Running LLMs on edge devices? This is a must-watch from JetsonHacks. 👀 Watch as he unlocks 10x performance with Gemma 4 on NVIDIA Jetson Orin Nano by understanding what's really required for edge AI—model size, quantization, and memory optimization done right. 🎥 https://nvda.ws/4t9zrZY
NVIDIA Robotics
Computer Hardware Manufacturing
Santa Clara, California 496,137 followers
Inspiring visionaries and developers to create the next gen of AI-driven robots and explore the world of physical AI.
About us
The NVIDIA Robotics platform accelerates the development of AI-driven robots, streamlining processes from design and simulation to deployment. It enables key functions like navigation, mobility, grasping, and vision, supporting robotics across industries such as manufacturing, agriculture, logistics, and healthcare.
- Website
-
https://www.nvidia.com/en-us/industries/robotics/
External link for NVIDIA Robotics
- Industry
- Computer Hardware Manufacturing
- Company size
- 10,001+ employees
- Headquarters
- Santa Clara, California
Updates
-
Did you spot Humanoid's robots at #HM26? 🤖 Hear Sotirios Stasinopoulos, Chief Product Officer at Humanoid, explain how they're using NVIDIA and Siemens technology to accelerate hardware development and AI model training. Read the blog 👉 https://nvda.ws/4cLHt4M
-
Heading to Week of Robotics in Odense next week? 🦾 Join us and the robotics ecosystem to explore the future of physical AI — from simulation and training to edge deployment. Learn more 🔗 https://nvda.ws/48sLZUM Odense Robotics
-
-
NVIDIA Nemotron 3 Nano Omni, a new multimodal model, is now live on Jetson AI Lab. 🙌 This open multimodal model unifies vision, audio, and language into a single reasoning loop. No cloud required. Power your NemoClaws by running this model with Ollama, vLLM and other inference frameworks on NVIDIA Jetson hardware. ➡️ https://nvda.ws/4t9nSlx
-
Experience the SO-101 teleop arm yourself—this simple task is more interesting than it looks. 🦾
So, why did we pick this task for the SO-101 workshop? We wanted to find a problem that was accessible in terms of teleoperation, but had some nuances that made it interesting, all while being a direct analogy for a real-world problem. This video shows you some of the nuances of what make it tricky. 1. The rack and vials are scattered, albeit within a certain area. 2. The vial blocks the gripper camera (well, a lot of it) while holding the vial. 3. The vials might be aimed differently depending on how they're grasped. With an SO-101 teleop arm, you can try out this task in simulation using our code! Link to the full course in comments. NVIDIA Robotics
-
The Physical AI Robotics GR00T‑X Embodiment Sim dataset has surpassed 10 million downloads on Hugging Face. 🥳 A huge shoutout to the global research and developer community exploring the future of embodied AI and robotics with this open dataset — you made this milestone possible. 📥 Try it on Hugging Face 👉 https://nvda.ws/42AkKnF
-
-
Great read from IEC on how AI is reshaping industrial automation and robotics, highlighting the importance of safety and standards, with insights from our experts. 👇
AI is transforming robotics and industrial automation, boosting productivity and reducing downtime across manufacturing. But with rapid innovation come new challenges. International standards play a key role in ensuring reliability, safety and interoperability. Learn more: https://lnkd.in/eSFfEyaa #IECEmergingTech #AI #Robotics #IndustrialAutomation #Innovation NVIDIA Dr. Riccardo Mariani
-
-
NVIDIA Robotics reposted this
Another successful HANNOVER MESSE in the books. 👏 Amazing to see our industrial AI partners showcasing AI-driven manufacturing in action and pushing the ecosystem forward together. Read the full #HM26 blog to catch up on all the industrial advancements 👉 https://nvda.ws/3OhfEJI
-
-
NVIDIA Robotics reposted this
Visiting Agile Robots! 🦾 We're back on the NVIDIA tour with Akhil Docca, right now at the booth of Agile Robots. Akhil Docca, Head of Robotics Product Marketing at NVIDIA explains how NVIDIA and Agile Robots are tackling the integration challenge, and with a new partner joining the conversation, it's a great moment to dive in. As with many of their ecosystem partners, NVIDIA has a strong relationship with Agile Robots SE, connected across multiple layers. The first layer is the Industrial AI Cloud, announced and launched together with T-Systems, which Agile Robots is using to train their humanoid brain.🧠 The second layer involves Idealworks, where Agile Robots is using Isaac Sim to integrate into their AMRs at the factory scale level. The third layer is Franka Robotics, leveraging Isaac Sim and Isaac Lab for synthetic data generation, bringing deeper research capabilities into their robotics development. NVIDIA can support Agile Robots at any level they need. The NVIDIA platform is fully disaggregated, meaning any partner can pick and choose the components that make sense for them. In Agile's case, that meant taking Isaac Sim and Isaac Lab, building their own foundation model, and sourcing the compute through NVIDIA. Agile Robots is a great example of exactly how that collaboration is meant to work. With that, it's time to move on to the next partner. HANNOVER MESSE 2026! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news → http:// ziegler.substack.com
-
Dive deeper into building robots in this technical talk at Week of Robotics in Odense, Denmark. 🤖 Join Kartik Sachdev to explore the full physical AI lifecycle — from data curation and OpenUSD-based digital twins to high-fidelity simulation and real-world deployment. Learn how to go beyond scripted behavior and quickly build autonomous robots and humanoids. 🔗 https://nvda.ws/4efPMbK 📅 Wednesday, May 6 | 3:00 p.m. CEST 📍 UCL University Lillebaelt, R&D Workshop Track 2 Odense Robotics
-