Waymo automobiles have reportedly racked up greater than 200 million miles of autonomous driving on public roads. However it’s but to run right into a twister or an elephant, and odds are that it’d reply poorly if it did. To strive to assist with these once-in-a-billion-miles eventualities, Waymo introduced Friday that it is introducing Waymo World Model, a generative AI mannequin that it’ll use to run near-endless conditions to strive to make certain its vehicles are ready for the unpredictable, which additionally simply occurs to match into the newest pattern in the AI area.
To be clear, Waymo’s world mannequin makes about as a lot sense as any use case for the expertise. The corporate has a ton of high-definition information that it has collected from its time on the highway that it may possibly use to generate practical re-creations of roads. However, the firm mentioned, as an alternative of constructing a mannequin based mostly solely on that information, it’s going to use Google’s Genie 3 mannequin to put its vehicles in simulated conditions that reach past what is already in its information set collected from cameras and lidar sensors.
We’re excited to introduce the Waymo World Mannequin—a frontier generative mode for large-scale, hyper-realistic autonomous driving simulation constructed on @GoogleDeepMind’s Genie 3.
By simulating the “unattainable”, we proactively put together the Waymo Driver for a few of the most uncommon and… pic.twitter.com/Pl80OMDqLC
— Waymo (@Waymo) February 6, 2026
Google made a splash final month when it released a beta version of Genie 3 to the public, permitting a subset of paid subscribers to generate 3D worlds with practical physics. Not like a big language mannequin (LLM)—the underlying expertise that powers most AI instruments together with Google’s personal Gemini—which use the huge quantity of coaching information they are given to predict the most probably subsequent a part of a sequence, world fashions are skilled on the dynamics of the actual world, together with physics and spatial properties, to create a simulation of how bodily environments function.
Genie 3 🤝 @Waymo
The Waymo World Mannequin generates photorealistic, interactive environments to prepare autonomous automobiles.
This helps the vehicles navigate uncommon, unpredictable occasions before encountering them in actuality. 🧵 pic.twitter.com/m6rlmkMFJH
— Google DeepMind (@GoogleDeepMind) February 6, 2026
Waymo plans to faucet into that to put its vehicles by way of a gauntlet of eventualities that they doubtless wouldn’t discover themselves in till it’s too late. That features excessive climate situations and pure disasters, so the vehicles can work out how to navigate a twister or flood waters; sudden security emergencies like falling tree branches or an accident with a number of particles; and run-ins with the sudden, like an elephant on the highway. “By simulating the ‘unattainable,’ we proactively put together the Waymo Driver for a few of the most uncommon and complicated eventualities,” the firm mentioned.
The speculation is actually sound, although world fashions aren’t with out their drawbacks. The early suggestions on the shopper model of Genie 3 was a bit spotty, and world fashions are nonetheless vulnerable to hallucinations. We’re nonetheless in the earliest levels of seeing these fashions deployed, and so they have a number of room to iterate.
And Waymos have undoubtedly had their points in edge-case eventualities in the actual world. Late final 12 months, a Waymo ran over a beloved bogeda cat named Kit Kat, and final month, one ran into a kid in a school zone. These interactions aren’t even notably uncommon for a driver to discover themselves in, so hopefully Waymo can refine its responses in these eventualities on high of prepping for the impossible conditions.
Disclaimer: This article is sourced from external platforms. OverBeta has not independently verified the information. Readers are advised to verify details before relying on them.
