Evaluation is the hardest problem for physical AI systems: do you crash test cars every time you debug a new FSD build? Traditional game engine (sim 1.0) is an alternative, but it's not possible to hard-code all edge cases. A neural net-based sim 2.0 is purely programmed by data,

🚀 Teaching the SO-ARM to lift a cube, the pure RL way in Isaac Lab. 🦾 No imitation learning. No pre-defined motions. Just trial, error, and learning. Partnering with @LycheeAI to bring open-source RL training for the SO-ARM100/101. 📂 Repo: github.com/MuammerBay/Isa…

🤖 The future of smart manufacturing is simulation-first. Amazon Devices and Services is making a leap in manufacturing by leveraging #DigitalTwins, NVIDIA AI, and #NVIDIARobotics technology to train robots for highly precise quality audits. #SIGGRAPH2025 Learn more 👉

👀 Get a first look at how synthetic data, 3D graphics, and AI advancements are changing the game and explore how Physical AI is shaping smarter, more capable machines. 🦾 🤖✨ #NVIDIACosmos + Nemotron reasoning models use synthetic data to supercharge multimodal learning —

The wait is over. 🥁 NVIDIA Isaac Sim 5.0 and Isaac Lab 2.2 are now generally available. Dive in and start to simulate, train, and validate your AI-powered robots with these new key features: ⚡ Instant GPU access via NVIDIA Brev 🤖 3D #GaussianSplatting with @NVIDIAOmniverse

I got tired of people complaining that IsaacLab is hard to install. here’s a single makefile to install everything and set it up. conda or uv. go wild: github.com/KyleM73/isaac_…

Nvidia launched Jetson AGX Thor, a $3,499 chip for real-time physical AI It uses a 2,560-core Blackwell GPU, 96 fifth-generation Tensor cores, and 128GB of memory to deliver up to 2,070 FP4 teraflops of AI compute

It's real and just ran the whole time Jason Ma was giving a talk. Dynasaur folding t-shirts autonomously at Actuate

People often use student-teacher setups -- where a teacher has access to underlying state -- to make training easier but this is inherently limiting. In the end there are few shortcuts that don't end up limiting you; important to just solve the problem you actually want solved.

Happening in less than an hour. 👀

Newton's Classroom - The Physics Class Every Robot Should Attend x.com/i/broadcasts/1…

Be a part of the next era of physical AI. 👏 Join our labs at #NVIDIAGTC Washington D.C., where you’ll get hands-on with OpenUSD, industrial digital twins, robotics, and more. Don't miss: 👀 Advancing World Simulation with 3D Gaussian Splatting 🧠 An Introduction to NVIDIA

Over 100 contestants joined our #EmbodiedAIHackathon in Shenzhen! 🤖🔥 From single #robot arm pick & place to dual-arm manipulation, from handling rigid objects to soft textiles, teams pushed boundaries — evolving into long-horizon actions with stronger generalization. Next

Can't wait to see all the projects come to life at the #EmbodiedAIHackathon in Mountain View. 🙌 See you there?

AI is transforming the world’s factories into intelligent thinking machines, the engines of a new industrial revolution.” - Jensen Huang 👏 Announced today at #NVIDIAGTC, America’s leading manufacturers are building state-of-the-art robotic factories to help overcome labor

NVIDIA is bringing safety and AI performance to robotics, medical, and industrial fields. ⚡ The NVIDIA IGX Thor, announced at #NVIDIAGTC, delivers real-time physical AI to the edge with enterprise-grade reliability. This powerful, industrial-grade platform empowers developers

Announced at #NVIDIAGTC: NVIDIA AI physics is powering the future of aerospace and automotive design. By integrating GPU-accelerated computing, NVIDIA AI Physics and interactive digital twin technologies, enterprises are accelerating their modeling and simulation workflows by up

U.S. manufacturers face significant obstacles, from reshoring to lack of skilled labor. 🏭 Rev Lebaredian hosted a panel at #NVIDIAGTC featuring manufacturing leaders across the semiconductor, pharmaceutical, and robotics industries. Read how Agility Robotics, CaterpillarInc,

Working side by side with robots? Safety is key. 🤖 Matt Powers from Boston Dynamics shares his quick take on innovation, policy, and safety best practices. Full panel recording coming soon. #NVIDIAGTC

Researchers are exploring Marble’s generative 3D worlds as a way to rapidly produce simulation-ready environments for robotics without manual scene construction.