Safety
Our Safety Philosophy
The data to date indicates the Waymo Driver is already reducing traffic injuries and fatalities in the places where we currently operate. At Waymo, we aim to reduce traffic injuries and fatalities by driving safely and responsibly, and will carefully manage risk as we scale our operations.
Explore our Safety Case Framework
Because Safety is Urgent™
Autonomous Driving Technology Can Save Lives and Improve Mobility

1.36M
42,915
$836B
50M
79%
12M
Safety Publications
Year
Topics
Safety Methodologies


Safety Methodologies
-
Building a Credible Case for Safety: Waymo's Approach for the Determination of Absence of Unreasonable Risk
Francesca Favaro, Laura Fraade-Blanar, Scott Schnelle, Trent Victor, Mauricio Peña, Johan Engstrom, John Scanlon, Kris Kusano, Dan SmithWaymo’s approach to building a reliable case for safety that can serve as a toolkit that any AV developer can use to inform their own safety case.
-
Framework for a conflict typology including causal factors for use in ADS safety evaluation
Kristofer D. Kusano, John M. Scanlon, Mattias Brännström, Johan Engström, Trent VictorGrouping collisions with similar characteristics and causes is how traffic safety researchers measure effectiveness of different technologies, like autonomous vehicles. This paper introduces a comprehensive conflict typology that can be applied to both human and AV crash and near-crash data.
-
Determining Maximum Injury Potential
Methodology for Determining Maximum Injury Potential for Automated Driving System Evaluation
Kristofer Kusano, Trent VictorThe potential severity in a collision is affected by braking and steering. The metric developed in this paper predicts the worst case probability of injury as if there was no avoidance maneuvers. This metric is important when comparing different crash datasets.
-
Waymo's Fatigue Risk Management Framework: Prevention, Monitoring, and Mitigation of Fatigue-Induced Risks while Testing Automated Driving Systems
Francesca Favaro, Keith Hutchings, Philip Nemec, Lety Cavalcante, Trent VictorOur proposed Fatigue Risk Management Framework addresses prevention, monitoring, and mitigation of fatigue-induced risks that affect autonomous specialists during testing of the Waymo Driver.
-
Modeling Road User Response Timing in Naturalistic Traffic Conflicts: A surprise-based framework
Johan Engström, Shu-Yuan Liu, Azadeh Dinparastdjadid, Camelia SimoiuOur framework to analyze and model response timing in a crash-imminent situation on the road.
-
Safety Methodologies
Waymo's Safety Methodologies and Safety Readiness Determinations
Nick Webb, Daniel Smith, Chris Ludwick, Trent Victor, Qi Hommes, Francesca Favaro, George Ivanov, Tom DanielOur Safety Framework – the careful and multilayered approach to safety that has made it possible for Waymo to deploy fully autonomous driving technology on public roads.
-
Collision Avoidance Effectiveness of an Automated Driving System Using a Human Driver Behavior Reference Model in Reconstructed Fatal Collisions
John M. Scanlon, Kristofer D. Kusano, Johan Engström, Trent VictorA study examining how well the Waymo Driver avoids collisions by using a human behavior reference model — the response time and evasive action of a human driver that is non-impaired, with eyes always on the conflict (NIEON).
-
An Omni-Directional Model of Injury Risk
An omni-directional model of injury risk in planar crashes with application for autonomous vehicles.
Timothy L. McMurry, Joseph M. Cormier, Tom Daniel, John M. Scanlon, Jeff R. CrandallPredicting injury risk in a vehicle collision is important for autonomous vehicle design, when most collisions happen in virtual simulations. This paper provides an injury risk function that is continuous in every direction that is more suitable for simulation use than previous injury risk curves.
-
Waymo Safety Report
The Waymo TeamAutonomous driving technology holds the promise to improve road safety and offer new mobility options to millions of people. The Waymo Safety Report, which was originally published in 2017, provides a high-level, general overview of our system safety program, how our fleet of fully autonomous vehicles work, our approach to testing and validation, and how we interact with the public.
Safety Performance Data


Safety Performance Data
-
Safety Performance of the Waymo Rider-Only Automated Driving System at One Million Miles
Trent Victor, Kristofer Kusano, Tilia Gode, Ruoshu Chen, Matthew SchwallAn assessment of all contact events experienced by the Waymo Driver during its first 1M miles without a human behind the wheel supporting that the Waymo Driver is successful at reducing injuries and fatalities.
-
Collision Avoidance Testing of the Waymo Automated Driving System
Kristofer D. Kusano, Kurt Beatty, Scott Schnelle, Francesca Favarò, Cam Crary, Trent VictorOur scenario-based testing methodology to evaluate the Waymo Driver's behavior in conflict situations initiated by other road users.
-
Waymo Simulated Driving Behavior in Reconstructed Fatal Crashes within an AV Operating Domain
John M. Scanlon, Kristofer D. Kusano, Tom Daniel, Christopher Alderson, Alexander Ogle, Trent VictorA study that explores the safety of the Waymo Driver using simulated versions of real-world events. Our latest paper looks at data on fatal crashes that occured within our operating domain in Chandler, Arizona between 2008 - 2017.
-
Waymo Public Road Safety Performance Data
Matthew Schwall, Tom Daniel, Trent Victor, Francesca Favaro, Henning HohnholdOur Public Road Safety Performance Data whitepaper includes details about the miles we’ve driven on public roads in Arizona to provide data about our safe operations in practice.
-
Comparative Safety Performance of Autonomous and Human Drivers
Luigi Di Lillo, Tilia Gode, Xilin Zhou, Margherita Atzei, Ruoshu Chen, Trent VictorA real-world case study of the Waymo One service that compares human drivers against the Waymo Driver, using Swiss Re’s property damage liability and bodily injury claims data from 2016-2021 and Waymo’s rider-only data collected through August 1, 2023. The analysis shows that the Waymo Driver is significantly and consistently safer than human drivers when it comes to crash causation.
Other Technical Publications


Other Technical Publications
-
ADS Standardization Landscape
ADS Standardization Landscape: Making Sense of its Status and of the Associated Research Questions
Scott Schnelle, Francesca FavaroThis paper presents a simplified framework for abstracting and organizing the current landscape of ADS safety standards into high-level, long-term themes. This framework is then utilized to develop and organize associated research questions that have not yet reached widely adopted industry positions, along with identifying potential gaps where further research and standardization is needed.
-
Interpreting Safety Outcomes: Waymo’s Performance Evaluation in the Context of a Broader Determination of Safety Readiness
Francesca M. Favaro, Trent Victor, Henning Hohnhold, Scott SchnelleThis paper calls for a diversified approach to safety determination beyond the analysis of safety outcomes. It highlights a “credibility paradox” within the comparison between ADS data and human-derived baselines, and speaks to continuous confidence growth in ADS performance estimates
-
Measuring Surprise in the Wild
Measuring Surprise in the Wild
Azadeh Dinparastdjadid, Isaac Supeene, Johan EngstromThis paper presents, for the first time, how computational models of surprise rooted in cognitive science and neuroscience combined with state-of-the-art machine learned generative models can be used to detect surprising human behavior in complex, dynamic environments like road traffic. We also present novel approaches to quantify surprise and use naturalistic driving scenarios to demonstrate a number of advantages over existing surprise measures from the literature.
-
An active inference model of car following: Advantages and applications
Ran Wei, Anthony D. McDonald, Alfredo Garcia, Gustav Markkula, Johan Engstrom, Matthew O'KellyThe papers explore a novel way to model human road user behavior by means of active inference, an approach adopted from contemporary cognitive neuroscience. Specifically, the papers show how active inference can provide a middle ground between glass-box mechanistic models and black-box machine-learned models, generating versatile, yet interpretable behavioral outputs.
-
Challenges for the evaluation of automated driving systems using current ADAS and active safety test track protocols
Scott Schnelle, Kristofer D. Kusano, Francesca Favaro, Guy Sier, Trent VictorTo gain practical insight into the types of challenges and limitations arising from executing traditional consumer-focused testing protocols to an ADSs, the Waymo Driver was the subject of a testing campaign that leveraged several of the most difficult currently available ADAS and active safety test procedures. The Waymo Driver was able to pass all of the test procedures and the main challenges discovered were that most procedures that are designed to evaluate collision avoidance behavior could not be evaluated as designed due to the increased capabilities of the Waymo Driver that prevented the vehicle from even entering into a conflict.
-
Representative pedestrian collision injury risk distributions for a dense-urban US ODD using naturalistic dash camera data
Eamon T. Campolettano, John M. Scanlon, Trent VictorAssessing injury severity for collisions involving vulnerable road users (VRUs) is highly impactful for the continued development of traffic safety, including ADAS, ADS, and roadway design. Using naturalistic VRU collision data collected from dashboard cameras of third-party vehicles, a methodology for assessing event severity by pairing accelerometer and GPS data with video to compute impact speed was presented.
-
World model learning from demonstrations with active inference: application to driving behavior
Ran Wei, Alfredo Garcia, Anthony McDonald, Gustav Markkula, Johan Engstrom, Isaac Supeene, Matthew O’KellyThe papers explore a novel way to model human road user behavior by means of active inference, an approach adopted from contemporary cognitive neuroscience. Specifically, the papers show how active inference can provide a middle ground between glass-box mechanistic models and black-box machine-learned models, generating versatile, yet interpretable behavioral outputs.