Accelerate AI-enabled robotics with industry-leading hardware, software, simulation, and cloud infrastructure.
The NVIDIA Isaac™ robotics platform includes a full suite of GPU-accelerated innovations in AI perception, manipulation, simulation, and software. You can now take your performance to the next level by optimizing for advancements in AI—including robot learning, LLMs, generative AI, and foundation models.
The GROOT general-purpose foundation model will act as the mind of robots, making them capable of learning skills to solve a variety of helpful tasks.
The robotics platform is adding new foundation models, a robot learning framework, and AI workflow orchestration and robot perception tools.
NVIDIA Isaac Perceptor's unmatched precision enables 3D perception for automated material-handling equipment and service robots, letting them operate safely and effectively in dynamic environments. NVIDIA Isaac Sim™ also provides software-in-the-loop development and testing using simulated sensors.
NVIDIA Isaac Lab, a lightweight app built on top of Isaac Sim, delivers robot learning with integrated physics for complex grasping tasks. Start with pre-trained models and synthetic data from NVIDIA Omniverse™ Replicator for robot training. Define the robot's task, validate its training, and deploy advanced robotic manipulation and grasping with NVIDIA Isaac Manipulator to reduce cycle times for re-training when tracking new objects.
NVIDIA Jetson™, with its exceptional efficiency, powers autonomous tractors, mowers, and other outdoor equipment by processing onboard sensor data and running real-time AI algorithms on the edge. Developers benefit from hardware-accelerated SDKs like Isaac ROS and the Jetson Generative AI Lab, which offer open-source generative AI models. NVIDIA Isaac Sim tests outdoor scenarios and supports the creation of robot foundational models.
For bipedal and quadruped robots, pretrained foundational models like NVIDIA Project GR00T (Generalist Robot 00 Technology) will significantly improve robot capabilities such as perception, control, and decision-making. These models use tools such as Isaac Lab for robot learning and NVIDIA OSMO for cloud workflow orchestration. NVIDIA Metropolis also helps robots survey a work environment for large-scale inspection tasks.
NVIDIA has announced a new partnership with Open Robotics to launch the Open Source Robotics Alliance. This will enable us to continue to bring accelerated computing and AI to open-source robotics.
NVIDIA software—Omniverse, Metropolis, Isaac and cuOpt—combine to create an AI gym where robots and AI agents can work out and be evaluated in complex industrial spaces.
The Husky robot from Clearpath Robotics is a four-wheeled platform made for research. It's simple to modify by adding other sensors and changing the high-level board. Learn how to use the official ROS 2 Husky packages to import the robot into NVIDIA Isaac Sim and create a simulation.
Clearpath Robotics, by Rockwell Automation
Using NVIDIA Omniverse and Universal Scene Description (OpenUSD), Delta is virtually linking production lines, aggregating 3D data from a diverse range of equipment to create a digital twin. Then, Delta uses NVIDIA Isaac Sim to generate physically accurate, photorealistic synthetic data for training their computer vision models and simulating the performance of their inspection cameras.
Learn about the NVIDIA Isaac platform for robotics and the corresponding accelerated computing hardware that makes it possible.
NVIDIA Isaac Sim is a powerful robotics software suite that combines synthetic data generation, simulation, reinforcement learning, perception, and testing. It provides a comprehensive solution that integrates tools for robot perception, motion planning, system integration, foundation models, and generative AI.
NVIDIA Jetson is a complete system-on-module (SOM) that includes a GPU, CPU, memory, power management, high-speed interfaces, and more. These modules are available in a wide range of performance, power efficiency, and form factors for use across all industries.
Simulate ground-truth perception and physics-based sensors made possible with NVIDIA RTX™ ray tracing and NVIDIA PhysX®. Accurate sensor emulation is the backbone for training robotics AI in a high-fidelity simulation environment, enabling synthetic data generation and robot learning.
AI for robotics is trained in the cloud using Omniverse Cloud (OVX), with the help of orchestration platforms such as NVIDIA OSMO for multi-container support. For ultimate performance, deploy AI workloads on NVIDIA Cloud, on-premises, or with a preferred CSP.
NVIDIA Jetson, with its broad and diverse user base and partner ecosystem, has helped drive a revolution in robotics and AI at the edge…As application requirements become increasingly complex, we need a foundational shift to platforms that simplify and accelerate the creation of edge deployments. This significant software expansion by NVIDIA gives developers access to new multi-sensor models and generative AI capabilities.
— Jim McGregor, principal analyst at Tirias Research
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
Learn how companies use NVIDIA’s robotics solutions across industries to optimize processes, reduce risk, and trim costs.
Amazon Robotics is building digital twins of their warehouses using NVIDIA technology to better optimize warehouse design, train intelligent robot assistants, and improve productivity.
Electronics manufacturer, Pegatron, is using NVIDIA AI and Omniverse to digitalize their factories. This helps them accelerate factory bring-up, minimize change orders, continuously optimize operations, and maximize production line throughput—all while reducing costs.
Monarch Tractor’s MK-V tractor, which uses the Jetson edge AI platform, combines electrification, automation, and data analysis to help farmers reduce their carbon footprint, improve field safety, streamline farming operations, and increase their bottom line.
Featured
A look at how NVIDIA robotics ecosystem partners are using NVIDIA Isaac Sim for their robotics simulation needs.
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.
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.
See how our experts can help your business unlock its full potential.
NVIDIA Privacy Policy