From controlling a robot arm to running the brain behind a robot — this session bridges physical robotics and AI. We start with Gr00t 1.7, NVIDIA's foundation model for robots — what it can do, how to run it, and how to fine-tune it, with a live demo of it in action. From there, we break down ROS: what it is, how graphs and nodes work together, and how it serves as the operating system and control layer that connects everything. We then get hands-on with the SO101, showing how to deploy a model that can execute real-world tasks on your behalf. We close with a guest speaker covering the latest open-source robotics advances and community highlights.
In this stream, you will learn how to bring vision-language models into real-world physical AI applications — from model selection to robot control.
We'll cover:
- Gr00t 1.7 in depth — explore NVIDIA's foundation model for robots: what it can do, how to run it, and how to fine-tune it for your use case, with a live demo of it in action.
- ROS fundamentals and connecting the dots — learn what ROS is, how graphs and nodes work together, and how it serves as the operating system and control layer that ties your models, sensors, and actuators together.
- Hands-on with the SO101 — walk through a live example deploying a model to execute real-world tasks, putting everything together from model inference to physical actuation.
- Open-source robotics highlights — a guest speaker covers the latest advances and community highlights in open-source robotics worth knowing about.
Watch all three episodes on the NVIDIA Jetson AI Lab YouTube playlist here.