# Waymo's Safety Methodologies and Safety Readiness Determinations

arXiv: https://arxiv.org/abs/2011.00054 · HTML: https://mlsanity.com/paper/2011.00054/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2020.

## Built on by (most cited first, 16 of 16)

- [Learning Realistic Traffic Agents in Closed-loop](https://mlsanity.com/paper/2311.01394/) (2023)
- [What Truly Matters in Trajectory Prediction for Autonomous Driving?](https://mlsanity.com/paper/2306.15136/) (2023)
- [Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking](https://mlsanity.com/paper/2411.00174/) (2024)
- [The missing link: Developing a safety case for perception components in automated driving](https://mlsanity.com/paper/2108.13294/) (2021)
- [DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Models](https://mlsanity.com/paper/2503.05808/) (2025)
- [Few-Shot Scenario Testing for Autonomous Vehicles Based on Neighborhood Coverage and Similarity](https://mlsanity.com/paper/2402.01795/) (2024)
- [Agent-aware State Estimation in Autonomous Vehicles](https://mlsanity.com/paper/2108.00366/) (2021)
- [Savvy: Trustworthy Autonomous Vehicles Architecture](https://mlsanity.com/paper/2402.14580/) (2024)
- [Future Intelligent Autonomous Robots, Ethical by Design. Learning from Autonomous Cars Ethics](https://mlsanity.com/paper/2107.08122/) (2021)
- [Taking the Intentional Stance Seriously, or "Intending" to Improve Cognitive Systems](https://mlsanity.com/paper/2209.11764/) (2022)
- [Exiting the Simulation: The Road to Robust and Resilient Autonomous Vehicles at Scale](https://mlsanity.com/paper/2210.10876/) (2022)
- [Finding Needles in Haystack: Formal Generative Models for Efficient Massive Parallel Simulations](https://mlsanity.com/paper/2301.01594/) (2023)
- [Systems Engineering for Autonomous Vehicles; Supervising AI using Large Language Models (SSuperLLM)](https://mlsanity.com/paper/2501.10839/) (2025)
- [A Five-Layer MLOps Architecture for Connected Automated Driving](https://mlsanity.com/paper/2605.12719/) (2026)
- [Guiding Neuro-Symbolic Scenario Generation with Spatio-Temporal Logic](https://mlsanity.com/paper/2605.19038/) (2026)
- [LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles](https://mlsanity.com/paper/2608.13450/) (2026)

## Abstract (arXiv)

Waymo's safety methodologies, which draw on well established engineering processes and address new safety challenges specific to Automated Vehicle technology, provide a firm foundation for safe deployment of Waymo's Level 4 ADS, which Waymo also refers to as the Waymo Driver. Waymo's determination of its readiness to deploy its AVs safely in different settings rests on that firm foundation and on a thorough analysis of risks specific to a particular Operational Design Domain. Waymo's process for making these readiness determinations entails an ordered examination of the relevant outputs from all of its safety methodologies combined with careful safety and engineering judgment focused on the specific facts relevant for a particular determination. Waymo will approve when it determines the ADS is ready for the new conditions without creating any unreasonable risks to safety. This paper explains Waymo's methodologies as applied to the three layers of its technology: hardware, ADS behavior, and operations, and also explains Waymo's safety governance. Waymo will continue to apply and adapt those methodologies, and to learn from the important contributions of others in the AV industry, as Waymo continues to build an ever safer and more able ADS.