NVIDIA Tutorial: Deploying VLA Models for Robot Manipulation with LeRobot and ROS 2
NVIDIA Developer · youtube · 2026-08-12
NVIDIA Jetson AI Lab released a hands-on tutorial on robot manipulation, focusing on applying Vision-Language Models (VLM) and Vision-Language-Action Models (VLA) to real-world physical AI tasks.
Key topics covered:
- Model Selection: Analyzes when to use a general VLM like Gemma 4 versus a specialized robotics model like NVIDIA GR00T.
- Task Execution: Demonstrates how to apply these models to practical manipulation tasks such as pick and place.
- SW/HW Integration: Explains how to orchestrate model outputs via the ROS 2 framework to drive real robot behavior, including a live hardware demo using the SO-101 or reBot Arm.
Related event: NVIDIA Releases LeRobot and ROS 2 Robotics Tutorial(3 posts)→
More from coding & agent
- Beware of Claude Code in Science: AI Hallucinates Data Verification Standards — rishabh16_ · 2026-08-12
- Grok Bot Test: Autonomously Pulls and Analyzes Full GitHub Repositories — prasenx · 2026-08-12
- Are We Wasting Local GPU Power? Call for Natively Parallel AI Models — FaithlessnessFar6431 · 2026-08-12
- Graft Hits 1.6k Stars: Open-Source Context Layer for Coding Agents — shhdwi · 2026-08-12
- Cursor Integrates with Grok: SuperGrok Subscription Now Unlocks Cursor Ultra — XFreeze · 2026-08-12
- Shumer Announces Public Release of OpenClaw, Praises Grok Bot — mattshumer_ · 2026-08-12