“This study represents the first retrospective safety assessment of RO advertising, which draws statistical conclusions on more severe crash results (airbag deployment and suspected severe injury +) and analyzes crash rates based on crash type,” the authors said.
The analysis covers Waymo’s operations in Phoenix, San Francisco, Los Angeles and Austin until January 2025. Human benchmark data comes from statistics from the state vehicle Myers and police report crash data from the same area.
Although most collision types show a decrease, the results of back-end collisions are more subtle. The chances of Waymo vehicles hitting other vehicles from behind were significantly reduced, but were slightly increased by being hit behind Phoenix – although this difference was offset by a decrease in the more severe crash types.
Transportation safety experts have long expected that self-driving cars might bring safety benefits, but until now, there is limited real-world data in the real world to support these predictions. This study provides some of the most compelling evidence to improve safety from fully autonomous vehicles operating at scale to date.
The researchers suggest that the findings provide valuable insights to stakeholders, regulators and other self-driving car companies to objectively evaluate the safety impact of autonomous driving technology.
If our report has been informed or inspired, please consider donating. No matter how big or small, every contribution allows us to continue to deliver accurate, engaging and trustworthy scientific and medical news. Independent news takes time, energy and resources – your support ensures that we can continue to reveal the stories that matter most to you.
Join us to make knowledge accessible and impactful. Thank you for standing with us!
