Like it or not, autonomous vehicles (AVs) are coming and all of us on the roads are part of the experiment.
In the US, how safe are AVs?
The US leader in autonomy, Waymo, a Google/Alphabet-backed venture, periodically releases safety data that provides a window into their AV’s safety.
The other big news maker in US AVs, Tesla, doesn’t release detailed data on its advanced driver-assist safety and does not yet have AVs (unsupervised) on public roads (instead they are testing a small fleet with humans in the vehicle who supervise the AI driving).
Waymo has AVs that are rider-only (robot drives the car without human supervision) on city roads (no highways yet) in Phoenix, San Fran, LA and Austin.
After about 96 million miles, Waymo had about 304 fewer injury crashes, 80% lower, than a human driver benchmark.
Hmmm, as I am due, after today, to renew my DL, I wonder if one is needed if you own an AV? You aren’t driving, just a passenger, it would be like taking an Uber, Lyft or taxi!
Great news, Londoners! We’re bringing our fully autonomous ride-hailing service across the pond, where we intend to offer rides – with no human behind the wheel – in 2026.
Waymo’s expansion, current and planned (interesting times).
Currently, 11 cities have true autonomous driving and 6 have current commercial service and 4 (testing now) are planned to have commercial service by end of 2025. One city (testing now) has service planned for 2026.
Waymo plans for at least a total of 17 cities to have commercial service by the end of 2026.
Driverless is true autonomy (unsupervised by a human).
Supervised is human responsible for the driving even if AI/robot is driving, which is used to test the AI driver.
Commercial driverless operations:
San Francisco [and Bay Area: San Mateo, Redwood City, Palo Alto, San Jose]
Los Angeles
Phoenix
Atlanta
Austin
Miami (began Nov 18)
Driverless testing, commercial service expected in 2026:
Dallas - end of 2025
Houston - end of 2025
San Antonio - end of 2025
Orlando - end of 2025
San Diego - in 2026
Supervised testing, commercial service expected in 2026:
Las Vegas
Denver
Detroit
Nashville
Washington DC
London
Supervised testing for service in 2026 or beyond (aka, no confirmed launch timeline):
Safety data release from Waymo, now with robotaxis in 10 metro areas and 170 million autonomous miles as of December 2025 and accumulating 4 million autonomous miles per week.
Waymo is the only robotaxi deployed at anything near this scale in the US, so no meaningful robotaxi competition at the moment (although many companies are making announcements and running very small deployments).
I’ve now seen them in two cities, but have not ridden.
I crossed the street in front of one and it did not run me over.
There is a lot of information in the links, including very technical details on how they try to do apples-to-apples statistical comparison to human drivers.
This is not experimental data like a clinical trial, so the results are even more dependent on the assumptions in their statistical model (this is not good or bad, just the state of the art).
Waymo has released new data indicating that the Waymo Driver continues to make roads safer in the places in which we operate.
A new analysis covers over 170 million fully autonomous miles—an equivalent of 200 human lifetimes of driving. The data shows that regardless of fault, the Waymo Driver was involved in 92% fewer crashes that cause serious or fatal injuries than human drivers in the same driving conditions. Our Driver was also involved in 83% fewer crashes where airbags are deployed, and 82% fewer crashes involving any injuries at all.
At our current scale, driving over 4 million miles weekly, our analysis suggests the Waymo Driver is preventing approximately one serious-injury crash every 8 days.
Recent interview with Waymo co-CEO that provides a window into their AI capabilities (long interview, summary further below as well).
(At 4 million miles per week, Waymo is on pace to more than double their cumulative miles this year to go from 170 to over 400 million. At 500,000 rides per week, they average 8 miles per ride. To continue their scaling across more metro areas, they need to not be at fault for a bad accident.)
One of the most significant technical revelations is how Waymo has moved beyond simple modular systems to a sophisticated foundation-model-driven approach:
Offboard Foundation Model: Waymo starts with a massive offboard model that understands the physical and social aspects of the world [07:31].
The Three Teachers: This foundation is specialized into three high-capacity “teacher” models:
The Waymo Driver: The core intelligence that handles driving.
The Simulator: A generative model that creates realistic, closed-loop synthetic environments for training [08:15].
The Critic: An opinionated model that identifies interesting events and judges whether a behavior was “good” or “bad” [09:18].
Distillation: These large teacher models are then “distilled” into smaller, highly efficient “student” models that can run real-time inference on the vehicle’s onboard computer [09:50].
Generalizability & “Zero-Shot” Learning
Dolgov emphasizes that Waymo is no longer in the “research” phase but in a “global scaling” phase, enabled by AI that generalizes across domains [23:57].
Inheriting World Knowledge: By hooking the Waymo Driver into VLMs, the system inherits general world knowledge. This allows for “zero-shot” or “few-shot” learning, where the car can understand new environments or signs without needing specific training data for every new city [25:30].
The “Tick-Tock” Cycle: Waymo’s scaling strategy mimics a hardware/software “tick-tock” cycle. Generation 6 features a brand-new custom vehicle and sensor stack (the “tick”), while keeping the software relatively consistent (the “tock”) to prove generalizability across different vehicle platforms [36:04].
Novel Technical Insights
“X-Ray” Vision through Multi-Modal Fusion: Dolgov shares a striking example where a Waymo vehicle “saw” a pedestrian through a bus. It wasn’t magic or literally seeing through metal; rather, the AI detected extremely noisy peripheral LiDAR reflections bouncing under the bus off the pedestrian’s feet. The models were sophisticated enough to interpret those few noisy bits as a human and predict their path [45:11].
Cloud vs. Local Inference: While all driving-critical inference happens locally on the car, Waymo uses the cloud for “nice-to-have” tasks. For example, after a ride, an offboard model checks the car for left-behind items or messes to decide if it needs to go to a cleaning depot [06:13].
Generative Simulation vs. Pixels: Dolgov explains the debate over “end-to-end” (pixels-to-actions) systems. He argues that while pure end-to-end is impressive (the “talking horse” effect), it is too inefficient for safety at scale. Waymo uses an augmented architecture that maintains intermediate representations (concepts like “roads” and “signs”) because they provide the “knobs” necessary to run efficient simulations and specify reward functions for the “Critic” [18:53].
Hardware: The 6th Generation & Cost Reduction
Custom Vehicle Design: The upcoming 6th generation is a custom-designed vehicle (not a derivative of a consumer car like the Jaguar I-PACE) featuring sliding doors, a flat floor, and a living-room-like interior [32:43].
Drastic Cost Reduction: The Gen 6 sensor stack is a “fraction of the cost” of previous versions, bringing the price of a fully autonomous hardware suite down to a level comparable to high-end consumer Driver Assist (ADAS) systems [35:40].
Sensor Strengths: He clarifies why LiDAR and Radar are both essential: while LiDAR provides fine-grained mapping, imaging radar is critical for high-speed freeway driving in dense fog because its physics allow it to see through particulates that blind cameras and LiDAR [39:13].
Operational Efficiency
The “Autonomous Dance”: Waymo depots are now highly automated. Cars automatically navigate to depots for charging or cleaning, use icons on their “sensor dome” to signal staff what they need (e.g., a cleaning emoji), and self-orchestrate their movements within the facility [52:14].
Global Expansion: As of the recording, Waymo is operating in 11 U.S. cities (with Nashville being the most recent “ghost city” launch) and is preparing to launch in * London and Tokyo [24:42].