NVIDIA Isaac ROS

Open Ecosystem

Built on ROS

NVIDIA Isaac ROS is built on the open-source ROS 2™ software framework. This means the millions of developers in the ROS community can easily take advantage of NVIDIA-accelerated libraries and AI models to fast track their AI robot development and deployment workflows.

ROS is a trademark of Open Robotics

High-Throughput Perception

Isaac ROS provides a rich collection of individual ROS packages (GEMs) and complete pipelines (NITROS) optimized for NVIDIA GPUs and Jetson™ platforms. This helps you achieve more with reduced development times.

Modular, Flexible Packages

Plug and play with a selection of packages for computer vision, image processing, robust object detection, collision detection, and trajectory optimization and easily go to production.

The Power of NVIDIA AI

Isaac ROS is compatible with all ROS 2 nodes, making it easier to integrate into existing applications. Develop robotic applications using NVIDIA AI and pretrained models from robotics-specific datasets for faster development.

cuMotion for Robot Manipulation

Integrate NVIDIA® CUDA®-accelerated path planning for robotic arm-related tasks such as collision detection using robot masking and integrated trajectory optimization using the MoveIt motion-planning framework.

FoundationPose

Introducing our state-of-the-art foundational model for 6D pose estimation to detect novel objects. You now have an easier way to build applications that encounter prior unseen objects.

Multi-Camera Visual Inertial Odometry

This advanced solution allows for smarter localization for robots. They can quickly and accurately maintain knowledge of their position while accurately detecting and avoiding obstacles.

NVIDIA Isaac Transport for ROS (NITROS)

The latest Humble ROS 2 release improves performance on compute platforms that use hardware accelerators. It enables accelerated computing features for type adaptation and type negotiation, eliminating software/CPU overhead and improving performance of hardware acceleration.

The NVIDIA implementation of type adaption and negotiation is called NITROS, which are ROS processing pipelines made up of Isaac ROS hardware-accelerated modules (a.k.a. GEMs). The source code of NITROS is now available for developers to modify, extend, and use in your applications. H.264 video encode and decode hardware-accelerated packages for NITROS are used for compressed camera data recording and playback for development of AI models and perception functions. They compress two 1080p stereo cameras at 30fps (>120fps total) and reduce the data footprint by ~10X.

Boost performance with powerful pipelines that take advantage of hardware acceleration additions to ROS 2 Humble. You can find a complete performance summary here >

3D Scene Reconstruction With nvBlox

Knowledge of a robot’s position alone isn't enough to safely navigate complex environments. Robots must also be able to discover obstacles on their own. nvBlox uses RGB-D data to create a dense 3D representation of the robot's environment. It includes unforeseen obstacles that could cause a danger to the robot if not observed in real time. This data helps generate a temporal costmap for the navigation stack.

Stereo Perception

Stereo perception DNN-based GEMs are designed to help roboticists with common perception tasks.

Enhanced Semi-Supervised (ESS) stereo disparity is a DNN for stereo camera disparity prediction and Bi3D is a DNN for vision-based proximity detection.

Both are pre-trained for robotics applications using synthetic data and are intended for commercial use.

Mission Dispatch and Client

Isaac Mission Dispatch allows a cloud/edge system to send and monitor tasks from a ROS 2 robot with Isaac Mission Client using industry standards for production deployments. Mission Dispatch is a cloud-native microservice that can be integrated as part of larger fleet management systems.

Mission Dispatch and Mission Client are both available in open source and can be used to test robots in simulation for automating test portions of continuous integration and continuous deployments (CI/CD), performing a series of predefined tasks evaluated against expected results. This benefit is in addition to the primary usage of assigning tasks to robots in operation.

Mission Dispatch can be integrated into fleet management systems (e.g., Anyfleet, Roborunner FleetGateway) with Mission Client on the ROS 2 robot. It will also interoperate with other ROS 2 Clients built on VDA5050.