Everything that moves will one day be autonomous. Demand for autonomous machines and AI-enabled robots is at an all-time high as industries look to improve operational efficiency, combat workforce shortages, optimize repetitive tasks, and manage dangerous tasks or environments.
With major advancements in AI, accelerated computing, physically based simulation, and a vast ecosystem of sensors and actuators, today’s AI robots can easily adapt, learn, and perform complex tasks with precision.
Developers are using NVIDIA Robotics full-stack, accelerated cloud-to-edge systems, acceleration libraries, and optimized AI models to develop, train, simulate, deploy, operate, and optimize their robot systems and software.
Catch up with Jim Fan from the NVIDIA Research team as he discusses the latest suite of tools, models, and platforms developers can use to improve their AI models and more efficiently build humanoid robots.
Advance generative AI for robotics with NVIDIA NIM™ inference microservices for robotics simulation in Isaac Lab and Isaac Sim™, OSMO robot cloud compute orchestration service, teleoperated data capture workflows, and more.
New services accelerate universal scene description-based workflows and development of industrial digital twins and robotics.
NVIDIA Isaac ROS is built on the open-source ROS 2™ (Robot Operating System) software framework. This means the millions of developers in the ROS community can easily take advantage of NVIDIA-accelerated libraries and AI models to accelerate their AI robot development and deployment workflows.
Discover a large community of partners that can help you build your full robot system with products ranging from specialized boards to AI software to application design services to sensors and developer tools.
Learn how these new services accelerate universal scene description-based workflows and development of industrial digital twins and robotics.
Fraunhofer IML
NVIDIA Omniverse™ Cloud Sensor RTX generates synthetic data to speed AI development of autonomous vehicles, robotic arms, mobile robots, humanoids, and smart spaces.
For the annual AI City Challenge at CVPR, hundreds of teams from around the world tested their AI models on physically based datasets generated with NVIDIA Omniverse. The results will help researchers and developers advance the development of solutions for smart cities and industrial automation.
Fourier Intelligence
NVIDIA Omniverse is a development platform for virtual world simulation that combines real-time physically based rendering, physics simulation, and generative AI technologies. In Omniverse, robots can learn to be robots—minimizing the sim-to-real gap, and maximizing the transfer of learned behavior.
NVIDIA Omniverse, Isaac, and Metropolis enable Delta Electronics, Foxconn, Pegatron, and Wistron to digitally build, simulate and operate factory digital twins.
Learn about the NVIDIA Robotics platform for robotics and vision AI.
The Isaac robotics platform includes a full suite of NVIDIA-accelerated systems, libraries, application frameworks, and generative AI models to help you advance AI perception, manipulation, and simulation.
NVIDIA Metropolis is an application framework, set of developer tools, and partner ecosystem that brings visual data and AI together. This helps improve operational efficiency and safety across a range of industries.
Physically accurate simulation and synthetic data generation accelerate development, testing, and validation of AI robots. NVIDIA Isaac Sim is a fully customizable application framework, built on Omniverse, that lets you put these tools to work to simulate and test your AI robots’ trained skills.
AI robot development workflows are complex, requiring many workloads to be orchestrated across several compute environments. Now, developers can use NVIDIA OSMO to easily deploy multi-container workloads across heterogeneous shared compute resources with no specialized knowledge.
For the broader industry, our work with NVIDIA shows how foundation models can have a profound impact, including making today’s processing challenges easier to manage at scale, creating previously infeasible applications, reducing development costs, and increasing flexibility for end users.
— Wendy Tan White, CEO at Intrinsic
ROS continues to grow and evolve to provide open-source software for the whole robotics community…NVIDIA’s new prebuilt ROS 2 packages, launched with this release, will accelerate that growth by making ROS 2 readily available to the vast NVIDIA Jetson developer community.
— Geoff Biggs, CTO of the Open Source Robotics Foundation
At Collaborative Robotics, we have a deep conviction that the future of robotics involves collaborative robots working alongside humans…We’ve adopted a sim-first development approach, using Isaac Sim extensively to accelerate our development and deployment timelines.
— Jon Battles, VP of Technology Strategy of Collaborative Robotics
Featured
NVIDIA Isaac Perceptor, optimized on Jetson Orin, uses multiple cameras for 3D surround perception to detect obstacles. Robust AI-based depth estimation, GPU-accelerated 3D reconstruction, and semantic segmentation lets the mobile robot work more safely alongside humans.
Videos
NVIDIA Research uses artificial intelligence to enable breakthroughs in robotics that solve real-world problems in a variety of industries like manufacturing, logistics, and healthcare. We focus on areas such as robot manipulation, physics-based simulation, and robot perception. The goal is to develop the next generation of robots that can robustly manipulate the physical world and safely work alongside humans.
Connect with robotics experts live to get your questions answered.
Learn at your own pace with free getting-started material.
Get the latest news in robotics from NVIDIA.
NVIDIA Privacy Policy