%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
In the 2026 Consumer Electronics Show (CES), NVIDIA launched a new open-source AI platform called Alpamayo. This platform is specifically designed for physical robots and autonomous vehicles, aiming to help these smart devices make more intelligent decisions in complex driving scenarios. NVIDIA's CEO, Jensen Huang, stated that the release of this platform marks the "ChatGPT moment" for machines to understand, reason, and act in the real world.
The core of Alpamayo is the model called "Alpamayo1," which has 10 billion parameters and uses advanced vision-language-action (VLA) technology. This allows autonomous vehicles to think like humans and handle complex scenarios such as malfunctioning traffic lights without being labeled or trained. For example, when a vehicle encounters an intersection with a broken traffic light, Alpamayo1 can autonomously plan a safe route through it.
Ali Kanai, Vice President of NVIDIA's Automotive Division, added that the model works by breaking down complex problems into multiple simple steps, evaluating each possibility, and finally choosing the safest solution. This means that vehicles can not only control the steering wheel, brakes, and accelerator based on sensor inputs but also clearly explain the actions they are about to take and the reasoning behind them to the driver.
To support developers, NVIDIA has already opened the underlying code of Alpamayo1 on the Hugging Face platform, allowing developers to fine-tune and build lightweight versions of the model. In addition, NVIDIA has released a cross-border driving dataset covering 1,727 hours, including real-world traffic conditions from 25 countries and over 2,500 cities, aimed at helping developers better train and test their autonomous driving systems.
At the same time, NVIDIA's AlpaSim simulation framework is also open, used to accurately recreate real driving environments, helping developers conduct large-scale safety testing of autonomous driving systems. With the first car equipped with NVIDIA technology expected to hit the road in the first quarter in the United States, the release of Alpamayo undoubtedly will accelerate the development of autonomous driving technology and usher in a new era of intelligent driving.