Nvidia launches Alpamayo, open AI models that allow autonomous vehicles to 'think like a human' | TechCrunch

"The ChatGPT moment for physical AI is here - when machines begin to understand, reason, and act in the real world,"

"Alpamayo brings reasoning to autonomous vehicles, allowing them to think through rare scenarios, drive safely in complex environments, and explain their driving decisions."

"It does this by breaking down problems into steps, reasoning through every possibility, and then selecting the safest path,"

"They can also use Cosmos to generate synthetic data and then train and test their Alpamayo-based AV application on the combination of the real and synthetic dataset,"

Nvidia launched Alpamayo, an open-source family of AI models, simulation tools, and datasets for training physical robots and autonomous vehicles to reason through complex driving situations. The centerpiece, Alpamayo 1, is a 10-billion-parameter chain-of-thought, reason-based vision-language-action (VLA) model that breaks problems into steps, reasons through possibilities, and selects the safest path. Alpamayo 1 enables vehicles to address complex edge cases without prior experience, such as navigating a traffic light outage at a busy intersection. The underlying code is available on Hugging Face and can be fine-tuned or distilled into smaller, faster versions. Developers can use Nvidia’s Cosmos to generate synthetic worlds and combine them with real data for training and testing. Nvidia is releasing an open driving dataset with more than 1,700 hours of data collected across diverse geographies.

Read at TechCrunch