{"id":13820,"date":"2025-01-07T09:50:49","date_gmt":"2025-01-07T09:50:49","guid":{"rendered":"https:\/\/topat10.com\/?p=13820"},"modified":"2025-01-07T09:50:49","modified_gmt":"2025-01-07T09:50:49","slug":"nvidias-cosmos-ai-helps-humanoid-robots-navigate-the-world","status":"publish","type":"post","link":"https:\/\/topat10.com\/?p=13820","title":{"rendered":"Nvidia\u2019s \u2018Cosmos\u2019 AI Helps Humanoid Robots Navigate the World"},"content":{"rendered":"


\n<\/p>\n

\n

Nvidia announced today it\u2019s releasing a family of foundational AI models called Cosmos that can be used to train humanoids<\/a>, industrial robots, and self-driving cars<\/a>. While language models learn how to generate text by training on copious amounts of books, articles, and social media posts, Cosmos is designed to generate images and 3D models of the physical world.<\/p>\n

During a keynote presentation at the annual CES conference in Las Vegas, Nvidia CEO Jensen Huang<\/a> showed examples of Cosmos being used to simulate activities inside of warehouses. Cosmos was trained on 20 million hours of real footage of \u201chumans walking, hands moving, manipulating things,\u201d Jensen said. \u201cIt\u2019s not about generating creative content, but teaching the AI to understand the physical world.\u201d<\/p>\n

Researchers and startups hope that these kinds of foundational models could give robots used in factories and homes<\/a> more sophisticated capabilities. Cosmos can, for example, generate realistic video footage of boxes falling from shelves inside a warehouse, which can be used to train a robot to recognize accidents. Users can also fine-tune the models using their own data.<\/p>\n

A number of companies are already using Cosmos, Nvidia says, including humanoid robot startups Agility and Figure AI as well as self-driving car companies like Uber, Waabi, and Wayve.<\/p>\n

\n