vision language action

  • Nvidia Unveils Alpamayo for Autonomous Vehicles


    Nvidia launches Alpamayo, open AI models that allow autonomous vehicles to ‘think like a human’Nvidia has introduced Alpamayo, a suite of open-source AI models, simulation tools, and datasets aimed at enhancing the reasoning abilities of autonomous vehicles (AVs). Alpamayo's core model, Alpamayo 1, features a 10-billion-parameter vision language action model that mimics human-like thinking to navigate complex driving scenarios, such as traffic light outages, by breaking down problems into manageable steps. Developers can customize Alpamayo for various applications, including training simpler driving systems and creating auto-labeling tools. Additionally, Nvidia is offering a comprehensive dataset with over 1,700 hours of driving data and AlpaSim, a simulation framework for testing AV systems in realistic conditions. This advancement is significant as it aims to improve the safety and decision-making capabilities of autonomous vehicles, bringing them closer to real-world deployment.

    Read Full Article: Nvidia Unveils Alpamayo for Autonomous Vehicles