Real-world robot data is expensive and slow to collect, creating a major challenge for humanoid development. 🤖 The NVIDIA GR00T N1.6 open vision language action model is pre-trained on a diverse mix of data, including thousands of hours of Stanford Vision and Learning Lab’s BEHAVIOR simulation data, which covers long-horizon everyday manipulation tasks. This diverse training is the key to robust cross-embodiment performance and real-world adaptability. 🌍 Read the blog 🔗 https://nvda.ws/4q3Kn9

Get started with JetBot, a new open source autonomous robotics kit to build an AI-powered #deeplearning robot for under $250-- the brains behind this bot is Jetson Nano. #GTC19 https://nvda.ws/2HJFyRB | NVIDIA Robotics

25K views · 32 reactions | AI-powered robotics are revolutionizing the way we work and live. Watch now to see the diverse robotics partner solutions showcased at NVIDIA’s #GTC18, from detecting defects in phone housings to on-demand food and product delivery. Learn more: https://nvda.ws/2GDi0gV | NVIDIA Robotics | Facebook

17K views · 337 reactions | Dex is ready for the factory floor.  Learn how Richtech Robotics built this mobile humanoid robot, powered by NVIDIA Jetson AGX Thor and trained in Isaac Sim, to handle light to medium industrial tasks. Read the blog ➡️ https://nvda.ws/4pqUoOR | NVIDIA Robotics | Facebook