Nvidia launches Alpamayo, an open AI model that allows self-driving vehicles to ‘think like a human’

At CES 2026, Nvidia launched Alpamayo, a new family of open source AI models, simulation tools, and datasets for training physical robots and vehicles designed to help autonomous vehicles reason through complex driving situations.

“The ChatGPT moment for physical AI has arrived — when machines begin to understand, think, and act in the real world,” Nvidia CEO Jensen Huang said in a statement. “Alpamayo brings logic to autonomous vehicles, allowing them to reason through rare scenarios, drive safely in complex environments, and explain their driving decisions.”

At the heart of Nvidia’s new family is Alpamayo 1, a 10-billion-parameter thought chain and reason-based Vision Language Action (VLA) model that allows self-driving vehicles to think more like a human so they can solve complex edge cases — such as how to navigate when a traffic light breaks at a busy intersection — without prior experience.

“It does this by breaking down problems into steps, considering all the possibilities, and then choosing the safest path,” Ali Kani, Nvidia’s vice president of automotive, said Monday during a press conference.

Or as Huang said during his keynote on Monday: “It’s not just that, it is.” [Alpamayo] Take the sensor inputs and activate the steering wheel, brakes and acceleration, and it determines what action it is about to take. He tells you the action he will take, and the reasons why he took that action. And then the track, of course.”

The base code for Alpamayo 1 is available on Hugging Face. Developers can fine-tune Alpamayo into smaller, faster versions for vehicle development, use it to train simpler driving systems, or build tools on top of it such as auto-tagging systems that tag video data automatically or assessment tools that check whether a car made an intelligent decision.

“They can also use Cosmos to generate synthetic data and then train and test their Alpamayo-based autonomous vehicle application on a mix of real and synthetic data set,” said Kani. Cosmos is Nvidia’s brand for generative world models, artificial intelligence systems that create a representation of a physical environment so you can make predictions and take action.

As part of the Alpamayo rollout, Nvidia is also releasing an open dataset containing more than 1,700 hours of driving data collected across a range of geographies and conditions, covering rare and complex real-world scenarios. In addition, the company is launching AlpaSim, an open source simulation framework for validating autonomous driving systems. AlpaSim, available on GitHub, is designed to recreate real-world driving conditions, from sensors to traffic, so developers can safely test systems at scale.